Anthropic Skills vs Codex Plugins

Agent ops

1. ai-native userMy agent can author and package a new skill end to end by following the project's own spec, template, or meta-skill

   weight 2 · round to Anthropic Skills
   Anthropic Skills✓fullclaimed9/10

   Anthropic ships a dedicated 'skill-creator' meta-skill for creating new skills and iteratively improving/benchmarking them, plus an official template SKILL.md and the open agentskills.io specification detailing required frontmatter, description rules, and folder structure (scripts/references/assets) — together these let an agent author and package a skill end-to-end per spec. Missing for 10: independent hands-on account of an agent successfully using skill-creator to author a new skill from scratch (community evidence only discusses skill triggering/invocation issues, not authoring/packaging).

   • [claimed-docs] “A skill for creating new skills and iteratively improving them.”
   • [claimed-docs] “benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy”
   • [claimed-docs] “Create new skills, modify and improve existing skills, and measure skill performance.”
   • [claimed-docs] “Replace with description of the skill and when Claude should use it.”
   • [claimed-docs] “The required `description` field: Must be 1-1024 characters, Should describe both what the skill does and when to use it”
   • [claimed-docs] “A skill is a directory containing, at minimum, a `SKILL.md` file”
   • [claimed-docs] “name: skill-name description: A description of what this skill does and when to use it.”
   • [claimed-docs] “The `SKILL.md` file must contain YAML frontmatter followed by Markdown content.”
   • [claimed-docs] “scripts/ # Optional: executable code references/ # Optional: documentation assets/ # Optional: templates, resources”
   • [claimed-docs] “add a skill, and test it locally using the \`--plugin-dir\` flag”

   proof ↗⚑ flag

   Codex Plugins✓fullcommunity8/10

   Docs describe a full authoring pipeline: SKILL.md spec with required fields, a plugin-creator/skill-creator meta-skill that scaffolds .codex-plugin/plugin.json and MCP wiring, a recorder that drafts a skill from a demonstration, skill-installer for distribution, and a submission portal for publishing, matching author-and-package-end-to-end via the project's own spec, template, or meta-skill. Community comments corroborate real users creating and customizing skills with the skill-creator skill. Missing for 10: independent hands-on verification of the full creator-to-published-package flow, and more detail on packaging/versioning nuances beyond the manifest.

   • [claimed-docs] “For the fastest setup, use the built-in `@plugin-creator` skill. It scaffolds the required `.codex-plugin/plugin.json` manifest and can also…”
   • [claimed-docs] “A skill is a directory with a `SKILL.md` file plus optional scripts and references. The `SKILL.md` file must include `name` and `description…”
   • [claimed-docs] “The plugin-creator skill will create the plugin folder, create the required `.codex-plugin/plugin.json`, and add MCP server wiring for the p…”
   • [claimed-docs] “The recorder captures the workflow, inspects the steps, and drafts a reusable skill from the demonstration.”
   • [claimed-docs] “It scaffolds the required `.codex-plugin/plugin.json` manifest and can also generate a local marketplace entry for testing.”
   • [claimed-docs] “For the fastest setup, use the built-in `@plugin-creator` skill. It scaffolds the required `.codex-plugin/plugin.json` manifest”
   • [claimed-docs] “For a portable Agent Plugins package, add `plugin.json` at the plugin root and declare the Agent Plugins schema.”
   • [claimed-docs] “Use the plugin submission portal to submit a plugin for review when you're ready to publish it for public use.”
   • [community] “The skills that matter most to me are the ones I create myself (with the skill creator skill) that are very specific and proprietary... I mi…”

   proof ↗⚑ flag

2. ai-native userMy coding agent can install a skill by itself — a non-interactive, promptless install path an agent can run headlessly end to end

   weight 3 · round to Codex Plugins
   Anthropic Skills~partialclaimed4/10

   Docs show scriptable install commands (`/plugin marketplace add`, `/plugin install ...`) and a Skills API for uploading/managing skills programmatically, which could in principle be run non-interactively by automation. However, none of the evidence explicitly documents a promptless, fully headless end-to-end install flow (e.g., a CLI flag or API call an agent invokes autonomously without any human-run slash command or confirmation step). Missing for 10: explicit non-interactive/headless install documentation, evidence of an agent autonomously choosing and installing a skill without human-issued commands, and confirmation that no interactive confirmation/prompt is required during install.

   • [claimed-docs] “/plugin marketplace add ./my-marketplace /plugin install quality-review-plugin@my-plugins”
   • [claimed-docs] “/plugin install quality-review-plugin@my-plugins”
   • [claimed-docs] “Upload and manage through the [Skills API](https://platform.claude.com/docs/en/api/skills/create)”
   • [claimed-docs] “Upload and manage through the [Skills API]”
   • [github] “You can register this repository as a Claude Code Plugin marketplace by running the following command in Claude Code: /plugin marketplace a…”
   • [github] “/plugin install document-skills@anthropic-agent-skills /plugin install example-skills@anthropic-agent-skills”
   • [github] “/plugin marketplace add anthropics/skills”

   proof ↗⚑ flag

   Codex Plugins~partialclaimed5/10

   Docs show a `$skill-installer` skill and a `codex plugin marketplace add` CLI command that let a skill/plugin be installed by name without manual UI browsing (codex-plugins-docs-8, docs-11, docs-14, docs-21, docs-34), suggesting an agent could invoke these programmatically. However, none of the evidence confirms a fully non-interactive, promptless, end-to-end headless flow (e.g., a scripted CLI flag bypassing any session/config prompts, or documentation stating the agent can trigger this without human involvement) — install flows described (docs-25, docs-26) still reference starting a 'new session' via CLI/chat interaction rather than a scripted automation path. Missing for 10: explicit headless/CI-style install command or flag, confirmation the agent can self-invoke skill-installer without any human step, and evidence no interactive confirmation/prompt is required during install.

   • [claimed-docs] “To add curated skills beyond the built-ins for your own local Codex setup, use `$skill-installer`.”
   • [claimed-docs] “Use `codex plugin marketplace add` to add and track a marketplace source instead of editing `config.toml` by hand.”
   • [claimed-docs] “To add curated skills beyond the built-ins for your own local Codex setup, use `$skill-installer`. For example, to install the `$linear` ski…”
   • [claimed-docs] “$skill-installer linear”
   • [claimed-docs] “In Codex CLI, enter `/plugins` to open the plugin browser. Install a plugin from a configured marketplace, then start a new session before u…”
   • [claimed-docs] “Curated skills can be installed by name (defaults to `skills/.curated`): $skill-installer gh-address-comments ”

   proof ↗⚑ flag

Agent access

1. ai-native userPoint an agent at llms.txt or agent-oriented docs

   weight 2 · round to Anthropic Skills
   Anthropic Skills✓fullprobed8/10

   Anthropic's docs site serves a working llms.txt (HTTP 200) plus .md variants of docs pages (e.g. skills.md), explicitly designed for agent/LLM consumption, and Claude Code skills follow the agentskills.io open spec. missing for 10: no independent/community confirmation that agents were actually pointed at llms.txt and successfully used it end-to-end.

   • [probe] “PROBE llms.txt: HTTP 200 at https://code.claude.com/llms.txt # Claude Code Docs > Official documentation for Claude Code, Anthropic's agent…”
   • [probe] “PROBE docs-md: HTTP 200 at https://code.claude.com/docs/en/skills.md > ## Documentation Index > Fetch the complete documentation index at: h…”
   • [claimed-docs] “Claude Code skills follow the [Agent Skills](https://agentskills.io) open standard, which works across multiple AI tools.”

   proof ↗⚑ flag

   Codex Plugins~partialprobed5/10

   Codex documentation itself is published as llms.txt/agent-oriented markdown (developers.openai.com/llms.txt returns 200 and indexes markdown docs), showing the product's own docs are agent-consumable, but there is no evidence that a Codex plugin/agent can be pointed at an arbitrary external llms.txt or agent-oriented docs site to ingest and act on it as a user-directed capability. missing for 10: explicit feature/skill letting a user supply/point the agent at a third-party llms.txt or docs URL for ingestion, and any hands-on confirmation of this workflow beyond the docs' own self-hosting.

   • [probe] “PROBE llms.txt: HTTP 200 at https://developers.openai.com/llms.txt # OpenAI Developers > Complete documentation hub for OpenAI API, Ads, Pl…”
   • [probe] “PROBE docs-md: HTTP 200 at https://developers.openai.com/codex/skills.md # Build skills > For the complete documentation index, see [llms.t…”
   • [claimed-docs] “Codex scans `.agents/skills` in every directory from your current working directory up to the repository root.”

   proof ↗⚑ flag

2. ai-native userRun the product headlessly / in CI for automation

   weight 2 · round to Anthropic Skills
   Anthropic Skills~partialclaimed5/10

   Skills can be invoked programmatically via the Messages API (`container` parameter, Skills API for upload/management), which is inherently headless and scriptable, implying CI/automation use is possible. However, there is no explicit documentation or example of running Skills in a CI pipeline, headless mode, or automated build system — missing for 10: explicit CI/headless workflow examples, CLI flags for non-interactive automation, and independent evidence of production CI usage.

   • [claimed-docs] “You specify Skills in the `container` parameter with a `skill_id`, `type`, and optional `version`, and they run in the code execution enviro…”
   • [claimed-docs] “Skills are specified using the `container` parameter in the Messages API. You can include up to 20 Skills for each request.”
   • [claimed-docs] “Upload and manage through the [Skills API](https://platform.claude.com/docs/en/api/skills/create)”
   • [claimed-docs] “You can include up to 20 Skills for each request.”
   • [claimed-docs] “This guide shows you how to use both pre-built and custom Skills with the Claude API.”

   proof ↗⚑ flag

   Codex Plugins—none0/10

   No evidence in the pack addresses running Codex Plugins headlessly or invoking it from CI/automation pipelines; all docs describe interactive install/browse flows (/plugins, /skills, plugin-creator) via CLI or ChatGPT UI. Missing for 10: any mention of a non-interactive/headless invocation mode, CI examples, or automation-friendly APIs for plugins/skills.

   • [claimed-docs] “In Codex CLI, enter `/plugins` to open the plugin browser.”
   • [claimed-docs] “In Codex CLI or the IDE extension, run `/skills` or type `$` to mention a skill.”
   • [claimed-docs] “In Codex CLI, enter `/plugins` to open the plugin browser. Install a plugin from a configured marketplace, then start a new session before u…”

   proof ↗⚑ flag

3. ai-native userPlug MCP servers into this product so it can use their tools

   weight 3 · round to Codex Plugins
   Anthropic Skills~partialcommunity5/10

   Docs show that Claude Code plugins — the packaging mechanism used alongside Skills — can bundle MCP servers together with skills, agents, and hooks (anthropic-skills-docs-6, -7, -21, -35), implying an ai-native user could add an MCP server via the plugin/marketplace system. However, Skills themselves are a separate mechanism (plain SKILL.md instructions), and community commentary explicitly notes skills and MCP are distinct, sometimes competing approaches with skills lacking MCP's tool-calling functionality (anthropic-skills-comm-3, -10). Missing for 10: concrete first-party guide/example of installing an MCP server via a skill or plugin, hands-on confirmation that MCP tools become usable once added this way, and clarity on whether Skills (as opposed to Claude Code plugins broadly) directly expose MCP tool use.

   • [claimed-docs] “Create custom plugins to extend Claude Code with skills, agents, hooks, and MCP servers.”
   • [claimed-docs] “Plugins (self-contained directories with skills, agents, hooks, or a `.claude-plugin/plugin.json` manifest) | `/plugin-name:hello` | Sharing…”
   • [claimed-docs] “Plugins let you extend Claude Code with custom functionality that can be shared across projects and teams. This guide covers creating your o…”
   • [claimed-docs] “Plugins let you extend Claude Code with custom functionality that can be shared across projects and teams.”
   • [community] “A skill is a markdown & yaml file on your filesystem... but skills don't cover a lot of the functionality that MCP offers.”
   • [community] “If you can write a bash or python script, or an API or MCP to do what you want, then write it and include it in the skill. Keep top-level co…”

   proof ↗⚑ flag

   Codex Plugins✓fullclaimed8/10

   Codex Plugins explicitly documents that plugins 'use the Model Context Protocol (MCP) to expose server-backed capabilities to ChatGPT and Codex,' with a plugin browser (/plugins), marketplace add command, and plugin-creator skill that 'adds MCP server wiring' — showing first-party, well-documented support for plugging in MCP servers and using their tools. missing for 10: independent hands-on verification of third-party MCP servers being installed and invoked successfully in Codex, and more detail on runtime tool-call behavior/limits.

