Superpowers vs Skills for Real Engineers

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 Superpowers
   Superpowers✓fullcommunity8/10

   Superpowers includes a dedicated writing-skills SKILL.md meta-skill describing a full TDD-style workflow for authoring skills (write test cases, watch fail, write skill, watch pass, refactor) and a harness-porting spec/template for extending skills across agents, backed by an eval harness that verifies skill compliance. Community evidence corroborates the skill-authoring and self-review workflow exists and is used in practice, though with some workflow friction noted. Missing for 10: independent hands-on account of an agent actually authoring a brand-new skill end-to-end via this meta-skill, and packaging/publishing steps are only documented, not demonstrated by a third party.

   • [claimed-docs] “You write test cases (pressure scenarios with subagents), watch them fail (baseline behavior), write the skill (documentation), watch tests …”
   • [claimed-docs] “Invoke relevant or requested skills BEFORE any response or action — including clarifying questions, exploring the codebase, or checking file…”
   • [claimed-docs] “Skills (harness-agnostic). Everything in `skills/` is the source of truth, shared verbatim by every harness.”
   • [claimed-docs] “This guide explains how to add support for a new harness ... so that Superpowers skills auto-trigger there the same way they do natively.”
   • [claimed-docs] “tests/` — does the plugin's non-LLM code work? ... `evals/` — do agents behave correctly on real LLM sessions?”
   • [community] “Superpowers has several skills. Its core workflow is: brainstorm to design a spec, use subagents to adversarially review its own spec/plan, …”

   proof ↗⚑ flag

   Skills for Real Engineers—none0/10

   The evidence pack describes numerous existing skills (tdd, grilling, triage, setup-matt-pocock-skills) and packaging/distribution mechanics (npx skills, Claude plugin marketplace), but nothing documents a meta-skill, spec, or template that an agent would follow to author and package a brand-new SKILL.md from scratch within this project's own conventions.

   ⚑ 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 Skills for Real Engineers
   Superpowers—none0/10

   All installation evidence describes human-run commands (`/plugin marketplace add`, `devin plugins install`, git clone steps) that differ per harness and are documented as manual steps a user performs, not a single headless, promptless path the agent runs itself end-to-end. Community commentary even notes the install mechanism is 'curl|bash but with added LLM agents,' underscoring it's not a clean self-serve agent install. No evidence shows an agent autonomously invoking these install commands without human initiation.

   • [github] “Installation differs by harness. If you use more than one, install Superpowers separately for each one.”
   • [claimed-docs] “/plugin marketplace add obra/superpowers-marketplace /plugin install superpowers@superpowers-marketplace”
   • [claimed-docs] “**Devin CLI**: `devin plugins install obra/superpowers` now works, and skills auto-trigger at session start.”
   • [community] “The install mechanism for the superpowers plugin for codex and opencode is .... interesting... it's like curl|bash but with added LLM agents…”

   proof ↗⚑ flag

   Skills for Real Engineers~partialclaimed4/10

   The docs describe simple CLI install commands (`npx skills`, `claude plugins install mattpocock-skills`, `npx skills update`) that could in principle be scripted, but the accompanying setup skill explicitly interviews the user ('Ask you which issue tracker you want to use') and other examples show a human typing a slash command, not a fully headless agent-run flow. missing for 10: explicit non-interactive/CI flag or documented flow for an agent to run install end-to-end without any prompts, and confirmation that the interactive setup step can be skipped or automated.

   • [claimed-docs] “`mattpocock-skills` was accepted into **Claude Code's official marketplace**... `claude plugins install mattpocock-skills` is now the docume…”
   • [claimed-docs] “Install the ones you want, then type a slash command.”
   • [claimed-docs] “Ask you which issue tracker you want to use (GitHub, Linear, or local files)”
   • [claimed-docs] “Scaffold the per-repo configuration that the engineering skills assume: **Issue tracker**... **Triage labels**... **Domain docs**”
   • [claimed-docs] “Nothing updates behind your back; pull my latest changes when you want them with `npx skills update`”

   proof ↗⚑ flag

Agent access

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

   weight 2 · round drawn
   Superpowers~partialprobed5/10

   Superpowers ships extensive agent-oriented documentation (SKILL.md files as harness-agnostic 'source of truth', support for AGENTS.md/CLAUDE.md/GEMINI.md conventions, and a cross-runtime `~/.agents/skills/` alias), which is the spirit of pointing an agent at agent-native docs. However, a direct probe for an actual llms.txt on the project itself returned 404, and the only llms.txt success in evidence is GitHub's own generic file, not one authored by Superpowers. Missing for 10: an official llms.txt endpoint for the Superpowers project/docs, and confirmation that agents are explicitly pointed at it as an entry format.

   • [claimed-docs] “Skills (harness-agnostic). Everything in `skills/` is the source of truth, shared verbatim by every harness.”
   • [claimed-docs] “Codex, Copilot CLI, and Gemini CLI all also recognize `~/.agents/skills/` as a cross-runtime alias.”
   • [claimed-docs] “User instructions (CLAUDE.md, AGENTS.md, GEMINI.md, etc, direct requests) take precedence over skills, which in turn override default behavi…”
   • [probe] “PROBE docs-md: HTTP 404 at https://github.com/obra/superpowers.md”
   • [probe] “PROBE llms.txt: HTTP 200 at https://github.com/llms.txt # GitHub > GitHub is a developer platform for building, shipping, and maintaining s…”

   proof ↗⚑ flag

   Skills for Real Engineers~partialprobed5/10

   The product's entire mechanism is agent-oriented markdown docs (SKILL.md, CONTEXT.md files) explicitly written for agents to read and act on, and it documents raw.githubusercontent URLs an agent could be pointed at directly. However, there is no evidence of a dedicated llms.txt for this product itself — the probe shows only GitHub's own generic llms.txt (unrelated to this project) and a 404 for skills.md, so the specific llms.txt convention is not supported, only the broader 'agent-readable docs' pattern. missing for 10: a product-specific llms.txt file, and confirmation that agents can be pointed at a single canonical docs entry point rather than individual SKILL.md files.