   • [claimed-docs] “Plugins use the [Model Context Protocol (MCP)] to expose server-backed capabilities to ChatGPT and Codex.”
   • [claimed-docs] “The plugin-creator skill will create the plugin folder, create the required `.codex-plugin/plugin.json`, and add MCP server wiring for the p…”
   • [claimed-docs] “In Codex CLI, enter `/plugins` to open the plugin browser. Install a plugin from a configured marketplace, then start a new session before u…”
   • [claimed-docs] “Open the Plugins tab to browse and install plugins. After installation, you can use plugins in Chat or Work in ChatGPT, or in Codex. Install…”
   • [claimed-docs] “Use `codex plugin marketplace add` to add and track a marketplace source instead of editing `config.toml` by hand.”
   • [claimed-docs] “For the fastest setup, use the built-in `@plugin-creator` skill. It scaffolds the required `.codex-plugin/plugin.json` manifest and can also…”

   proof ↗⚑ flag

4. ai-native userUse an official CLI

   weight 2 · round to Codex Plugins
   Anthropic Skills~partialprobed5/10

   Skills are used and managed through Claude Code, which is described as a terminal-based agentic CLI tool, via slash commands like `/skill-name`, `/plugin marketplace add`, and `--plugin-dir` flags for local testing; the `skill-creator` skill also supports building/testing skills. However, there is no evidence of a dedicated standalone 'skills' CLI binary or command set (e.g., `skills create`, `skills validate`) separate from Claude Code's general slash-command interface, and API-based skill management (Skills API) is not CLI-based at all. Missing for 10: a purpose-built skills CLI tool, independent hands-on confirmation of CLI-based skill workflows, and CLI support outside the Claude Code product.

   • [claimed-docs] “Claude uses skills when relevant, or you can invoke one directly with `/skill-name`.”
   • [claimed-docs] “/plugin marketplace add ./my-marketplace /plugin install quality-review-plugin@my-plugins”
   • [claimed-docs] “add a skill, and test it locally using the \`--plugin-dir\` flag”
   • [claimed-docs] “A skill for creating new skills and iteratively improving them.”
   • [probe] “PROBE llms.txt: HTTP 200 at https://code.claude.com/llms.txt # Claude Code Docs > Official documentation for Claude Code, Anthropic's agent…”

   proof ↗⚑ flag

   Codex Plugins✓fullprobed8/10

   Codex Plugins documentation repeatedly references the official Codex CLI, including specific commands (/plugins, /skills, $skill-installer, codex plugin marketplace add) that let an AI-native user browse, install, and manage plugins/skills directly from the CLI, confirming an official CLI workflow exists and is documented as first-class. Missing for 10: independent hands-on confirmation of CLI usage beyond vendor docs, and a full command reference showing breadth of CLI capabilities.

   • [claimed-docs] “In Codex CLI, enter `/plugins` to open the plugin browser.”
   • [claimed-docs] “Use `codex plugin marketplace add` to add and track a marketplace source instead of editing `config.toml` by hand.”
   • [claimed-docs] “In Codex CLI or the IDE extension, run `/skills` or type `$` to mention a skill.”
   • [claimed-docs] “In Codex CLI, enter `/plugins` to open the plugin browser. Install a plugin from a configured marketplace, then start a new session before u…”
   • [claimed-docs] “To add curated skills beyond the built-ins for your own local Codex setup, use `$skill-installer`.”
   • [probe] “PROBE docs-md: HTTP 200 at https://developers.openai.com/codex/skills.md # Build skills > For the complete documentation index, see [llms.t…”

   proof ↗⚑ flag

5. ai-native userDrive the product through a documented public API

   weight 3 · round to Anthropic Skills
   Anthropic Skills✓fullclaimed8/10

   Skills can be driven via the documented Messages API `container` parameter with `skill_id`, uploaded/managed through a dedicated Skills API, and invoked with up to 20 skills per request, giving AI-native users a clear programmatic path distinct from the chat UI. missing for 10: independent/hands-on corroboration of the API workflow itself (community evidence only covers Claude Code skill-triggering reliability, not the Messages/Skills API), and no evidence of API rate limits, SDKs, or error handling specifics.

   • [claimed-docs] “You specify Skills in the `container` parameter with a `skill_id`, `type`, and optional `version`, and they run in the code execution enviro…”
   • [claimed-docs] “Skills are specified using the `container` parameter in the Messages API. You can include up to 20 Skills for each request.”
   • [claimed-docs] “Upload and manage through the [Skills API](https://platform.claude.com/docs/en/api/skills/create)”
   • [claimed-docs] “You can include up to 20 Skills for each request.”
   • [claimed-docs] “Upload and manage through the [Skills API]”
   • [claimed-docs] “This guide shows you how to use both pre-built and custom Skills with the Claude API.”

   proof ↗⚑ flag

   Codex Plugins—none0/10

   Evidence shows Codex Plugins uses MCP to let plugins expose capabilities *to* Codex/ChatGPT, and offers CLI commands (`codex plugin marketplace add`, `/plugins`) for local plugin management, but there is no documented public REST/GraphQL API for programmatically driving the Codex Plugins product itself — the direct OpenAPI probe returned 404 on all candidate spec paths, confirming no discoverable public API surface.

   • [probe] “PROBE openapi: all candidate paths 404 (https://developers.openai.com/openapi.json, https://developers.openai.com/swagger.json, https://deve…”
   • [claimed-docs] “Plugins use the [Model Context Protocol (MCP)] to expose server-backed capabilities to ChatGPT and Codex.”
   • [claimed-docs] “Use `codex plugin marketplace add` to add and track a marketplace source instead of editing `config.toml` by hand.”

   proof ↗⚑ flag

6. ai-native userBuild against official SDKs

   weight 2 · round to Anthropic Skills
   Anthropic Skills✓fullclaimed7/10

   Docs describe a dedicated Skills API and Messages API `container` parameter for programmatically attaching Skills (with `skill_id`, versioning, up to 20 per request), plus upload/management endpoints, which constitutes an official API/SDK surface to build against. Missing for 10: explicit language-specific SDK code samples (Python/TypeScript) and independent hands-on developer reports confirming building production integrations against this API.

   • [claimed-docs] “You specify Skills in the `container` parameter with a `skill_id`, `type`, and optional `version`, and they run in the code execution enviro…”
   • [claimed-docs] “Skills are specified using the `container` parameter in the Messages API. You can include up to 20 Skills for each request.”
   • [claimed-docs] “Upload and manage through the [Skills API](https://platform.claude.com/docs/en/api/skills/create)”
   • [claimed-docs] “You can include up to 20 Skills for each request.”
   • [claimed-docs] “Upload and manage through the [Skills API]”
   • [claimed-docs] “This guide shows you how to use both pre-built and custom Skills with the Claude API.”

   proof ↗⚑ flag

   Codex Plugins~partialprobed5/10

   Codex Plugins has real developer-facing build documentation (plugin.json manifest schema, MCP-based server wiring, plugin-creator scaffolding tool, submission portal, marketplace CLI) that lets developers build against an official plugin/skill framework, but this is a manifest/CLI-based plugin system rather than a formal client SDK, and the probe found no OpenAPI/API spec artifact. missing for 10: an actual downloadable/importable SDK library (e.g. Python/JS package), versioned API reference, and independent hands-on confirmation that third-party devs successfully build with it.

   • [claimed-docs] “For the fastest setup, use the built-in `@plugin-creator` skill. It scaffolds the required `.codex-plugin/plugin.json` manifest and can also…”
   • [claimed-docs] “The plugin-creator skill will create the plugin folder, create the required `.codex-plugin/plugin.json`, and add MCP server wiring for the p…”
   • [claimed-docs] “For a portable Agent Plugins package, add `plugin.json` at the plugin root and declare the Agent Plugins schema.”
   • [claimed-docs] “Plugins use the [Model Context Protocol (MCP)] to expose server-backed capabilities to ChatGPT and Codex.”
   • [claimed-docs] “Use the plugin submission portal to submit a plugin for review when you're ready to publish it for public use.”
   • [claimed-docs] “Use `codex plugin marketplace add` to add and track a marketplace source instead of editing `config.toml` by hand.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://developers.openai.com/openapi.json, https://developers.openai.com/swagger.json, https://deve…”

   proof ↗⚑ flag

Agentic features

1. ai-native userGet AI-generated insights and suggestions from my data inside the product

   weight 2 · round to Codex Plugins
   Anthropic Skills~partialcommunity4/10

   Skills can package data-handling capabilities (PDF, xlsx, docx extraction/manipulation) and are pitched for 'analyzing data using your organization's specific workflows,' giving Claude a path to generate insights from user data, but this is a general extensibility framework rather than a built-in insights/dashboard feature, and community reports show skills are frequently not invoked or unreliable in practice. missing for 10: a dedicated insights/analytics feature, proactive suggestion UI, and evidence that skills reliably surface unsolicited insights rather than requiring explicit triggering.

   • [claimed-docs] “Claude already knows a lot about understanding PDFs, but is limited in its ability to manipulate them directly (e.g. to fill out a form). Th…”
   • [claimed-docs] “Skills extend Claude’s capabilities by packaging your expertise into composable resources for Claude, transforming general-purpose agents in…”
   • [github] “whether that's creating documents with your company's brand guidelines, analyzing data using your organization's specific workflows, or auto…”
   • [github] “whether that's creating documents with your company's brand guidelines, analyzing data using your organization's specific workflows, or auto…”
   • [community] “Vercel found: In 56% of eval cases, the skill was never invoked. The agent had access to the documentation but didn't use it. Adding the ski…”
   • [community] “Same, I have a bunch of skills defined with proper YAML headers and semantic triggers... it's hit or miss if it picks up on the skill -- usu…”

   proof ↗⚑ flag

   Codex Plugins~partialclaimed6/10

   Codex Plugins connects to data sources (Gmail, Drive, Slack, Notion, Figma) and can summarize, draft, and act on that data via plugins/skills, giving AI-generated insights from connected data, but this is framed as tool-use/automation rather than a dedicated analytics/insights feature over the user's own stored data. missing for 10: no evidence of proactive dashboards, analytics summaries, or unprompted 'insights' generation from user data (e.g., trend detection, anomaly surfacing) beyond on-demand chat/skill invocation, and no independent hands-on validation of insight quality.

   • [claimed-docs] “Install the Gmail plugin to work with Gmail.”
   • [claimed-docs] “Install the Google Drive plugin to work across Drive, Docs, Sheets, and Slides.”
   • [claimed-docs] “Install the Slack plugin to summarize channels or draft replies.”
   • [github] “plugins/notion for planning, research, meetings, and knowledge capture”
   • [claimed-docs] “Install the Codex Security plugin to scan authorized code and confirm plausible vulnerability findings.”
   • [claimed-docs] “Plugins use the [Model Context Protocol (MCP)] to expose server-backed capabilities to ChatGPT and Codex.”

   proof ↗⚑ flag

2. ai-native userSet up automations that run autonomously in the background

   weight 2 · round drawn
   Anthropic Skills—none0/10

   Skills are packaged instructions/capabilities that Claude loads and uses during a session (invoked automatically or via /skill-name), but the evidence pack contains no mention of scheduling, triggers, or background/autonomous execution outside an active user session. Plugins and marketplaces cover distribution, not autonomous background automation.

   • [claimed-docs] “Create a `SKILL.md` file with instructions, and Claude adds it to its toolkit.”
   • [claimed-docs] “Claude uses skills when relevant, or you can invoke one directly with `/skill-name`.”
   • [claimed-docs] “If Claude thinks the skill is relevant to the current task, it will load the skill by reading its full `SKILL.md` into context.”

   proof ↗⚑ flag

   Codex Plugins—none0/10

   The evidence describes installable plugins, skills, and MCP tool wiring, but nothing shows Codex Plugins can be configured to run autonomously in the background without a user-initiated session — sessions must be started manually after installation (docs-25) and skill triggers are described in terms of manual invocation (/skills, $mentions) rather than scheduled/autonomous execution. Missing for 10: any scheduler/cron/trigger mechanism, background/always-on execution mode, or evidence of unattended autonomous runs.

   • [claimed-docs] “In Codex CLI, enter `/plugins` to open the plugin browser. Install a plugin from a configured marketplace, then start a new session before u…”
   • [claimed-docs] “The creator asks what the skill does, when it should trigger, and whether it should stay instruction-only or include scripts.”
   • [claimed-docs] “In Codex CLI or the IDE extension, run `/skills` or type `$` to mention a skill.”

   proof ↗⚑ flag

3. ai-native userDelegate tasks to a built-in AI assistant inside the product

   weight 3 · round to Codex Plugins
   Anthropic Skills!disputedcontradicted5/10

   Anthropic's docs claim Claude will autonomously discover and load relevant Skills to perform delegated work ('Claude uses skills when relevant... transforms general-purpose agents into specialized agents'), which matches the story of delegating tasks to a built-in assistant. However, hands-on community reports directly contradict reliable automatic delegation: a Vercel eval found the skill was never invoked in 56% of cases despite being available, and multiple users report invocation is 'hit or miss' even with proper YAML triggers, often requiring explicit manual pointers. Missing for 10: independent benchmarks showing consistent autonomous task delegation, and resolution of the documented invocation-reliability gap.

   • [claimed-docs] “Claude uses skills when relevant, or you can invoke one directly with `/skill-name`.”
   • [claimed-docs] “Skills extend Claude’s capabilities by packaging your expertise into composable resources for Claude, transforming general-purpose agents in…”
   • [community] “Vercel found: In 56% of eval cases, the skill was never invoked. The agent had access to the documentation but didn't use it. Adding the ski…”
   • [community] “I have an incredibly hard time getting them to use Skills at all, even when asked. I saw someone's analysis finding their agents were more a…”
   • [community] “Same, I have a bunch of skills defined with proper YAML headers and semantic triggers... it's hit or miss if it picks up on the skill -- usu…”

   proof ↗⚑ flag

   Codex Plugins✓fullclaimed7/10

   Codex ships a built-in AI assistant (Codex itself) that can be extended via installed plugins to delegate tasks such as summarizing Slack channels, searching Gmail, working across Drive/Docs, or messaging via iMessage, all invoked directly from Codex CLI/chat sessions after installation. Docs also show skills and MCP-backed plugin tools becoming available to Codex for task delegation without leaving the product. missing for 10: independent/hands-on evidence of reliable end-to-end task delegation (community comments focus on skills' pros/cons in general, not on Codex-plugin delegation specifically), and no benchmark of assistant task success rates.

   • [claimed-docs] “Install the Gmail plugin to work with Gmail.”
   • [claimed-docs] “Install the Google Drive plugin to work across Drive, Docs, Sheets, and Slides.”
   • [claimed-docs] “Install the Slack plugin to summarize channels or draft replies.”
   • [claimed-docs] “it can read and search iMessage, SMS, and RCS chats on your Mac and send messages on your behalf through the Messages app”
   • [claimed-docs] “Open the Plugins tab to browse and install plugins. After installation, you can use plugins in Chat or Work in ChatGPT, or in Codex. Install…”
   • [claimed-docs] “In Codex CLI, enter `/plugins` to open the plugin browser. Install a plugin from a configured marketplace, then start a new session before u…”

   proof ↗⚑ flag

4. ai-native userOperate the product with natural-language commands

   weight 2 · round to Codex Plugins
   Anthropic Skills!disputedcontradicted5/10

   Anthropic's docs explicitly promise natural-language operation: Claude 'uses skills when relevant' by matching the task to a skill's description, in addition to explicit `/skill-name` invocation (anthropic-skills-docs-2, -3, -25, -34). However, hands-on community reports concretely contradict this: a Vercel eval found skills were never invoked in 56% of cases despite being available, and multiple practitioners report skills are 'hit or miss' or require explicitly telling Claude to use them even when asked (anthropic-skills-comm-7, -8, -9). Missing for 10: reliable first-party benchmark of natural-language trigger accuracy, and resolution of the discovery/triggering inconsistency reported by users.

   • [claimed-docs] “Claude uses skills when relevant, or you can invoke one directly with `/skill-name`.”
   • [claimed-docs] “Skills add optional features: a directory for supporting files, frontmatter to [control whether you or Claude invokes them]... and the abili…”
   • [claimed-docs] “If Claude thinks the skill is relevant to the current task, it will load the skill by reading its full `SKILL.md` into context.”
   • [claimed-docs] “frontmatter to [control whether you or Claude invokes them](#control-who-invokes-a-skill)”
   • [community] “Vercel found: In 56% of eval cases, the skill was never invoked. The agent had access to the documentation but didn't use it. Adding the ski…”
   • [community] “I have an incredibly hard time getting them to use Skills at all, even when asked. I saw someone's analysis finding their agents were more a…”
   • [community] “Same, I have a bunch of skills defined with proper YAML headers and semantic triggers... it's hit or miss if it picks up on the skill -- usu…”

   proof ↗⚑ flag

   Codex Plugins✓fullcommunity7/10

   Docs show plugins/skills are used conversationally in ChatGPT/Codex chat (e.g., 'summarize channels or draft replies', skills auto-triggering based on natural-language description matching) alongside slash commands (/plugins, /skills) for management, indicating natural-language operation is the primary interaction mode. missing for 10: independent/hands-on confirmation that natural-language triggering reliably works, and clarification on how much slash/$ syntax is required vs pure natural language.

   • [claimed-docs] “Install the Slack plugin to summarize channels or draft replies.”
   • [claimed-docs] “The creator asks what the skill does, when it should trigger, and whether it should stay instruction-only or include scripts.”
   • [claimed-docs] “In Codex CLI or the IDE extension, run `/skills` or type `$` to mention a skill.”
   • [claimed-docs] “Open the Plugins tab to browse and install plugins. After installation, you can use plugins in Chat or Work in ChatGPT, or in Codex. Install…”
   • [community] “Skills are the matrix scene where neo learns kungfu. Imagine they are a database of specialized knowledge that can an agent can instantly ta…”

   proof ↗⚑ flag

Api quality

1. ai-native userDownload a machine-readable API spec (OpenAPI or equivalent)

   weight 2 · round to Anthropic Skills
   Anthropic Skills~partialclaimed3/10

   The evidence shows an open, machine-readable specification document (agentskills.io/specification.md) defining the SKILL.md format and frontmatter fields, plus references to a 'Skills API' for programmatic upload/management — these are the closest analogs to a downloadable machine-readable spec, but neither is an OpenAPI document nor explicitly offered as a downloadable API spec for the Skills/Messages API itself. Missing for 10: an actual OpenAPI/JSON-schema file for the Skills API endpoints, explicit download link/format, and independent confirmation that AI-native tooling consumes it.

   • [claimed-docs] “The required `description` field: Must be 1-1024 characters, Should describe both what the skill does and when to use it”
   • [claimed-docs] “A skill is a directory containing, at minimum, a `SKILL.md` file”
   • [claimed-docs] “The `SKILL.md` file must contain YAML frontmatter followed by Markdown content.”
   • [claimed-docs] “Upload and manage through the [Skills API](https://platform.claude.com/docs/en/api/skills/create)”
   • [claimed-docs] “This guide shows you how to use both pre-built and custom Skills with the Claude API.”

   proof ↗⚑ flag

   Codex Plugins—none0/10

   A direct probe for OpenAPI/swagger spec files at all standard paths returned 404, and no other evidence shows a downloadable machine-readable API spec for Codex Plugins; the plugin.json manifest and MCP protocol references describe plugin authoring, not a consumable API spec.

   • [probe] “PROBE openapi: all candidate paths 404 (https://developers.openai.com/openapi.json, https://developers.openai.com/swagger.json, https://deve…”

   proof ↗⚑ flag

2. ai-native userTest against a sandbox environment without touching production data

   weight 1 · round to Anthropic Skills
   Anthropic Skills~partialclaimed4/10

   Skills invoked via the Messages API run inside Anthropic's 'code execution environment' (a sandboxed container), and plugin docs mention testing skills locally with the `--plugin-dir` flag before sharing/distribution, which implies some separation from a live/production setup. However, there is no explicit documentation of a dedicated sandbox/staging environment for testing skills against non-production data, no discussion of data isolation guarantees, and no hands-on validation of this specific safety property. Missing for 10: explicit sandbox/staging environment documentation, data-isolation guarantees, and independent confirmation that local/test skill runs cannot touch production data.

   • [claimed-docs] “You specify Skills in the `container` parameter with a `skill_id`, `type`, and optional `version`, and they run in the code execution enviro…”
   • [claimed-docs] “add a skill, and test it locally using the \`--plugin-dir\` flag”
   • [claimed-docs] “Skills are specified using the `container` parameter in the Messages API. You can include up to 20 Skills for each request.”

   proof ↗⚑ flag

   Codex Plugins—none0/10

   No evidence of a sandbox/staging environment for testing plugins or skills against non-production data; docs only mention 'local marketplace entry for testing' which refers to plugin discovery/distribution, not data isolation from production systems.

   ⚑ flag

3. ai-native userRely on versioned APIs with a documented deprecation policy

   weight 2 · round drawn
   Anthropic Skills—none0/10

   Evidence covers Skills' structure, plugins, marketplaces, and API usage, but there is no mention of API versioning schemes or a documented deprecation policy for Skills/Claude API. Missing for 10: any documentation of API version numbers, backward-compatibility guarantees, or deprecation timelines/policy.

   ⚑ flag

   Codex Plugins—none0/10

   No evidence of API versioning scheme or a documented deprecation policy for Codex Plugins; the probe for an OpenAPI spec even returned 404s across all candidate paths, and docs only cover plugin/skill creation and usage, not lifecycle/versioning guarantees.

   • [probe] “PROBE openapi: all candidate paths 404 (https://developers.openai.com/openapi.json, https://developers.openai.com/swagger.json, https://deve…”

   proof ↗⚑ flag

1. ai-native userPerform bulk operations across many items at once

   weight 2 · round to Anthropic Skills
   Anthropic Skills~partialcommunity3/10

   Skills can bundle scripts that operate on multiple files (e.g., the PDF skill 'merges multiple PDFs' and fills forms across documents), suggesting some batch/bulk-processing capability, and skills may include arbitrary scripts/executable code for such tasks. However, there is no explicit documentation or example demonstrating bulk operations across many items (e.g., batch-processing hundreds of records/files) as a core Skills feature, and community feedback focuses on skill-triggering reliability rather than bulk-processing performance. Missing for 10: explicit bulk/batch-processing examples or docs, evidence of scale (many items processed reliably), and independent confirmation that bulk workflows work as intended.

   • [claimed-docs] “Claude already knows a lot about understanding PDFs, but is limited in its ability to manipulate them directly (e.g. to fill out a form). Th…”
   • [claimed-docs] “skills can bundle additional files within the skill directory and reference them by name from `SKILL.md`.”
   • [claimed-docs] “scripts/ # Optional: executable code references/ # Optional: documentation assets/ # Optional: templates, resources”
   • [community] “If you can write a bash or python script, or an API or MCP to do what you want, then write it and include it in the skill. Keep top-level co…”

   proof ↗⚑ flag

   Codex Plugins—none0/10

   Evidence covers plugin/skill installation, marketplace browsing, and per-item workflows (Slack summarization, Drive docs, Notion, etc.), but nothing describes performing an operation across many items/records/files at once (e.g., batch processing, multi-item automation loops). No batch or bulk-operation capability is documented or implied.