   • [claimed-docs] “Test only at pre-agreed seams. Before writing any test, write down the seams under test and confirm them with the user.”
   • [claimed-docs] “Interview the user relentlessly until you reach a shared understanding. Map this as a **design tree**”
   • [claimed-docs] “Scaffold the per-repo configuration that the engineering skills assume: **Issue tracker**... **Triage labels**... **Domain docs**”
   • [github] “Here's an example [`CONTEXT.md`]... Which one is easier to read?”
   • [probe] “PROBE llms.txt: HTTP 200 at https://github.com/llms.txt # GitHub > GitHub is a developer platform for building, shipping, and maintaining s…”
   • [probe] “PROBE docs-md: HTTP 404 at https://github.com/mattpocock/skills.md”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Superpowers—none0/10

   Superpowers is described as a Claude-Code-style plugin/skills system that repeatedly pauses for human approval (brainstorming step asks the user what they're trying to do, 'every path still stops for your approval before implementation', worktree conflicts ask rather than force) — this is an interactive workflow, and no evidence pack item mentions a headless mode, CI flag, non-interactive invocation, or automation pipeline usage.

   • [claimed-docs] “Requests are classified as spike, bounded, or architectural; small tasks skip the two-document ritual. Every path still stops for your appro…”
   • [claimed-docs] “Every path still stops for your approval before implementation.”
   • [claimed-docs] “If Claude thinks you're trying to start a project or task, it _should_ default into talking through a plan with you before it starts down th…”
   • [claimed-docs] “When `git worktree remove` refuses because the tree holds uncommitted work, the skill stops, names the files, and asks — instead of reaching…”

   proof ↗⚑ flag

   Skills for Real Engineers—none0/10

   The evidence describes skill files consumed by interactive coding agents (Claude Code, Cursor, etc.) that rely on human interviewing/grilling and manual slash-command invocation, with no mention of a CLI flag, non-interactive mode, or CI/automation pipeline usage. Nothing in the docs, GitHub, or community evidence discusses running the skills headlessly or in a CI pipeline.

   ⚑ flag

3. ai-native userConnect an agent via an official MCP server

   weight 3 · round drawn
   Superpowers—none0/10

   Superpowers is a skills/plugin framework installed into various agent harnesses (Claude Code, Devin, Codex, Gemini CLI, etc.), not an agent itself, so an official MCP server is a plausible axis for this kind of product—but no evidence anywhere in the pack mentions Superpowers exposing an MCP server for agents to connect to; installation is via harness-specific plugin mechanisms, not MCP.

   ⚑ flag

   Skills for Real Engineers—none0/10

   Evidence shows distribution via npm CLI, Claude Code plugin marketplace, and file-copy installation, but nowhere does it mention an MCP server for agents to connect to. Since this is a skills/plugin package (not itself an agent), the axis is a fair question, but there is no evidence of an official MCP server offering.

   • [claimed-docs] “`mattpocock-skills` was accepted into **Claude Code's official marketplace**... `claude plugins install mattpocock-skills` is now the docume…”
   • [claimed-docs] “subscribe to the set as a read-only, always-current bundle you don't edit, rather than a fork you own”
   • [claimed-docs] “Works with any agent Claude Code · Cursor · Codex · Copilot · 25 skills · MIT”
   • [claimed-docs] “Nothing updates behind your back; pull my latest changes when you want them with `npx skills update`.”

   proof ↗⚑ flag

4. ai-native userBuild against official SDKs

   weight 2 · round to Superpowers
   Superpowers~partialclaimed3/10

   Superpowers is a skills library rather than an API/service product, but its 'porting-to-a-new-harness' docs, harness-agnostic skills format, and tool-mapping/bootstrap injector amount to a quasi-SDK for extending the system to new agent runtimes; there's also a testing/eval harness for building compliant skills. Missing for 10: no formally branded 'SDK', no language-specific client libraries, no versioned API reference, and no independent developer accounts of building against it as an SDK.

   • [claimed-docs] “Skills (harness-agnostic). Everything in `skills/` is the source of truth, shared verbatim by every harness.”
   • [claimed-docs] “The harness must let you inject text into the model's context at the start of every session, with no per-session opt-in by your human partne…”
   • [claimed-docs] “Porting adds a tool-mapping reference and a bootstrap injector; it never reaches into `skills/*/SKILL.md` to swap tool names.”
   • [claimed-docs] “Everything ships through the harness's own install mechanism. Never edit the user's files.”
   • [claimed-docs] “Python harness driving real tmux sessions of Claude Code / Codex / Gemini CLI, with an LLM actor and verifier judging skill compliance.”

   proof ↗⚑ flag

   Skills for Real Engineers—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

Agentic features

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

   weight 2 · round to Skills for Real Engineers
   Superpowers—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

   Skills for Real Engineers~partialclaimed6/10

   The skill bundle includes several skills that produce AI-generated insights/suggestions from a user's own project data — a visual refactor-worthiness report (docs-18), bug diagnosis from a repro (docs-19), diff review against standards (docs-14), and issue triage/sorting (docs-30, docs-34) — but these are discrete slash-command skills rather than a unified 'insights' surface, and there's no evidence of a dashboard or proactive analytics view. missing for 10: a consolidated insights UI/report aggregating findings, independent hands-on evidence of the insight-generating skills actually producing useful output, and evidence these insights update automatically rather than being invoked per-skill.

   • [claimed-docs] “Find the modules worth refactoring, as a visual report.”
   • [claimed-docs] “Diagnose a hard bug, starting from a repro that fails.”
   • [claimed-docs] “Review a diff against your standards and against the spec.”
   • [claimed-docs] “Sort raw issues into work someone can pick up.”

   proof ↗⚑ flag

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

   weight 2 · round to Superpowers
   Superpowers~partialclaimed5/10

   Superpowers enables an agent to work autonomously for extended periods once dispatched—"work autonomously for a couple hours at a time without deviating from the plan" via subagent-driven-development with review loops (gh-6, gh-10, docs-11)—which is real unsupervised agentic execution. But this is autonomy within an active coding session triggered by a user prompt, not a background/scheduled automation that runs independent of an open session (e.g., cron-like triggers, headless unattended jobs). Missing for 10: evidence of scheduling/triggering mechanisms, headless/background execution outside an active session, or automation independent of user-initiated sessions.

   • [github] “It's not uncommon for your agent to work autonomously for a couple hours at a time without deviating from the plan you put together.”
   • [github] “your agent launches a *subagent-driven-development* process, having agents work through each engineering task, inspecting and reviewing thei…”
   • [claimed-docs] “this month's cool new process, where it dispatches tasks one by one to subagents to implement and then code reviews each task before continu…”
   • [claimed-docs] “The review-fix loop resumes the implementer... installs a five-round circuit breaker with controller adjudication when it trips.”

   proof ↗⚑ flag

   Skills for Real Engineers—none0/10

   The skills are built around interactive, human-in-the-loop workflows (grilling/interviewing the user, confirming test seams, triage state machines) rather than unattended background automation; the project's own philosophy explicitly rejects processes that 'take away your control' in favor of user-confirmed steps. No evidence of scheduling, background triggers, or autonomous execution without human interaction is present in the pack.

   • [github] “They help you align with the agent before you get started, and think deeply about the change you're making. Use them _every_ time you want t…”
   • [claimed-docs] “Interview the user relentlessly until you reach a shared understanding. Map this as a **design tree**”
   • [claimed-docs] “Verify the claim. Before any grilling, check that the claim holds up. For a bug, reproduce it from the reporter's steps.”
   • [github] “Approaches like GSD, BMAD, and Spec-Kit try to help by owning the process. But while doing so, they take away your control”

   proof ↗⚑ flag

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

   weight 3 · round to Superpowers
   Superpowers~partialcommunity6/10

   Superpowers' core workflow explicitly delegates engineering tasks to subagents that implement, review, and iterate autonomously for hours (superpowers-gh-3, superpowers-gh-6, superpowers-gh-10, superpowers-docs-11, superpowers-docs-60), which matches the 'delegate to a built-in AI assistant' story. However, community reports note the self-review subagent step was recently folded back into the main agent (superpowers-comm-3) and mixed real-world effectiveness (superpowers-comm-2), and the 'assistant' is not a standalone built-in AI but relies on an external host agent (Claude Code, Devin, etc.) to run. Missing for 10: independent verification that delegated subagent work is reliably higher quality, and evidence of a fully self-contained assistant not dependent on a third-party host CLI.

   • [github] “your agent launches a *subagent-driven-development* process, having agents work through each engineering task, inspecting and reviewing thei…”
   • [github] “It's not uncommon for your agent to work autonomously for a couple hours at a time without deviating from the plan you put together.”
   • [github] “your agent launches a *subagent-driven-development* process, having agents work through each engineering task, inspecting and reviewing thei…”
   • [claimed-docs] “this month's cool new process, where it dispatches tasks one by one to subagents to implement and then code reviews each task before continu…”
   • [claimed-docs] “The framework includes a code-reviewer agent that evaluates implementations against plans, coding standards, and architectural principles.”
   • [community] “I personally don't like superpowers very much. My boss does. I think Claude makes more mistakes when using superpowers than when not... Just…”
   • [community] “A recent update got rid of the subagents for the self review and now does the self review in the main agent.”

   proof ↗⚑ flag

   Skills for Real Engineers—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

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

   weight 2 · round drawn
   Superpowers✓fullcommunity8/10

   Superpowers operates entirely via natural-language interaction and slash-commands (/brainstorm, /execute-plan) layered on top of chat-based agents, with users directing tasks conversationally and the system interpreting intent, clarifying goals, and driving implementation without requiring code-level commands. Community evidence corroborates real-world natural-language-driven workflows (brainstorm/spec/TDD loop), though some users find the resulting plans/specs not always intuitive to read. missing for 10: independent third-party benchmarking of NL command robustness across edge cases, and no evidence of non-command free-form conversational control beyond the documented skill/slash-command triggers.