   ⚑ flag

2. ai-native userDefine rules that trigger actions automatically on events

   weight 3 · round to Codex Plugins
   Anthropic Skills!disputedcontradicted4/10

   Anthropic's docs claim skills auto-trigger ('Claude uses skills when relevant... loads it automatically') based on description matching, which is the closest analog to event-driven rule triggering in this product, but this is relevance-based context loading, not true event/webhook/schedule triggers. Hands-on community reports directly contradict reliability of this claimed automation: Vercel's eval found skills were never invoked in 56% of cases despite being applicable, and multiple users report 'hit or miss' triggering even with proper YAML triggers, sometimes requiring explicit manual invocation. Missing for 10: genuine event-based triggers (webhooks, schedules, file-watchers), reliable automatic invocation without manual prompting, and independent confirmation that trigger accuracy is dependable in production.

   • [claimed-docs] “Claude uses skills when relevant, or you can invoke one directly with `/skill-name`.”
   • [claimed-docs] “If Claude thinks the skill is relevant to the current task, it will load the skill by reading its full `SKILL.md` into context.”
   • [community] “Vercel found: In 56% of eval cases, the skill was never invoked. The agent had access to the documentation but didn't use it. Adding the ski…”
   • [community] “I have an incredibly hard time getting them to use Skills at all, even when asked. I saw someone's analysis finding their agents were more a…”
   • [community] “Same, I have a bunch of skills defined with proper YAML headers and semantic triggers... it's hit or miss if it picks up on the skill -- usu…”

   proof ↗⚑ flag

   Codex Plugins~partialclaimed3/10

   Skill creation asks the author to define 'when it should trigger' (docs-7), implying some contextual auto-invocation logic, but all other evidence shows skills/plugins being invoked manually via `/skills`, `$` mention, or `/plugins` browser rather than firing automatically on external events like schedules, webhooks, or file changes. Missing for 10: explicit event-trigger/automation-rule mechanism (e.g., cron, webhook, file-watch), documentation of autonomous invocation without user prompt, and independent confirmation that trigger conditions actually fire without manual mention.

   • [claimed-docs] “The creator asks what the skill does, when it should trigger, and whether it should stay instruction-only or include scripts.”
   • [claimed-docs] “In Codex CLI or the IDE extension, run `/skills` or type `$` to mention a skill.”
   • [claimed-docs] “In Codex CLI, enter `/plugins` to open the plugin browser.”

   proof ↗⚑ flag

3. ai-native userSchedule recurring jobs or workflows

   weight 2 · round drawn
   Anthropic Skills—none0/10

   The evidence pack describes Skills as on-demand or auto-triggered instruction modules invoked by Claude during a task (via /skill-name, semantic triggering, or API container calls), but nothing describes a scheduler, cron-like trigger, or persistent recurring job mechanism. Automation-depth for scheduling is a fair ask for an agentic tool, but no evidence shows Skills or Claude Code support recurring/scheduled execution.

   • [claimed-docs] “Claude uses skills when relevant, or you can invoke one directly with `/skill-name`.”
   • [claimed-docs] “If Claude thinks the skill is relevant to the current task, it will load the skill by reading its full `SKILL.md` into context.”
   • [claimed-docs] “`/run` and `/verify` work without setup. They infer the launch from your project type (CLI, server, TUI, browser-driven) and from what's in …”

   proof ↗⚑ flag

   Codex Plugins—none0/10

   The evidence pack covers plugin installation, MCP wiring, and skill creation/curation, but there is no mention of scheduling, cron-like triggers, or recurring/automated workflow execution anywhere in the docs or community items.

   ⚑ flag

4. ai-native userVersion, review, and roll back my automations

   weight 1 · round to Anthropic Skills
   Anthropic Skills~partialclaimed4/10

   Docs mention plugin marketplaces provide 'version tracking' and 'versioned releases', and the API lets you specify an optional `version` for skill_id, implying some versioning support. However there is no documented review/approval workflow or explicit rollback mechanism — skills are just files/folders, so any versioning or rollback would rely on external git tooling not described as a first-class feature. missing for 10: explicit rollback command/feature, in-product review or approval workflow for skill changes, changelog/diff tooling, independent confirmation of version tracking in practice.

   • [claimed-docs] “A **plugin marketplace** is a catalog that lets you distribute plugins to others. Marketplaces provide centralized discovery, version tracki…”
   • [claimed-docs] “Marketplaces provide centralized discovery, version tracking, automatic updates, and support for multiple source types, including git reposi…”
   • [claimed-docs] “You specify Skills in the `container` parameter with a `skill_id`, `type`, and optional `version`, and they run in the code execution enviro…”
   • [claimed-docs] “Plugins (self-contained directories with skills, agents, hooks, or a `.claude-plugin/plugin.json` manifest) | `/plugin-name:hello` | Sharing…”

   proof ↗⚑ flag

   Codex Plugins—none0/10

   Evidence describes creating, installing, and browsing skills/plugins (SKILL.md files, `.agents/skills` directories, marketplace add/track commands) but contains no mention of version history, diffing/review workflows, or rollback/undo mechanisms for skills or plugins. Being file-based artifacts implies they could be manually versioned with external tools like git, but no such capability is documented as a product feature.

   • [claimed-docs] “A skill is a directory with a `SKILL.md` file plus optional scripts and references. The `SKILL.md` file must include `name` and `description…”
   • [claimed-docs] “Codex scans `.agents/skills` in every directory from your current working directory up to the repository root.”
   • [claimed-docs] “Use `codex plugin marketplace add` to add and track a marketplace source instead of editing `config.toml` by hand.”
   • [claimed-docs] “It scaffolds the required `.codex-plugin/plugin.json` manifest and can also generate a local marketplace entry for testing.”

   proof ↗⚑ flag

Portability

1. developerInstall the same collection into multiple different coding agents — Claude Code, Codex, Cursor, and others — with per-harness instructions

   weight 3 · round to Anthropic Skills
   Anthropic Skills~partialclaimed4/10

   Docs state Claude Code skills follow the open 'Agent Skills' standard which 'works across multiple AI tools' (agentskills.io spec), implying cross-agent portability, and the spec itself defines a tool-agnostic SKILL.md format. However, there is no concrete evidence of per-harness install instructions or documented support for Codex, Cursor, or other named agents — all install/marketplace instructions (plugin marketplace, /plugin install, container skill_id) are Claude-specific. Missing for 10: explicit Codex/Cursor installation docs, per-harness setup instructions, and independent confirmation that the same skill collection actually runs unmodified in non-Anthropic tools.

   • [claimed-docs] “Claude Code skills follow the [Agent Skills](https://agentskills.io) open standard, which works across multiple AI tools.”
   • [claimed-docs] “A skill is a directory containing, at minimum, a `SKILL.md` file”
   • [claimed-docs] “The `SKILL.md` file must contain YAML frontmatter followed by Markdown content.”
   • [claimed-docs] “The required `description` field: Must be 1-1024 characters, Should describe both what the skill does and when to use it”

   proof ↗⚑ flag

   Codex Plugins—none0/10

   All evidence describes installing plugins/skills within OpenAI's own ecosystem (Codex CLI, ChatGPT desktop/Chat/Work) — there is no evidence of a single collection being installed into Claude Code, Cursor, or other third-party coding agents. In fact docs-32 implies the opposite: migrating an existing Claude Code plugin to OpenAI requires reviewing what needs to change, suggesting formats are not simply portable across harnesses.

   • [claimed-docs] “In Codex CLI, enter `/plugins` to open the plugin browser.”
   • [claimed-docs] “In Codex CLI, enter `/plugins` to open the plugin browser. Install a plugin from a configured marketplace, then start a new session before u…”
   • [claimed-docs] “Open the Plugins tab to browse and install plugins. After installation, you can use plugins in Chat or Work in ChatGPT, or in Codex. Install…”
   • [claimed-docs] “If you're migrating an existing Claude Code plugin or connector, first review [Submit your Claude Code plugin to OpenAI] to see what you nee…”

   proof ↗⚑ flag

2. developerSkills are plain markdown files and folders I can read, copy, and carry to another harness — not a proprietary binary format

   weight 2 · round to Anthropic Skills
   Anthropic Skills✓fullclaimed9/10

   Docs confirm skills are just plain folders with a SKILL.md file (YAML frontmatter + markdown) plus optional scripts/references/assets, explicitly following the open Agent Skills standard (agentskills.io) that 'works across multiple AI tools,' and GitHub examples show these as ordinary files/folders anyone can read, copy, or fork. This directly supports the portability claim of non-proprietary, cross-harness markdown format. missing for 10: no independent hands-on report of someone actually carrying a skill folder to a different (non-Anthropic) harness and confirming it works unmodified.

   • [claimed-docs] “A skill is a directory containing, at minimum, a `SKILL.md` file”
   • [claimed-docs] “The `SKILL.md` file must contain YAML frontmatter followed by Markdown content.”
   • [claimed-docs] “scripts/ # Optional: executable code references/ # Optional: documentation assets/ # Optional: templates, resources”
   • [claimed-docs] “Claude Code skills follow the [Agent Skills](https://agentskills.io) open standard, which works across multiple AI tools.”
   • [github] “Skills are simple to create - just a folder with a `SKILL.md` file containing YAML frontmatter and instructions.”
   • [claimed-docs] “The required `description` field: Must be 1-1024 characters, Should describe both what the skill does and when to use it”

   proof ↗⚑ flag

   Codex Plugins~partialclaimed6/10

   Docs confirm skills are plain directories with a SKILL.md file plus optional scripts/references (not a proprietary binary), scanned from `.agents/skills` folders that teams can check into a repo alongside code, which supports the 'read/copy' portability claim. However, there is no explicit evidence describing moving a skill folder to a different harness (e.g., Claude Code) working out-of-the-box, and the plugin.json/MCP wiring layer around plugins is more proprietary/manifest-based than pure markdown. Missing for 10: explicit cross-harness carry demonstration, and clarity that plugin-level packaging (vs skill-level) is also portable.

   • [claimed-docs] “A skill is a directory with a `SKILL.md` file plus optional scripts and references. The `SKILL.md` file must include `name` and `description…”
   • [claimed-docs] “Codex scans `.agents/skills` in every directory from your current working directory up to the repository root.”
   • [claimed-docs] “teams can check in skills relevant to a working folder. For example, skills only relevant to a microservice or a module.”
   • [claimed-docs] “A skill packages instructions, resources, and optional scripts so either product can follow a workflow reliably.”
   • [claimed-docs] “If you're migrating an existing Claude Code plugin or connector, first review [Submit your Claude Code plugin to OpenAI] to see what you nee…”

   proof ↗⚑ flag

Discovery

1. developerBrowse or search a catalog of available skills — a registry, leaderboard, or marketplace listing — before installing anything

   weight 2 · round to Codex Plugins
   Anthropic Skills~partialclaimed6/10

   Anthropic provides a discoverable catalog via the official `anthropics/skills` GitHub repo (browsable list of example skills) and a formal 'plugin marketplace' concept described as providing 'centralized discovery, version tracking, automatic updates' that developers can add and install from (`/plugin marketplace add`, `/plugin install`). However, there's no evidence of a dedicated searchable registry UI, ratings/leaderboard, or cross-marketplace search — discovery is limited to browsing a GitHub repo or manually adding marketplace sources one at a time. Missing for 10: a searchable/filterable registry UI, popularity or leaderboard signals, and evidence of a unified cross-marketplace search experience.

   • [claimed-docs] “A **plugin marketplace** is a catalog that lets you distribute plugins to others. Marketplaces provide centralized discovery, version tracki…”
   • [claimed-docs] “/plugin marketplace add ./my-marketplace /plugin install quality-review-plugin@my-plugins”
   • [claimed-docs] “Marketplaces provide centralized discovery, version tracking, automatic updates, and support for multiple source types, including git reposi…”
   • [github] “You can register this repository as a Claude Code Plugin marketplace by running the following command in Claude Code: /plugin marketplace a…”
   • [github] “These example skills are all already available to paid plans in Claude.ai.”
   • [github] “/plugin install document-skills@anthropic-agent-skills /plugin install example-skills@anthropic-agent-skills”

   proof ↗⚑ flag

   Codex Plugins✓fullclaimed8/10

   Docs describe a `/plugins` command that opens a 'plugin browser' and a 'Plugins tab' to browse and install plugins in ChatGPT/Codex, backed by a marketplace.json listing plugin entries with categories and a `codex plugin marketplace add` CLI command; the openai/plugins GitHub repo also serves as a browsable catalog of available plugins (Figma, Notion, Expo, etc.). Missing for 10: independent/hands-on confirmation of the browsing UI's search/filter experience, and no evidence of ratings, leaderboards, or third-party marketplace aggregation beyond OpenAI's own listing.