   • [github] “it *doesn't* just jump into trying to write code. Instead, it steps back and asks you what you're really trying to do.”
   • [claimed-docs] “If Claude thinks you're trying to start a project or task, it _should_ default into talking through a plan with you before it starts down th…”
   • [claimed-docs] “Invoke skills with slash commands like `/brainstorming` to explore requirements and design before implementation, or `/execute-plan` to run …”
   • [claimed-docs] “20+ battle-tested skills; `/brainstorm`, `/write-plan`, `/execute-plan` commands; Skills-search tool for discovery; SessionStart context inj…”
   • [community] “Superpowers has several skills. Its core workflow is: brainstorm to design a spec, use subagents to adversarially review its own spec/plan, …”
   • [community] “Yeah I agree with the implementation plan not being that useful for me to read. I often just tell it to go after reading the design doc.”

   proof ↗⚑ flag

   Skills for Real Engineers✓fullclaimed8/10

   The skills are designed to be invoked and operated conversationally: users type slash commands (e.g., /grill-with-docs) and the agent then interviews/grills the user in natural language to reach shared understanding before acting (docs-43, gh-6, docs-6/26/33). This natural-language interaction model is central and repeated across multiple skill docs (grilling, triage, TDD flows). Missing for 10: independent hands-on confirmation that the natural-language command flow works smoothly in practice (community evidence only critiques prose quality, not the interaction mechanism), and no demonstration of free-form (non-slash) natural language command parsing beyond the interview pattern.

   • [claimed-docs] “Install the ones you want, then type a slash command.”
   • [github] “getting the agent to ask you detailed questions about what you're building”
   • [claimed-docs] “Interview the user relentlessly until you reach a shared understanding. Map this as a **design tree**”
   • [claimed-docs] “Interview the user relentlessly until you reach a shared understanding.”
   • [github] “They help you align with the agent before you get started, and think deeply about the change you're making. Use them _every_ time you want t…”
   • [claimed-docs] “Turn an agreed conversation into a written spec.”

   proof ↗⚑ flag

Api quality

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

   weight 1 · round to Superpowers
   Superpowers~partialclaimed4/10

   Superpowers isolates agent work via git worktrees so parallel tasks 'don't clobber each other' and blocks destructive actions like force-removing trees with uncommitted work, which functions as a code-level sandbox, but there is no evidence of a dedicated staging/test-data environment or safeguards against touching production databases/services. Missing for 10: explicit production-data isolation, staging/test environment support, and evidence of data-level (not just git-worktree) sandboxing.

   • [claimed-docs] “After you're done brainstorming, if you're in a git repo it automatically creates a worktree for the project and changes to that directory.”
   • [claimed-docs] “After you're done brainstorming, if you're in a git repo it automatically creates a worktree for the project and changes to that directory. …”
   • [claimed-docs] “When `git worktree remove` refuses because the tree holds uncommitted work, the skill stops, names the files, and asks — instead of reaching…”
   • [claimed-docs] “Worktree removal no longer destroys untracked files. When `git worktree remove` refuses because the tree holds uncommitted work, the skill s…”
   • [claimed-docs] “NO PRODUCTION CODE WITHOUT A FAILING TEST FIRST”

   proof ↗⚑ flag

   Skills for Real Engineers—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

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

   weight 2 · round to Superpowers
   Superpowers~partialclaimed5/10

   Release notes describe a specific batching capability where 'small same-shape tasks batch into one dispatch, cutting subagent cost sharply on micro-task plans,' with batch reviews verifying every file in the brief made it into the diff — this is a real bulk-operation mechanism for micro-tasks in a plan. However, this is narrow (limited to same-shape subagent task batching within SDD plans) rather than general-purpose bulk operations across arbitrary items, and comes only from first-party release notes with no independent or hands-on corroboration. Missing for 10: evidence of bulk operations beyond same-shape micro-tasks (e.g., bulk file edits, bulk API calls across many independent items), and community/hands-on validation of the batching feature's reliability.

   • [claimed-docs] “Small same-shape tasks batch into one dispatch, cutting subagent cost sharply on micro-task plans; batch reviews verify every file in the br…”
   • [claimed-docs] “Small same-shape tasks batch into one dispatch, cutting subagent cost sharply on micro-task plans.”
   • [claimed-docs] “Small same-shape tasks batch into one dispatch, cutting subagent cost sharply on micro-task plans”

   proof ↗⚑ flag

   Skills for Real Engineers—none0/10

   The skill set is built around structured, one-at-a-time workflows (grilling, triage state machine, TDD, spec-to-ticket) rather than any documented bulk/batch processing across many items simultaneously; no evidence describes running a skill across multiple issues, files, or specs in one operation. Missing for 10: any documented bulk/batch command or workflow, evidence of parallel/multi-item processing, and independent confirmation of such usage.

   • [claimed-docs] “Move issues on the project issue tracker through a small state machine of triage roles.”
   • [claimed-docs] “Move issues on the project issue tracker through a small state machine of triage roles, categorise, verify, grill if needed, and write agent…”
   • [claimed-docs] “Scaffold the per-repo configuration that the engineering skills assume: **Issue tracker**... **Triage labels**... **Domain docs**”

   proof ↗⚑ flag

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

   weight 3 · round to Superpowers
   Superpowers~partialclaimed5/10

   Superpowers skills auto-trigger on contextual events (session start, failed fix attempts, git conflicts, worktree issues) and users can author new skills that encode conditional trigger/action rules, but this is a semantic skill-matching system rather than a general-purpose 'if event X then action Y' rule engine that AI-native users can freely define for arbitrary events. missing for 10: an explicit user-facing rule/trigger definition interface (vs. embedding logic in skill docs), support for arbitrary custom events beyond built-in dev workflow triggers, and independent confirmation that user-authored triggers reliably fire.