   • [claimed-docs] “In Codex CLI, enter `/plugins` to open the plugin browser.”
   • [claimed-docs] “In Codex CLI, enter `/plugins` to open the plugin browser. Install a plugin from a configured marketplace, then start a new session before u…”
   • [claimed-docs] “Open the Plugins tab to browse and install plugins. After installation, you can use plugins in Chat or Work in ChatGPT, or in Codex. Install…”
   • [claimed-docs] “Use `codex plugin marketplace add` to add and track a marketplace source instead of editing `config.toml` by hand.”
   • [claimed-docs] “"name": "slack", ... "category": "Communication"”
   • [github] “plugins/figma for `use_figma`, Code to Canvas, Code Connect, and design system rules”
   • [github] “plugins/notion for planning, research, meetings, and knowledge capture”
   • [github] “`plugins/notion` for planning, research, meetings, and knowledge capture”
   • [github] “`plugins/expo` for Expo and React Native apps, SDK upgrades, EAS workflows, and Codex Run actions”

   proof ↗⚑ flag

Distribution

1. engineering-leadDistribute a standard skill set to my whole team — via a marketplace, a shared repo, or files committed to the project

   weight 2 · round drawn
   Anthropic Skills✓fullclaimed8/10

   Anthropic Skills supports distribution via plugin marketplaces (git repos or local paths), shared GitHub repos (e.g., anthropics/skills registered as a marketplace), and files committed directly to a project (.claude/skills/SKILL.md), covering all three distribution channels named in the story. Community feedback confirms real-world use of shared skill repos and marketplace installs, though adoption/triggering reliability is debated. missing for 10: independent case study of an engineering team formally rolling out a standardized skill set org-wide, and more detail on permissions/governance controls for enforcing a 'standard' team-wide set.

   • [claimed-docs] “A **plugin marketplace** is a catalog that lets you distribute plugins to others. Marketplaces provide centralized discovery, version tracki…”
   • [claimed-docs] “/plugin marketplace add ./my-marketplace /plugin install quality-review-plugin@my-plugins”
   • [claimed-docs] “Marketplaces provide centralized discovery, version tracking, automatic updates, and support for multiple source types, including git reposi…”
   • [github] “You can register this repository as a Claude Code Plugin marketplace by running the following command in Claude Code: /plugin marketplace a…”
   • [github] “/plugin install document-skills@anthropic-agent-skills /plugin install example-skills@anthropic-agent-skills”
   • [claimed-docs] “A file at `.claude/commands/deploy.md` and a skill at `.claude/skills/deploy/SKILL.md` both create `/deploy` and work the same way.”
   • [claimed-docs] “Plugins (self-contained directories with skills, agents, hooks, or a `.claude-plugin/plugin.json` manifest) | `/plugin-name:hello` | Sharing…”

   proof ↗⚑ flag

   Codex Plugins✓fullcommunity8/10

   Docs describe all three distribution channels: checking skills into a repo/working folder (`.agents/skills` scanning, docs-9/docs-17), a marketplace mechanism (`codex plugin marketplace add`, marketplace.json, docs-11/docs-35), and a public submission portal for org-wide plugins (docs-31). Community commentary corroborates skills being used for 'cross-team standardization' (comm-3). Missing for 10: independent case study of a team actually rolling out a shared marketplace/repo at scale, and more detail on permissioning/governance for team-wide distribution.

   • [claimed-docs] “teams can check in skills relevant to a working folder. For example, skills only relevant to a microservice or a module.”
   • [claimed-docs] “Codex scans `.agents/skills` in every directory from your current working directory up to the repository root.”
   • [claimed-docs] “Use `codex plugin marketplace add` to add and track a marketplace source instead of editing `config.toml` by hand.”
   • [claimed-docs] “It scaffolds the required `.codex-plugin/plugin.json` manifest and can also generate a local marketplace entry for testing.”
   • [claimed-docs] “Use the plugin submission portal to submit a plugin for review when you're ready to publish it for public use.”
   • [claimed-docs] “"name": "slack", ... "category": "Communication"”
   • [community] “Skills are not useful for single-shot cases. They are for: cross-team standardization (for LLM generated code), and reliable reusability of …”

   proof ↗⚑ flag

Triggering

1. developerInstalled skills trigger automatically from task context, with descriptions engineered so the agent activates the right skill at the right moment

   weight 3 · round to Codex Plugins
   Anthropic Skills!disputedcontradicted5/10

   Anthropic's docs explicitly describe automatic activation via engineered description fields (e.g. docs-17, docs-25, docs-32, docs-44) and even ship a skill-creator tool to optimize descriptions for 'triggering accuracy' (docs-14). However, hands-on community reports directly contradict reliable auto-triggering: Vercel's eval found the skill was never invoked in 56% of cases with no improvement over baseline, and multiple users report skills are 'hit or miss' or 'incredibly hard' to get invoked even with proper YAML descriptions (comm-7, comm-8, comm-9). missing for 10: independent benchmark showing consistent correct auto-activation, and resolution of the documented reliability gap.

   • [claimed-docs] “The required `description` field: Must be 1-1024 characters, Should describe both what the skill does and when to use it”
   • [claimed-docs] “If Claude thinks the skill is relevant to the current task, it will load the skill by reading its full `SKILL.md` into context.”
   • [claimed-docs] “benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy”
   • [claimed-docs] “description: Extracts text and tables from PDF files, fills PDF forms, and merges multiple PDFs. Use when working with PDF documents or when…”
   • [community] “Vercel found: In 56% of eval cases, the skill was never invoked. The agent had access to the documentation but didn't use it. Adding the ski…”
   • [community] “I have an incredibly hard time getting them to use Skills at all, even when asked. I saw someone's analysis finding their agents were more a…”
   • [community] “Same, I have a bunch of skills defined with proper YAML headers and semantic triggers... it's hit or miss if it picks up on the skill -- usu…”

   proof ↗⚑ flag

   Codex Plugins~partialcommunity7/10

   Docs describe the mechanics needed for context-triggered skills: SKILL.md requires a `description` field, the skill-creator explicitly asks 'when it should trigger,' and Codex scans `.agents/skills` up the directory tree for applicable skills, implying automatic, description-driven activation. However, evidence is mostly first-party docs plus manual invocation commands (`/skills`, `$mention`), and community commentary voices skepticism about reliability ('you just append more text to prompt and pray') without a concrete hands-on failure, so this stays partial rather than full/disputed. Missing for 10: independent hands-on verification that description-matching reliably picks the correct skill at the correct moment, and quantitative/real-world evidence of trigger accuracy.

   • [claimed-docs] “The creator asks what the skill does, when it should trigger, and whether it should stay instruction-only or include scripts.”
   • [claimed-docs] “A skill is a directory with a `SKILL.md` file plus optional scripts and references. The `SKILL.md` file must include `name` and `description…”
   • [claimed-docs] “Codex scans `.agents/skills` in every directory from your current working directory up to the repository root.”
   • [claimed-docs] “In Codex CLI or the IDE extension, run `/skills` or type `$` to mention a skill.”
   • [community] “Skills are the matrix scene where neo learns kungfu. Imagine they are a database of specialized knowledge that can an agent can instantly ta…”
   • [community] “At least MCPs can be unit tested. With Skills however, you just selectively append more text to prompt and pray.”

   proof ↗⚑ flag

Onboarding

1. developerA quickstart takes me from nothing to a working installed skill in under five minutes

   weight 3 · round drawn
   Anthropic Skills~partialcommunity6/10

   Docs and GitHub show a genuinely lightweight path — a skill is 'just a folder with a SKILL.md file containing YAML frontmatter and instructions' (anthropic-skills-gh-3), installable via a single 'plugin marketplace add' + 'plugin install' command (anthropic-skills-gh-1, anthropic-skills-gh-4), which plausibly fits a five-minute window. However there's no dedicated timed 'quickstart' tutorial artifact, and community feedback shows friction getting Claude to actually invoke/use a newly installed skill reliably (anthropic-skills-comm-8, anthropic-skills-comm-9), meaning 'installed and working' isn't fully guaranteed in five minutes. Missing for 10: an explicit timed quickstart doc/tutorial, and independent hands-on confirmation of sub-5-minute install-to-working success.

   • [github] “Skills are simple to create - just a folder with a `SKILL.md` file containing YAML frontmatter and instructions.”
   • [github] “You can register this repository as a Claude Code Plugin marketplace by running the following command in Claude Code: /plugin marketplace a…”
   • [github] “/plugin install document-skills@anthropic-agent-skills /plugin install example-skills@anthropic-agent-skills”
   • [claimed-docs] “Create a `SKILL.md` file with instructions, and Claude adds it to its toolkit.”
   • [community] “I have an incredibly hard time getting them to use Skills at all, even when asked. I saw someone's analysis finding their agents were more a…”
   • [community] “Same, I have a bunch of skills defined with proper YAML headers and semantic triggers... it's hit or miss if it picks up on the skill -- usu…”

   proof ↗⚑ flag

   Codex Plugins~partialclaimed6/10

   Docs describe simple single-command paths to install a skill (`$skill-installer <name>`, `/skills`, `/plugins`) and to scaffold one via `@plugin-creator`, suggesting a fast setup, but no source gives an explicit time-to-first-working-skill benchmark or a hands-on account confirming a sub-five-minute experience. Missing for 10: an explicit quickstart timing claim, a step-by-step first-run walkthrough, and independent/community confirmation that installation actually completes quickly.

   • [claimed-docs] “To add curated skills beyond the built-ins for your own local Codex setup, use `$skill-installer`.”
   • [claimed-docs] “To add curated skills beyond the built-ins for your own local Codex setup, use `$skill-installer`. For example, to install the `$linear` ski…”
   • [claimed-docs] “In Codex CLI or the IDE extension, run `/skills` or type `$` to mention a skill.”
   • [claimed-docs] “For the fastest setup, use the built-in `@plugin-creator` skill. It scaffolds the required `.codex-plugin/plugin.json` manifest”
   • [claimed-docs] “In Codex CLI, enter `/plugins` to open the plugin browser. Install a plugin from a configured marketplace, then start a new session before u…”

   proof ↗⚑ flag

2. developerEvery skill documents what it does and when it activates, so I can predict my agent's new behavior before it surprises me

   weight 2 · round to Codex Plugins
   Anthropic Skills!disputedcontradicted5/10

   Anthropic's spec strongly documents that every SKILL.md must include a description of what the skill does and when to use it (frontmatter is designed to be both machine- and human-readable for predicting activation), and Claude Code/Claude API docs describe controllable invocation triggers. However, multiple hands-on community reports (Vercel eval: skill never invoked in 56% of cases despite being documented and available; users reporting 'hit or miss' triggering even with well-written descriptions) concretely contradict the promise that documented descriptions reliably predict when the agent will actually activate a skill. missing for 10: consistent, benchmarked activation reliability matching documented triggers, and independent evidence resolving the invocation unpredictability reported by users.

   • [claimed-docs] “The required `description` field: Must be 1-1024 characters, Should describe both what the skill does and when to use it”
   • [claimed-docs] “name: skill-name description: A description of what this skill does and when to use it.”
   • [claimed-docs] “description: Extracts text and tables from PDF files, fills PDF forms, and merges multiple PDFs. Use when working with PDF documents or when…”
   • [claimed-docs] “Skills add optional features: a directory for supporting files, frontmatter to [control whether you or Claude invokes them]... and the abili…”
   • [community] “Vercel found: In 56% of eval cases, the skill was never invoked. The agent had access to the documentation but didn't use it. Adding the ski…”
   • [community] “I have an incredibly hard time getting them to use Skills at all, even when asked. I saw someone's analysis finding their agents were more a…”
   • [community] “Same, I have a bunch of skills defined with proper YAML headers and semantic triggers... it's hit or miss if it picks up on the skill -- usu…”

   proof ↗⚑ flag

   Codex Plugins~partialcommunity7/10

   Docs describe the SKILL.md format (must include name and description) and state that the skill-creation flow explicitly asks 'what the skill does, when it should trigger, and whether it should stay instruction-only,' directly matching the story's ask for documented behavior and activation conditions. However, there's no evidence of a consistent, enforced convention across all published skills/plugins for describing trigger conditions, and community commentary flags real unpredictability in skill activation ('you just selectively append more text to prompt and pray'), reflecting some doubt about whether documented behavior always matches actual activation. Missing for 10: independent/hands-on verification that documented triggers reliably predict actual activation, and evidence that all shipped skills (not just the creator flow) enforce clear 'when it activates' documentation.

   • [claimed-docs] “The creator asks what the skill does, when it should trigger, and whether it should stay instruction-only or include scripts.”
   • [claimed-docs] “A skill is a directory with a `SKILL.md` file plus optional scripts and references. The `SKILL.md` file must include `name` and `description…”
   • [claimed-docs] “Codex scans `.agents/skills` in every directory from your current working directory up to the repository root.”
   • [community] “At least MCPs can be unit tested. With Skills however, you just selectively append more text to prompt and pray.”

   proof ↗⚑ flag

Install

1. developerInstall a skill collection with one documented command — a package-manager one-liner, CLI, or in-agent marketplace command — and it is active in my next session

   weight 3 · round to Codex Plugins
   Anthropic Skills~partialclaimed6/10

   Anthropic documents a clear CLI install path — `/plugin marketplace add anthropics/skills` followed by `/plugin install document-skills@anthropic-agent-skills` — which registers and installs a skill collection inside Claude Code, and docs imply skills become part of Claude's toolkit thereafter. However, this is a two-step sequence rather than a single one-liner, and there is no independent/hands-on confirmation that the installed skill persists and is reliably active in the very next session (community reports focus on activation/triggering reliability, not install itself). Missing for 10: a true single-command one-liner, and first-party or community confirmation of session-persistence after install.

   • [github] “You can register this repository as a Claude Code Plugin marketplace by running the following command in Claude Code: /plugin marketplace a…”
   • [github] “/plugin install document-skills@anthropic-agent-skills /plugin install example-skills@anthropic-agent-skills”
   • [github] “/plugin marketplace add anthropics/skills”
   • [claimed-docs] “/plugin marketplace add ./my-marketplace /plugin install quality-review-plugin@my-plugins”
   • [claimed-docs] “/plugin install quality-review-plugin@my-plugins”
   • [claimed-docs] “A **plugin marketplace** is a catalog that lets you distribute plugins to others. Marketplaces provide centralized discovery, version tracki…”

   proof ↗⚑ flag

   Codex Plugins✓fullclaimed7/10

   Docs explicitly describe a one-command install flow — `/plugins` browser or `$skill-installer <name>` — and state that after installing a plugin you should 'start a new session before using its bundled skills or tools,' directly matching the story's install-then-next-session pattern. Additional CLI support (`codex plugin marketplace add`) reinforces multiple documented one-liner paths. Missing for 10: independent/hands-on confirmation that installed skills actually activate reliably in the next session (only vendor docs, no community verification of this specific flow).

   • [claimed-docs] “In Codex CLI, enter `/plugins` to open the plugin browser. Install a plugin from a configured marketplace, then start a new session before u…”
   • [claimed-docs] “To add curated skills beyond the built-ins for your own local Codex setup, use `$skill-installer`.”
   • [claimed-docs] “To add curated skills beyond the built-ins for your own local Codex setup, use `$skill-installer`. For example, to install the `$linear` ski…”
   • [claimed-docs] “$skill-installer linear”
   • [claimed-docs] “Use `codex plugin marketplace add` to add and track a marketplace source instead of editing `config.toml` by hand.”
   • [claimed-docs] “In Codex CLI, enter `/plugins` to open the plugin browser.”

   proof ↗⚑ flag

2. developerChoose install scope — project-local files committed with my repo, or user-global across all projects

   weight 2 · round to Codex Plugins
   Anthropic Skills~partialclaimed4/10

   Docs show skills live in project-level directories like `.claude/skills/deploy/SKILL.md` and can be packaged into plugins shareable 'across projects and teams,' implying some notion of local vs shared scope, but there is no explicit documentation of a user-global (e.g. home-directory) skill install path or a direct project-vs-user scope toggle. missing for 10: explicit documentation of a user-global skill directory/location, explicit contrast between project-committed vs user-global install scope, and confirmation that both scopes are simultaneously supported and selectable by the developer.

   • [claimed-docs] “A file at `.claude/commands/deploy.md` and a skill at `.claude/skills/deploy/SKILL.md` both create `/deploy` and work the same way.”
   • [claimed-docs] “Plugins let you extend Claude Code with custom functionality that can be shared across projects and teams. This guide covers creating your o…”
   • [claimed-docs] “Plugins let you extend Claude Code with custom functionality that can be shared across projects and teams.”
   • [claimed-docs] “Marketplaces provide centralized discovery, version tracking, automatic updates, and support for multiple source types, including git reposi…”

   proof ↗⚑ flag

   Codex Plugins~partialclaimed5/10

   Evidence shows skills can be committed to a repo (`.agents/skills` scanned from cwd up to repo root, teams can check in module-specific skills) and installed to a local Codex setup via `$skill-installer`, implying both project-local and user-global-like scopes exist, but there's no explicit documentation contrasting a 'project-local vs user-global' install flag or config for plugins/skills. missing for 10: explicit docs on a user-global (all-projects) install location/flag distinct from project-local, and confirmation that plugin (not just skill) installs support both scopes.

   • [claimed-docs] “Codex scans `.agents/skills` in every directory from your current working directory up to the repository root.”
   • [claimed-docs] “teams can check in skills relevant to a working folder. For example, skills only relevant to a microservice or a module.”
   • [claimed-docs] “To add curated skills beyond the built-ins for your own local Codex setup, use `$skill-installer`.”
   • [claimed-docs] “To add curated skills beyond the built-ins for your own local Codex setup, use `$skill-installer`. For example, to install the `$linear` ski…”

   proof ↗⚑ flag

3. developerInstall only the specific skills I want from a collection instead of taking the whole bundle

   weight 2 · round drawn
   Anthropic Skills~partialclaimed6/10

   Docs show marketplace-based installs where a user can add a marketplace and then install just one named plugin (e.g. `/plugin install document-skills@anthropic-agent-skills` vs `example-skills@anthropic-agent-skills`, or `quality-review-plugin@my-plugins`) rather than every plugin in the marketplace, and `disableBundledSkills` can turn off built-in skills en masse. This demonstrates selecting a specific plugin/skill bundle out of a larger marketplace, but there's no documented mechanism to cherry-pick an individual skill from inside a single plugin bundle. Missing for 10: explicit per-skill (sub-bundle) install granularity, and independent confirmation that partial installs work as described.

   • [github] “/plugin install document-skills@anthropic-agent-skills /plugin install example-skills@anthropic-agent-skills”
   • [claimed-docs] “/plugin marketplace add ./my-marketplace /plugin install quality-review-plugin@my-plugins”
   • [claimed-docs] “/plugin install quality-review-plugin@my-plugins”
   • [claimed-docs] “the [`disableBundledSkills`](/docs/en/settings-reference#disablebundledskills) setting, which disables every bundled skill except `/doctor`.”
   • [claimed-docs] “To turn bundled skills off, use the [`disableBundledSkills`](/docs/en/settings-reference#disablebundledskills) setting, which disables every…”

   proof ↗⚑ flag

   Codex Plugins~partialclaimed6/10

   Docs show `$skill-installer <name>` to install individual curated skills (e.g. `$skill-installer linear`, `$skill-installer gh-address-comments`) rather than a whole bundle, and plugins are installed individually via `/plugins` browser. However, plugins themselves appear to be installed as whole packages (a plugin can bundle multiple skills/tools) with no documented way to cherry-pick a subset of skills from within a single installed plugin. missing for 10: evidence of selecting/excluding individual skills within one plugin bundle at install time, independent hands-on confirmation of partial-bundle installs.

   • [claimed-docs] “To add curated skills beyond the built-ins for your own local Codex setup, use `$skill-installer`.”
   • [claimed-docs] “To add curated skills beyond the built-ins for your own local Codex setup, use `$skill-installer`. For example, to install the `$linear` ski…”
   • [claimed-docs] “$skill-installer linear”
   • [claimed-docs] “Curated skills can be installed by name (defaults to `skills/.curated`): $skill-installer gh-address-comments ”
   • [claimed-docs] “In Codex CLI, enter `/plugins` to open the plugin browser. Install a plugin from a configured marketplace, then start a new session before u…”
   • [claimed-docs] “Open the Plugins tab to browse and install plugins. After installation, you can use plugins in Chat or Work in ChatGPT, or in Codex. Install…”

   proof ↗⚑ flag

Lifecycle

1. developerList what is installed and remove skills cleanly, without orphaned files or lingering instructions

   weight 1 · round to Codex Plugins
   Anthropic Skills—none0/10

   The evidence pack shows how to create, add, invoke, and disable skills (e.g., disableBundledSkills, /plugin install), but there is no documentation of a command or workflow to list all installed skills or to cleanly uninstall/remove a skill and its plugin files, hooks, or references without leftovers.

   • [claimed-docs] “the [`disableBundledSkills`](/docs/en/settings-reference#disablebundledskills) setting, which disables every bundled skill except `/doctor`.”
   • [claimed-docs] “To turn bundled skills off, use the [`disableBundledSkills`](/docs/en/settings-reference#disablebundledskills) setting, which disables every…”
   • [claimed-docs] “/plugin marketplace add ./my-marketplace /plugin install quality-review-plugin@my-plugins”
   • [claimed-docs] “A file at `.claude/commands/deploy.md` and a skill at `.claude/skills/deploy/SKILL.md` both create `/deploy` and work the same way.”

   proof ↗⚑ flag

   Codex Plugins~partialclaimed3/10

   Docs show how to list/browse installed plugins and skills (the /plugins browser, Skills sidebar, /skills command) and how to install them via skill-installer or plugin marketplace add, but there is no documented uninstall/removal command or explanation of how installed skill files, manifests, or config.toml entries are cleaned up. Missing for 10: documented uninstall/remove command, confirmation that removal deletes .agents/skills files and marketplace/config entries without leaving orphaned instructions, and any hands-on evidence of clean removal.

   • [claimed-docs] “In Codex CLI, enter `/plugins` to open the plugin browser.”
   • [claimed-docs] “Open the Plugins tab to browse and install plugins. After installation, you can use plugins in Chat or Work in ChatGPT, or in Codex. Install…”
   • [claimed-docs] “In the ChatGPT desktop app, open **Skills** in the sidebar to view and explore skills created across your projects.”
   • [claimed-docs] “In Codex CLI or the IDE extension, run `/skills` or type `$` to mention a skill.”
   • [claimed-docs] “Use `codex plugin marketplace add` to add and track a marketplace source instead of editing `config.toml` by hand.”
   • [claimed-docs] “To add curated skills beyond the built-ins for your own local Codex setup, use `$skill-installer`.”

   proof ↗⚑ flag

1. ai-native userDo everything through the API that I can do in the UI

   weight 2 · round to Anthropic Skills
   Anthropic Skills~partialclaimed5/10

   Docs confirm Skills can be invoked and managed programmatically via the Messages API (container parameter, skill_id/type/version, up to 20 skills per request) and via a dedicated Skills API for upload/management, giving real API-level parity for core skill usage. However, other capabilities visible in the Claude Code/Claude.ai UI — plugin marketplaces, automatic relevance-based skill loading, /plugin and /skill-name invocation, bundled-skill toggling — are documented only as CLI/UI features with no evidence of an equivalent API path. Missing for 10: API equivalents for plugin marketplace distribution, automatic skill discovery/loading parity, and confirmation that all UI-configurable settings (e.g., disableBundledSkills) are reachable via API.