   • [claimed-docs] “**Devin CLI**: `devin plugins install obra/superpowers` now works, and skills auto-trigger at session start.”
   • [claimed-docs] “safeguards that trigger architectural review after three failed fix attempts”
   • [claimed-docs] “When `git worktree remove` refuses because the tree holds uncommitted work, the skill stops, names the files, and asks — instead of reaching…”
   • [claimed-docs] “Non-catastrophic conflicts and ambiguities get a recorded ruling and work continues; only destructive or irreversible actions still stop for…”
   • [github] “because the skills trigger automatically, you don't need to do anything special. Your coding agent just has Superpowers.”
   • [claimed-docs] “Invoke relevant or requested skills BEFORE any response or action — including clarifying questions, exploring the codebase, or checking file…”
   • [claimed-docs] “You write test cases (pressure scenarios with subagents), watch them fail (baseline behavior), write the skill (documentation), watch tests …”

   proof ↗⚑ flag

   Skills for Real Engineers—none0/10

   The product ships a library of manually-invoked skill files triggered by slash commands or explicit user direction ('Install the ones you want, then type a slash command'; 'Use them every time you want to make a change'), not an event-driven rule/automation engine. No evidence describes defining rules that fire automatically on repo events, webhooks, or triggers without user invocation.

   • [claimed-docs] “Install the ones you want, then type a slash command.”
   • [github] “They help you align with the agent before you get started, and think deeply about the change you're making. Use them _every_ time you want t…”
   • [claimed-docs] “Scaffold the per-repo configuration that the engineering skills assume: **Issue tracker**... **Triage labels**... **Domain docs**”

   proof ↗⚑ flag

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

   weight 1 · round to Superpowers
   Superpowers~partialclaimed5/10

   Superpowers uses git worktrees, PR/merge workflows, and review-fix loops with a code-reviewer agent that checks implementations against plans, and states 'git history is the durable record' after workspace cleanup — giving some version/review/rollback capability for code changes it makes. However, this is about versioning the code it produces, not about versioning, reviewing, or rolling back the automations/skills/workflows themselves, and no dedicated rollback or automation-versioning mechanism is documented. Missing for 10: explicit versioning/rollback of the skills/automations themselves (not just git history of generated code), a rollback command or mechanism, and independent evidence that review/rollback works reliably in practice.

   • [claimed-docs] “`sdd-workspace` now requires the plan file and resolves a per-plan directory, `.superpowers/sdd//`; ... the workspace is deleted once the fi…”
   • [claimed-docs] “At the end of the implementation process, Claude will now offer to make a GitHub pull request, merge the worktree back to the source branch …”
   • [claimed-docs] “The framework includes a code-reviewer agent that evaluates implementations against plans, coding standards, and architectural principles.”
   • [claimed-docs] “The review-fix loop resumes the implementer... installs a five-round circuit breaker with controller adjudication when it trips.”
   • [claimed-docs] “When `git worktree remove` refuses because the tree holds uncommitted work, the skill stops, names the files, and asks — instead of reaching…”

   proof ↗⚑ flag

   Skills for Real Engineers~partialclaimed4/10

   The product offers two install modes—a locked, read-only bundle that only updates via an explicit `npx skills update` pull, or an editable copy where skills become 'ordinary files you own' in your repo—which gives some control over when changes land and implies normal git-based versioning/rollback, but there is no explicit changelog, diff view, or rollback command for the skills themselves. Missing for 10: dedicated version history or diff/review UI for skill changes, an explicit rollback mechanism, and any evidence of reviewing skill updates before applying them (beyond opting into `update`).

   • [claimed-docs] “installs the whole set as a managed, read-only bundle that updates when I ship, so you subscribe rather than fork”
   • [claimed-docs] “copies editable skill files into your project, so you can hack on them and make them your own”
   • [claimed-docs] “Nothing updates behind your back; pull my latest changes when you want them with `npx skills update`.”
   • [claimed-docs] “It writes the skills into your repo as ordinary files you own and can edit. Nothing updates behind your back”
   • [claimed-docs] “Nothing updates behind your back; pull my latest changes when you want them with `npx skills update`”
   • [claimed-docs] “subscribe to the set as a read-only, always-current bundle you don't edit, rather than a fork you own”

   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 Superpowers
   Superpowers✓fullcommunity8/10

   Superpowers documents skills as harness-agnostic source of truth (docs-13) with explicit per-harness install/porting instructions for Claude Code, Codex, Devin CLI, Hermes Agent, Grok Build CLI, Cursor-class tools, Gemini CLI, Copilot CLI, and Antigravity (docs-7,8,31,54,gh-8), plus a porting guide (docs-37,59) and a testing harness running real tmux sessions across Claude Code/Codex/Gemini CLI (docs-14). It explicitly notes installation differs by harness and must be done separately for each (gh-5), matching the story's 'per-harness instructions' framing. missing for 10: no independent hands-on confirmation that identical behavior/parity is achieved across all these harnesses (only vendor docs and release notes), and community evidence focuses mainly on Claude Code with only a passing, slightly negative mention of the Codex/OpenCode install mechanism (comm-4).

   • [claimed-docs] “Skills (harness-agnostic). Everything in `skills/` is the source of truth, shared verbatim by every harness.”
   • [claimed-docs] “**Devin CLI**: `devin plugins install obra/superpowers` now works, and skills auto-trigger at session start.”
   • [claimed-docs] “**Hermes Agent**: install from a git clone; skills register with Hermes' native loader and the bootstrap loads on the first turn.”
   • [claimed-docs] “Codex, Copilot CLI, and Gemini CLI all also recognize `~/.agents/skills/` as a cross-runtime alias.”
   • [claimed-docs] “Grok Build CLI added to the install docs.”
   • [github] “Antigravity runs the plugin's session-start hook, so Superpowers is active from the first message. Reinstall with the same command to update…”
   • [github] “Installation differs by harness. If you use more than one, install Superpowers separately for each one.”
   • [claimed-docs] “Porting adds a tool-mapping reference and a bootstrap injector; it never reaches into `skills/*/SKILL.md` to swap tool names.”
   • [claimed-docs] “This guide explains how to add support for a new harness ... so that Superpowers skills auto-trigger there the same way they do natively.”
   • [claimed-docs] “Python harness driving real tmux sessions of Claude Code / Codex / Gemini CLI, with an LLM actor and verifier judging skill compliance.”
   • [community] “The install mechanism for the superpowers plugin for codex and opencode is .... interesting... it's like curl|bash but with added LLM agents…”

   proof ↗⚑ flag

   Skills for Real Engineers~partialclaimed6/10

   Docs explicitly claim the collection 'works with any agent' — listing Claude Code, Cursor, Codex, Copilot — and show at least one harness-specific install path (Claude Code plugin marketplace vs. generic `npx skills` copy/subscribe modes), supporting cross-agent installability. However, evidence lacks concrete per-harness instructions for Cursor, Codex, or Copilot individually (only Claude Code's plugin route is documented in detail), and no hands-on confirmation that the same skill set actually functions identically across harnesses. Missing for 10: explicit install/config steps for Cursor, Codex, and Copilot, and independent verification that per-harness behavior matches claims.

   • [claimed-docs] “Works with any agent Claude Code · Cursor · Codex · Copilot · 25 skills · MIT”
   • [claimed-docs] “`mattpocock-skills` was accepted into **Claude Code's official marketplace**... `claude plugins install mattpocock-skills` is now the docume…”
   • [claimed-docs] “installs the whole set as a managed, read-only bundle that updates when I ship, so you subscribe rather than fork”
   • [claimed-docs] “copies editable skill files into your project, so you can hack on them and make them your own”
   • [claimed-docs] “It writes the skills into your repo as ordinary files you own and can edit. Nothing updates behind your back”

   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 drawn
   Superpowers✓fullclaimed8/10

   Docs explicitly confirm skills are harness-agnostic markdown source-of-truth files (skills/*/SKILL.md) shared verbatim across harnesses, with per-harness install adapters that never modify the skill files themselves, and community/vendor evidence of usage across Claude Code, Codex, Gemini CLI, Devin, Hermes, Grok Build, etc. missing for 10: independent hands-on confirmation of copying skill folders manually into a new harness without the official installer, and explicit statement that no binary/compiled artifacts are involved.

   • [claimed-docs] “Skills (harness-agnostic). Everything in `skills/` is the source of truth, shared verbatim by every harness.”
   • [claimed-docs] “Codex, Copilot CLI, and Gemini CLI all also recognize `~/.agents/skills/` as a cross-runtime alias.”
   • [claimed-docs] “Porting adds a tool-mapping reference and a bootstrap injector; it never reaches into `skills/*/SKILL.md` to swap tool names.”
   • [claimed-docs] “Everything ships through the harness's own install mechanism. Never edit the user's files.”
   • [claimed-docs] “This guide explains how to add support for a new harness ... so that Superpowers skills auto-trigger there the same way they do natively.”
   • [github] “Installation differs by harness. If you use more than one, install Superpowers separately for each one.”

   proof ↗⚑ flag

   Skills for Real Engineers✓fullclaimed8/10

   Docs explicitly state skills are written as ordinary markdown files into the repo that you own and can edit, not a proprietary format, and work across multiple harnesses (Claude Code, Cursor, Codex, Copilot). This directly matches the story's plain-file, portable-across-harness claim. Missing for 10: independent hands-on confirmation that files are literally copy-pasteable markdown (only vendor docs/ADR cited) and no explicit demonstration of moving skills to a different harness in practice.

   • [claimed-docs] “copies editable skill files into your project, so you can hack on them and make them your own”
   • [claimed-docs] “It writes the skills into your repo as ordinary files you own and can edit. Nothing updates behind your back”
   • [claimed-docs] “Works with any agent Claude Code · Cursor · Codex · Copilot · 25 skills · MIT”
   • [claimed-docs] “subscribe to the set as a read-only, always-current bundle you don't edit, rather than a fork you own”

   proof ↗⚑ flag

Discovery

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

   weight 2 · round drawn
   Superpowers~partialclaimed6/10

   The project ships an 'obra/superpowers-marketplace' repo listing 20+ skills plus a 'Skills-search tool for discovery' and a `/plugin marketplace add` command, giving developers a way to see/search available skills before installing individual ones. However, there's no evidence of a rich browsable UI, ratings, leaderboard, or independent confirmation that search works well pre-install — it's mostly first-party doc mentions. Missing for 10: independent/hands-on confirmation of the search tool, a UI or leaderboard-style catalog, and community commentary on discoverability.

   • [claimed-docs] “20+ battle-tested skills; `/brainstorm`, `/write-plan`, `/execute-plan` commands; Skills-search tool for discovery; SessionStart context inj…”
   • [claimed-docs] “20+ battle-tested skills * `/brainstorm`, `/write-plan`, `/execute-plan` commands * Skills-search tool for discovery”
   • [claimed-docs] “Add this marketplace to Claude Code: /plugin marketplace add obra/superpowers-marketplace”

   proof ↗⚑ flag

   Skills for Real Engineers~partialclaimed6/10

   The aihero.dev/skills page functions as a lightweight catalog listing all 25 skills with one-line descriptions (docs-11 through docs-23, docs-30/35/37, docs-42/43), and the project is also listed in Claude Code's official plugin marketplace (docs-10), letting a developer browse before installing. However there's no evidence of search, filtering, ratings, or a leaderboard-style comparison across skills/authors. Missing for 10: searchable/filterable registry UI, ratings or usage leaderboard, independent confirmation of the marketplace listing's browsability.