   • [claimed-docs] “You specify Skills in the `container` parameter with a `skill_id`, `type`, and optional `version`, and they run in the code execution enviro…”
   • [claimed-docs] “Skills are specified using the `container` parameter in the Messages API. You can include up to 20 Skills for each request.”
   • [claimed-docs] “Upload and manage through the [Skills API](https://platform.claude.com/docs/en/api/skills/create)”
   • [claimed-docs] “You can include up to 20 Skills for each request.”
   • [claimed-docs] “Upload and manage through the [Skills API]”
   • [claimed-docs] “Availability | Available to all users | Private to your workspace”
   • [claimed-docs] “A **plugin marketplace** is a catalog that lets you distribute plugins to others. Marketplaces provide centralized discovery, version tracki…”
   • [claimed-docs] “/plugin marketplace add ./my-marketplace /plugin install quality-review-plugin@my-plugins”

   proof ↗⚑ flag

   Codex Plugins—none0/10

   Codex Plugins documentation only describes UI (ChatGPT Plugins tab, desktop Skills sidebar) and CLI (`/plugins`, `$skill-installer`, `codex plugin marketplace add`) workflows for installing and managing plugins/skills; there is no mention of a public API for plugin/skill management, and a direct probe for an OpenAPI/swagger spec returned 404 on all candidate paths, indicating no documented API parity.

   • [claimed-docs] “In Codex CLI, enter `/plugins` to open the plugin browser.”
   • [claimed-docs] “Use `codex plugin marketplace add` to add and track a marketplace source instead of editing `config.toml` by hand.”
   • [claimed-docs] “Open the Plugins tab to browse and install plugins. After installation, you can use plugins in Chat or Work in ChatGPT, or in Codex. Install…”
   • [claimed-docs] “In the ChatGPT desktop app, open **Skills** in the sidebar to view and explore skills created across your projects.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://developers.openai.com/openapi.json, https://developers.openai.com/swagger.json, https://deve…”

   proof ↗⚑ flag

2. ai-native userExport all of my data in open formats and leave

   weight 3 · round drawn
   Anthropic Skills—none0/10

   The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)

   ⚑ flag

   Codex Plugins—none0/10

   No evidence of any data export feature, open-format export, or account/data portability mechanism for Codex Plugins; the documentation focuses on plugin/skill installation and creation, not user data export or exit.

   ⚑ flag

3. ai-native userRead the product's source under an open license

   weight 2 · round to Codex Plugins
   Anthropic Skills—none0/10

   While the anthropics/skills GitHub repo makes example skill files (SKILL.md, templates) publicly readable, none of the evidence cites an open-source license for Skills, Claude Code, or the underlying product; core Claude Code/Skills functionality itself is closed, proprietary tooling with no license grant shown.

   ⚑ flag

   Codex Plugins~partialclaimed3/10

   There is a public GitHub repo (openai/plugins) exposing plugin source code and structure, offering some read access, but none of the evidence cites an explicit open-source license (e.g., MIT/Apache) governing the Codex Plugins product or its source. missing for 10: explicit license declaration, confirmation that core Codex Plugins platform code (not just example plugins) is open-sourced, independent corroboration of license terms.

   • [github] “plugins/figma for `use_figma`, Code to Canvas, Code Connect, and design system rules”
   • [github] “`plugins/notion` for planning, research, meetings, and knowledge capture”
   • [claimed-docs] “"name": "slack", ... "category": "Communication"”

   proof ↗⚑ flag

1. ai-native userControl data retention and deletion

   weight 2 · round drawn
   Anthropic Skills—none0/10

   The evidence pack covers how Skills are created, invoked, packaged, and distributed, but contains no documentation about data retention policies, deletion controls, or privacy settings for skill data/usage. No mention of retention windows, user-initiated deletion, or data handling controls exists in this pack.

   ⚑ flag

   Codex Plugins—none0/10

   Evidence only describes what limited profile data is shared during plugin sign-in (name, email, picture) and that this doesn't grant automatic data access, but there is no mention of controls for retaining, exporting, or deleting plugin-related data or conversation history. Missing for 10: any documented retention policy, data deletion mechanism, or user-facing controls to manage stored data for plugins/skills.

   • [claimed-docs] “Signing in shares only your name, email address, and profile picture, when available, with the partner. It doesn't grant the plugin access t…”
   • [claimed-docs] “Signing in shares only your name, email address, and profile picture, when available, with the partner.”

   proof ↗⚑ flag

Review

1. engineering-leadReview exactly what instructions and scripts a skill will add — list contents before installing and read every file afterward

   weight 3 · round to Anthropic Skills
   Anthropic Skills~partialclaimed6/10

   Docs confirm skills are transparent, plain-text directories (SKILL.md plus optional scripts/references/assets folders) that a lead can browse in a repo/marketplace and read after installation, and plugins/marketplaces are just git repos or local paths a lead could inspect. However, there is no documented feature for listing or previewing a skill's full file contents specifically before installation (e.g., a dry-run/manifest-diff command), so the 'before install' half of the story is only implicit via manual repo browsing. missing for 10: a dedicated pre-install content-listing/manifest command, any audit/review tooling, and independent confirmation that installs can't run additional undisclosed files.

   • [claimed-docs] “scripts/ # Optional: executable code references/ # Optional: documentation assets/ # Optional: templates, resources”
   • [claimed-docs] “skills can bundle additional files within the skill directory and reference them by name from `SKILL.md`.”
   • [claimed-docs] “A skill is a directory containing, at minimum, a `SKILL.md` file”
   • [claimed-docs] “Marketplaces provide centralized discovery, version tracking, automatic updates, and support for multiple source types, including git reposi…”
   • [github] “You can register this repository as a Claude Code Plugin marketplace by running the following command in Claude Code: /plugin marketplace a…”
   • [claimed-docs] “add a skill, and test it locally using the \`--plugin-dir\` flag”

   proof ↗⚑ flag

   Codex Plugins~partialclaimed5/10

   Skills are documented as plain directories (SKILL.md plus optional scripts/references) and plugins ship with an inspectable manifest (`.codex-plugin/plugin.json`), and curated skills/plugins live in public GitHub repos that can be browsed before installing via `$skill-installer` or the plugin marketplace. However, there is no documented in-product command or UI that explicitly lists a skill/plugin's file contents prior to installation, nor any stated post-install audit/read workflow for engineering leads. Missing for 10: a dedicated 'preview/list contents' command before install, and confirmation that all installed files (scripts, resources) are surfaced for review after install rather than just SKILL.md.

   • [claimed-docs] “A skill is a directory with a `SKILL.md` file plus optional scripts and references. The `SKILL.md` file must include `name` and `description…”
   • [claimed-docs] “Codex scans `.agents/skills` in every directory from your current working directory up to the repository root.”
   • [claimed-docs] “It scaffolds the required `.codex-plugin/plugin.json` manifest and can also generate a local marketplace entry for testing.”
   • [claimed-docs] “To add curated skills beyond the built-ins for your own local Codex setup, use `$skill-installer`.”
   • [claimed-docs] “Curated skills can be installed by name (defaults to `skills/.curated`): $skill-installer gh-address-comments ”
   • [github] “`plugins/notion` for planning, research, meetings, and knowledge capture”

   proof ↗⚑ flag

Trust

1. engineering-leadThe project documents its security posture — what skills can execute, the trust model for third-party skills, and any telemetry or data collection

   weight 2 · round to Codex Plugins
   Anthropic Skills—none0/10

   The evidence pack shows extensive functional docs (SKILL.md structure, plugin marketplaces, execution environment, disableBundledSkills toggle) but no dedicated security-posture documentation addressing what skills can execute (sandboxing, permissions), a trust model for vetting third-party/marketplace skills, or telemetry/data-collection disclosures tied to skills usage.

   ⚑ flag

   Codex Plugins~partialclaimed4/10

   Docs disclose some security-relevant details (sign-in only shares name/email/photo, submission/review portal for publishing plugins, MCP-based server capability exposure) but there is no consolidated security posture document covering what skills can execute, an explicit trust model for third-party skills, or telemetry/data collection practices beyond OAuth sign-in scope. Missing for 10: dedicated security/trust-model documentation, explicit execution/sandboxing model for skills, and telemetry/data-collection disclosure beyond sign-in scopes.

   • [claimed-docs] “Signing in shares only your name, email address, and profile picture, when available, with the partner. It doesn't grant the plugin access t…”
   • [claimed-docs] “Signing in shares only your name, email address, and profile picture, when available, with the partner.”
   • [claimed-docs] “Use the plugin submission portal to submit a plugin for review when you're ready to publish it for public use.”
   • [claimed-docs] “Plugins use the [Model Context Protocol (MCP)] to expose server-backed capabilities to ChatGPT and Codex.”
   • [claimed-docs] “If you're migrating an existing Claude Code plugin or connector, first review [Submit your Claude Code plugin to OpenAI] to see what you nee…”

   proof ↗⚑ flag

Authoring

1. developerAuthor a new skill from a documented template — a SKILL.md with name and description frontmatter — without reverse-engineering existing skills

   weight 3 · round drawn
   Anthropic Skills✓fullcommunity8/10

   There is a documented open specification (agentskills.io) detailing required frontmatter (name, description, length constraints), file structure (SKILL.md plus optional scripts/references/assets folders), and even a template file (template/SKILL.md) with placeholder text, plus a dedicated skill-creator skill for authoring/improving skills without needing to reverse-engineer existing ones. Community evidence (comm-1) shows some users still had to ask others for example SKILL.md files, suggesting the template isn't universally discovered/used. missing for 10: independent hands-on confirmation that a developer successfully authored a skill purely from the template without consulting other examples, and more visibility/discoverability of the template in mainline docs.

   • [claimed-docs] “A skill is a directory containing, at minimum, a `SKILL.md` file”
   • [claimed-docs] “Replace with description of the skill and when Claude should use it.”
   • [claimed-docs] “name: skill-name description: A description of what this skill does and when to use it.”
   • [claimed-docs] “The `SKILL.md` file must contain YAML frontmatter followed by Markdown content.”
   • [claimed-docs] “scripts/ # Optional: executable code references/ # Optional: documentation assets/ # Optional: templates, resources”
   • [claimed-docs] “A skill for creating new skills and iteratively improving them.”
   • [claimed-docs] “Create new skills, modify and improve existing skills, and measure skill performance.”
   • [community] “Github MCP: 39 tools, 30K tokens - had to disable it. Asked if anyone has a good SKILLS.md file to study.”

   proof ↗⚑ flag

   Codex Plugins✓fullcommunity8/10

   Docs explicitly define the SKILL.md format (name + description frontmatter, directory with optional scripts/references) and describe a guided `@plugin-creator`/skill-creator flow that asks what the skill does, when it triggers, and whether to include scripts — enabling authoring from a documented template rather than reverse-engineering. Community evidence corroborates developers building their own skills this way. Missing for 10: a full worked SKILL.md example/template file shown verbatim and independent hands-on verification of the authoring flow.

   • [claimed-docs] “A skill is a directory with a `SKILL.md` file plus optional scripts and references. The `SKILL.md` file must include `name` and `description…”
   • [claimed-docs] “The creator asks what the skill does, when it should trigger, and whether it should stay instruction-only or include scripts.”
   • [claimed-docs] “For the fastest setup, use the built-in `@plugin-creator` skill. It scaffolds the required `.codex-plugin/plugin.json` manifest and can also…”
   • [claimed-docs] “Codex scans `.agents/skills` in every directory from your current working directory up to the repository root.”
   • [community] “The skills that matter most to me are the ones I create myself (with the skill creator skill) that are very specific and proprietary... I mi…”

   proof ↗⚑ flag

2. developerThe collection ships a meta-skill or tool that guides my agent through writing, improving, and packaging new skills

   weight 2 · round drawn
   Anthropic Skills✓fullclaimed8/10

   Anthropic ships a dedicated "skill-creator" meta-skill that explicitly guides creation, iteration, and improvement of skills, including benchmarking performance and optimizing description triggers for accuracy, and there's a template SKILL.md and open spec to follow. This directly matches the story of a meta-skill guiding authoring/improving/packaging skills, backed by first-party GitHub and docs evidence. Missing for 10: independent hands-on validation of the skill-creator workflow itself (community evidence only discusses skills generally, not this meta-skill specifically) and no evidence of a dedicated 'packaging for distribution' step within skill-creator beyond plugin/marketplace mechanisms.

   • [claimed-docs] “A skill for creating new skills and iteratively improving them.”
   • [claimed-docs] “benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy”
   • [claimed-docs] “Create new skills, modify and improve existing skills, and measure skill performance.”
   • [claimed-docs] “Replace with description of the skill and when Claude should use it.”
   • [claimed-docs] “The required `description` field: Must be 1-1024 characters, Should describe both what the skill does and when to use it”
   • [claimed-docs] “The `SKILL.md` file must contain YAML frontmatter followed by Markdown content.”

   proof ↗⚑ flag

   Codex Plugins✓fullcommunity8/10

   Codex ships explicit meta-skills for this: the `@plugin-creator` skill scaffolds `.codex-plugin/plugin.json`, wires MCP servers, and generates a marketplace entry (docs-10/15/18/24), a skill-creation flow that interviews the user on triggers/scripts (docs-7), and a recorder that drafts a reusable skill from a demonstrated workflow (docs-16), covering write/improve/package end-to-end. Community commentary corroborates the general pattern of using a 'skill creator skill' to build proprietary skills (comm-1). Missing for 10: independent hands-on account specifically of using @plugin-creator/skill-installer rather than general skills discussion, and no evidence of an 'improve existing skill' iteration workflow beyond initial creation.

   • [claimed-docs] “For the fastest setup, use the built-in `@plugin-creator` skill. It scaffolds the required `.codex-plugin/plugin.json` manifest and can also…”
   • [claimed-docs] “The plugin-creator skill will create the plugin folder, create the required `.codex-plugin/plugin.json`, and add MCP server wiring for the p…”
   • [claimed-docs] “It scaffolds the required `.codex-plugin/plugin.json` manifest and can also generate a local marketplace entry for testing.”
   • [claimed-docs] “For the fastest setup, use the built-in `@plugin-creator` skill. It scaffolds the required `.codex-plugin/plugin.json` manifest”
   • [claimed-docs] “The creator asks what the skill does, when it should trigger, and whether it should stay instruction-only or include scripts.”
   • [claimed-docs] “The recorder captures the workflow, inspects the steps, and drafts a reusable skill from the demonstration.”
   • [community] “The skills that matter most to me are the ones I create myself (with the skill creator skill) that are very specific and proprietary... I mi…”

   proof ↗⚑ flag

Spec

1. developerSkills follow the open Agent Skills specification so the same skill folder is valid beyond this one vendor's tooling

   weight 2 · round to Anthropic Skills
   Anthropic Skills✓fullclaimed8/10

   Anthropic explicitly states Claude Code skills follow the open Agent Skills standard (agentskills.io) that works across multiple AI tools, and the same SKILL.md folder format (frontmatter + markdown, optional scripts/references/assets dirs) is documented both on the vendor docs and the independent agentskills.io spec site. Missing for 10: no third-party/independent tool (outside Anthropic) is shown actually consuming the same folder, and community commentary questions skill invocation reliability rather than spec portability.

   • [claimed-docs] “Claude Code skills follow the [Agent Skills](https://agentskills.io) open standard, which works across multiple AI tools.”
   • [claimed-docs] “A skill is a directory containing, at minimum, a `SKILL.md` file”
   • [claimed-docs] “The `SKILL.md` file must contain YAML frontmatter followed by Markdown content.”
   • [claimed-docs] “scripts/ # Optional: executable code references/ # Optional: documentation assets/ # Optional: templates, resources”
   • [claimed-docs] “The required `description` field: Must be 1-1024 characters, Should describe both what the skill does and when to use it”
   • [claimed-docs] “name: skill-name description: A description of what this skill does and when to use it.”

   proof ↗⚑ flag

   Codex Plugins~partialcommunity6/10

   Docs describe skills as a directory with a SKILL.md containing required `name`/`description` fields plus optional scripts/references (docs-13), which matches the general shape of the open Agent Skills format, and community commentary links Codex Skills to the same lineage as Claude Skills (comm-6). However, no evidence explicitly states conformance to a named open 'Agent Skills specification' or demonstrates a skill folder authored elsewhere working unmodified in Codex. Missing for 10: explicit statement of spec compliance/versioning, and a concrete cross-vendor portability example or test.

   • [claimed-docs] “A skill is a directory with a `SKILL.md` file plus optional scripts and references. The `SKILL.md` file must include `name` and `description…”
   • [claimed-docs] “A skill packages instructions, resources, and optional scripts so either product can follow a workflow reliably.”
   • [community] “Yes! I was raving about Claude Skills a few days ago, and excited they come to Codex as well!”

   proof ↗⚑ flag

Maintenance

1. developerThe collection is actively maintained — recent releases, triaged issues, and accepted community contributions

   weight 2 · round drawn
   Anthropic Skills—none0/10

   Evidence pack covers docs, specification, and usage patterns for Skills, but contains no information about release cadence, issue triage, or acceptance of community contributions to the anthropics/skills repository. No changelog, release notes, contributor stats, or issue-response evidence is present.

   ⚑ flag

   Codex Plugins—none0/10

   The evidence pack documents plugin/skill features and how-tos but contains no information about release cadence, issue triage, or accepted community contributions for the openai/plugins repository — no changelog, commit history, issue tracker activity, or PR merge data is cited. Community comments present are about skills vs MCP design tradeoffs, not maintenance activity.

   ⚑ flag

Testing

1. developerThe collection maintains tests or evals for its skills so changes are verified against regressions rather than shipped on vibes

   weight 2 · round drawn
   Anthropic Skills—none0/10

   The skill-creator skill offers ad-hoc 'benchmark skill performance' tooling for authors (anthropic-skills-docs-14, -30), but there is no evidence of a maintained test suite, CI pipeline, or regression eval framework for the official skills collection itself. The only concrete eval-style evidence (Vercel's finding that skills were never invoked in 56% of cases) is a third-party community critique, not Anthropic's own maintained regression testing.

   • [claimed-docs] “benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy”
   • [claimed-docs] “Create new skills, modify and improve existing skills, and measure skill performance.”
   • [community] “Vercel found: In 56% of eval cases, the skill was never invoked. The agent had access to the documentation but didn't use it. Adding the ski…”

   proof ↗⚑ flag

   Codex Plugins—none0/10

   The evidence pack documents skill/plugin creation, installation, and marketplace workflows but contains no mention of automated tests, evals, or regression suites for skills; a community comment even contrasts skills unfavorably with MCP by noting skills are 'append more text to prompt and pray' rather than testable. No vendor documentation describes any verification harness for skill quality.

   • [community] “At least MCPs can be unit tested. With Skills however, you just selectively append more text to prompt and pray.”
   • [claimed-docs] “A skill is a directory with a `SKILL.md` file plus optional scripts and references. The `SKILL.md` file must include `name` and `description…”
   • [claimed-docs] “Codex scans `.agents/skills` in every directory from your current working directory up to the repository root.”

   proof ↗⚑ flag

Pinning

1. engineering-leadControl when skill changes reach my team — pinned versions or a lockfile rather than silent behind-the-back updates

   weight 1 · round to Anthropic Skills
   Anthropic Skills~partialclaimed5/10

   The Skills API explicitly supports pinning a specific version via the `container` parameter's optional `version` field when invoking a skill, and plugin manifests include a version field with marketplaces offering 'version tracking' (docs-10, docs-23, docs-27, docs-36). However, for Claude Code's locally-installed/bundled skills there is no lockfile or team-wide pinning mechanism described — marketplaces are instead touted for 'automatic updates', which is the opposite of controlled rollout, and no evidence shows a way to pin or freeze skill versions across a team's Claude Code installs. missing for 10: lockfile or pinned-version mechanism for Claude Code skill/plugin installs, evidence that automatic marketplace updates can be disabled or gated per-team, and any hands-on confirmation that version pinning works as documented.

   • [claimed-docs] “You specify Skills in the `container` parameter with a `skill_id`, `type`, and optional `version`, and they run in the code execution enviro…”
   • [claimed-docs] “Skills are specified using the `container` parameter in the Messages API. You can include up to 20 Skills for each request.”
   • [claimed-docs] “The manifest file at `.claude-plugin/plugin.json` defines your plugin's identity: its name, description, and version.”
   • [claimed-docs] “Marketplaces provide centralized discovery, version tracking, automatic updates, and support for multiple source types, including git reposi…”

   proof ↗⚑ flag

   Codex Plugins—none0/10

   Evidence covers installing plugins/skills, marketplace sources, and manifest scaffolding, but nothing describes version pinning, a lockfile, or any mechanism to prevent automatic/silent skill updates for a team.

   • [claimed-docs] “Use `codex plugin marketplace add` to add and track a marketplace source instead of editing `config.toml` by hand.”
   • [claimed-docs] “In Codex CLI, enter `/plugins` to open the plugin browser. Install a plugin from a configured marketplace, then start a new session before u…”
   • [claimed-docs] “Open the Plugins tab to browse and install plugins. After installation, you can use plugins in Chat or Work in ChatGPT, or in Codex. Install…”

   proof ↗⚑ flag

Updates

1. developerThere is a documented update path — marketplace auto-updates or an explicit update command — so I get fixes without reinstalling from scratch

   weight 3 · round to Anthropic Skills
   Anthropic Skills~partialclaimed6/10

   Docs explicitly state plugin marketplaces provide 'centralized discovery, version tracking, automatic updates' for plugins that can bundle skills, and marketplace/plugin install commands are documented (e.g. /plugin marketplace add, /plugin install). However, this update path is scoped to the plugin-marketplace distribution mechanism rather than a general update command for individually-created or hand-copied skills (e.g. skills dropped into .claude/skills/), and there's no explicit 'update' CLI verb or independent confirmation of update behavior in practice. missing for 10: an explicit 'update' command example/output, confirmation this works for non-marketplace skills, independent/hands-on evidence of auto-update actually firing.

   • [claimed-docs] “A **plugin marketplace** is a catalog that lets you distribute plugins to others. Marketplaces provide centralized discovery, version tracki…”
   • [claimed-docs] “Marketplaces provide centralized discovery, version tracking, automatic updates, and support for multiple source types, including git reposi…”
   • [claimed-docs] “/plugin marketplace add ./my-marketplace /plugin install quality-review-plugin@my-plugins”
   • [github] “You can register this repository as a Claude Code Plugin marketplace by running the following command in Claude Code: /plugin marketplace a…”
   • [claimed-docs] “A plugin marketplace is a catalog that lets you distribute plugins to others.”

   proof ↗⚑ flag

   Codex Plugins—none0/10

   Evidence covers plugin installation (`/plugins`, `codex plugin marketplace add`) and creation/submission workflows, but nowhere documents an explicit update/upgrade command or auto-update behavior for already-installed plugins to receive fixes without reinstalling.

   • [claimed-docs] “In Codex CLI, enter `/plugins` to open the plugin browser.”
   • [claimed-docs] “Use `codex plugin marketplace add` to add and track a marketplace source instead of editing `config.toml` by hand.”
   • [claimed-docs] “In Codex CLI, enter `/plugins` to open the plugin browser. Install a plugin from a configured marketplace, then start a new session before u…”
   • [claimed-docs] “Open the Plugins tab to browse and install plugins. After installation, you can use plugins in Chat or Work in ChatGPT, or in Codex. Install…”

   proof ↗⚑ flag

2. developerReleases ship with notes or a changelog so I can see what changed in the skills before I take an update

   weight 1 · round drawn
   Anthropic Skills—none0/10

   Evidence shows plugin marketplaces support 'version tracking' and skills/plugins have version fields in manifests, but there is no evidence of actual release notes or a changelog documenting what changed between skill versions before update.

   ⚑ flag

   Codex Plugins—none0/10

   No evidence in the pack mentions release notes, version changelogs, or any versioning information for plugins or skills before updating; the docs cover installation, creation, and marketplace submission but nothing about update transparency.

   ⚑ flag