   • [claimed-docs] “Works with any agent Claude Code · Cursor · Codex · Copilot · 25 skills · MIT”
   • [claimed-docs] “Install the ones you want, then type a slash command.”
   • [claimed-docs] “`mattpocock-skills` was accepted into **Claude Code's official marketplace**... `claude plugins install mattpocock-skills` is now the docume…”
   • [claimed-docs] “Find out which skill to use for the situation you are in.”
   • [claimed-docs] “Turn an agreed conversation into a written spec.”
   • [claimed-docs] “Sort raw issues into work someone can pick up.”

   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
   Superpowers✓fullcommunity8/10

   Superpowers ships as skills files (harness-agnostic, source of truth in `skills/`) that can be committed to a project, cloned from a git repo, or installed via the official `obra/superpowers-marketplace` plugin marketplace with a single `/plugin marketplace add` command, supporting many agent harnesses (Claude Code, Devin, Hermes, Codex, Gemini CLI, etc.), which is exactly the distribution story an engineering lead needs. Community evidence (HN) confirms real-world install/adoption across a team, though it also notes the install flow feels 'like curl|bash' — a minor rough edge. Missing for 10: no explicit team-permission/ACL or org-wide governance controls, and no first-party guidance on version-pinning a shared skill set across a team.

   • [claimed-docs] “/plugin marketplace add obra/superpowers-marketplace /plugin install superpowers@superpowers-marketplace”
   • [claimed-docs] “Add this marketplace to Claude Code: /plugin marketplace add obra/superpowers-marketplace”
   • [claimed-docs] “Skills (harness-agnostic). Everything in `skills/` is the source of truth, shared verbatim by every harness.”
   • [claimed-docs] “Codex, Copilot CLI, and Gemini CLI all also recognize `~/.agents/skills/` as a cross-runtime alias.”
   • [github] “Installation differs by harness. If you use more than one, install Superpowers separately for each one.”
   • [community] “The install mechanism for the superpowers plugin for codex and opencode is .... interesting... it's like curl|bash but with added LLM agents…”
   • [claimed-docs] “**Devin CLI**: `devin plugins install obra/superpowers` now works, and skills auto-trigger at session start.”
   • [claimed-docs] “**Hermes Agent**: install from a git clone; skills register with Hermes' native loader and the bootstrap loads on the first turn.”

   proof ↗⚑ flag

   Skills for Real Engineers✓fullclaimed8/10

   The product ships via Claude Code's official plugin marketplace (docs-10), as an npx-installed, updatable managed bundle (docs-1, docs-4/31, docs-41), or as editable files committed directly into the project repo (docs-2, docs-24), and is agent-agnostic/MIT-licensed so a lead can standardize it across a whole team's tools (docs-42). This covers all three named distribution paths (marketplace, subscribe/shared-source, and in-repo files). Missing for 10: no explicit 'shared git repo' distribution mode distinct from marketplace/npx, and no independent/community confirmation that team-wide rollout works smoothly in practice beyond first-party docs.

   • [claimed-docs] “`mattpocock-skills` was accepted into **Claude Code's official marketplace**... `claude plugins install mattpocock-skills` is now the docume…”
   • [claimed-docs] “installs the whole set as a managed, read-only bundle that updates when I ship, so you subscribe rather than fork”
   • [claimed-docs] “copies editable skill files into your project, so you can hack on them and make them your own”
   • [claimed-docs] “It writes the skills into your repo as ordinary files you own and can edit. Nothing updates behind your back”
   • [claimed-docs] “Nothing updates behind your back; pull my latest changes when you want them with `npx skills update`.”
   • [claimed-docs] “Works with any agent Claude Code · Cursor · Codex · Copilot · 25 skills · MIT”

   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 Superpowers
   Superpowers✓fullcommunity7/10

   Multiple first-party docs describe automatic, harness-agnostic skill triggering ('skills trigger automatically... you don't need to do anything special', 'Invoke relevant or requested skills BEFORE any response or action', session-start bootstrap injection across Claude Code, Devin CLI, Hermes, Antigravity) and a testing/eval harness that specifically judges skill-compliance triggering. Community discussion confirms the core brainstorm→plan→TDD workflow functions but doesn't contest trigger timing specifically. Missing for 10: independent hands-on verification that skill descriptions reliably select the *correct* skill at the *right* moment across diverse tasks (community comments focus on workflow quality/spec-plan friction rather than mis-triggering), and confirmation this holds uniformly across all listed harnesses rather than mainly Claude Code.

   • [github] “because the skills trigger automatically, you don't need to do anything special. Your coding agent just has Superpowers.”
   • [claimed-docs] “Invoke relevant or requested skills BEFORE any response or action — including clarifying questions, exploring the codebase, or checking file…”
   • [claimed-docs] “**Devin CLI**: `devin plugins install obra/superpowers` now works, and skills auto-trigger at session start.”
   • [claimed-docs] “**Hermes Agent**: install from a git clone; skills register with Hermes' native loader and the bootstrap loads on the first turn.”
   • [claimed-docs] “The harness must let you inject text into the model's context at the start of every session, with no per-session opt-in by your human partne…”
   • [github] “Antigravity runs the plugin's session-start hook, so Superpowers is active from the first message. Reinstall with the same command to update…”
   • [claimed-docs] “evals/` — do agents behave correctly on real LLM sessions? Python harness driving real tmux sessions of Claude Code / Codex / Gemini CLI, wi…”
   • [community] “Superpowers has several skills. Its core workflow is: brainstorm to design a spec, use subagents to adversarially review its own spec/plan, …”
   • [community] “A recent update got rid of the subagents for the self review and now does the self review in the main agent.”

   proof ↗⚑ flag

   Skills for Real Engineers—none0/10

   The evidence describes manual invocation — 'Install the ones you want, then type a slash command' (docs-43) and 'Use them every time you want to make a change' (gh-1/gh-4) — rather than automatic, context-triggered activation via engineered descriptions. There is a 'find out which skill to use' meta-skill (docs-23) but it's itself a skill you must invoke, not evidence of automatic description-based dispatch. No documentation or independent evidence shows the agent autonomously selecting/activating skills from task context.

   • [claimed-docs] “Install the ones you want, then type a slash command.”
   • [claimed-docs] “Find out which skill to use for the situation you are in.”
   • [github] “They help you align with the agent before you get started, and think deeply about the change you're making. Use them _every_ time you want t…”
   • [github] “They help you align with the agent before you get started, and think deeply about the change you're making. Use them every time you want to …”

   proof ↗⚑ flag

Onboarding

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

   weight 3 · round drawn
   Superpowers~partialcommunity6/10

   Docs show simple one-line install commands across multiple harnesses (e.g. `/plugin marketplace add obra/superpowers-marketplace` + `/plugin install superpowers@superpowers-marketplace`, `devin plugins install obra/superpowers`, git-clone for Hermes) and skills auto-trigger at session start without extra developer action, suggesting a fast path to a working skill. However, no first-party quickstart doc explicitly times the process, and a community comment calls the codex/opencode install mechanism 'interesting... curl|bash but with added LLM agents,' hinting at friction not captured in the marketing copy. missing for 10: an explicit timed quickstart walkthrough, and independent hands-on confirmation of sub-5-minute setup across harnesses.

   • [claimed-docs] “/plugin marketplace add obra/superpowers-marketplace /plugin install superpowers@superpowers-marketplace”
   • [claimed-docs] “Add this marketplace to Claude Code: /plugin marketplace add obra/superpowers-marketplace”
   • [claimed-docs] “**Devin CLI**: `devin plugins install obra/superpowers` now works, and skills auto-trigger at session start.”
   • [claimed-docs] “**Hermes Agent**: install from a git clone; skills register with Hermes' native loader and the bootstrap loads on the first turn.”
   • [github] “because the skills trigger automatically, you don't need to do anything special. Your coding agent just has Superpowers.”
   • [community] “The install mechanism for the superpowers plugin for codex and opencode is .... interesting... it's like curl|bash but with added LLM agents…”

   proof ↗⚑ flag

   Skills for Real Engineers~partialclaimed6/10

   Docs show a simple two-step install path ("Install the ones you want, then type a slash command" and `claude plugins install mattpocock-skills`), plus npx-based add/update commands, suggesting a fast setup, but there is no explicit quickstart walkthrough or timed benchmark confirming a five-minute install-to-working-skill experience, and no independent hands-on report timing the process. missing for 10: an actual quickstart guide/tutorial with step timings, independent/hands-on confirmation of install speed, and evidence that a first skill run succeeds quickly without extra config.

   • [claimed-docs] “Install the ones you want, then type a slash command.”
   • [claimed-docs] “`mattpocock-skills` was accepted into **Claude Code's official marketplace**... `claude plugins install mattpocock-skills` is now the docume…”
   • [claimed-docs] “Nothing updates behind your back; pull my latest changes when you want them with `npx skills update`.”
   • [claimed-docs] “It writes the skills into your repo as ordinary files you own and can edit. Nothing updates behind your back”

   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 Skills for Real Engineers
   Superpowers~partialcommunity7/10

   Each skill ships as a SKILL.md with explicit activation rules (e.g. 'Invoke relevant or requested skills BEFORE any response or action', 'NO PRODUCTION CODE WITHOUT A FAILING TEST FIRST'), a documented precedence order (user instructions > skills > defaults), and an eval harness that tests whether agents actually comply with each skill's documented behavior, which together let a developer predict activation and behavior. However, community reports note skill behavior has changed between updates in ways not obviously reflected to users in the moment (e.g. self-review subagents silently removed), and one experienced user found the plan/implementation docs didn't match what they expected in practice, showing documentation-to-behavior fidelity isn't perfect. Missing for 10: an independent audit confirming every one of the 20+ skills documents activation triggers consistently, and stronger evidence that doc updates keep pace with behavior changes.

   • [claimed-docs] “Invoke relevant or requested skills BEFORE any response or action — including clarifying questions, exploring the codebase, or checking file…”
   • [claimed-docs] “NO PRODUCTION CODE WITHOUT A FAILING TEST FIRST”
   • [claimed-docs] “User instructions (CLAUDE.md, AGENTS.md, GEMINI.md, etc, direct requests) take precedence over skills, which in turn override default behavi…”
   • [claimed-docs] “You write test cases (pressure scenarios with subagents), watch them fail (baseline behavior), write the skill (documentation), watch tests …”
   • [claimed-docs] “evals/` — do agents behave correctly on real LLM sessions? Python harness driving real tmux sessions of Claude Code / Codex / Gemini CLI, wi…”
   • [community] “A recent update got rid of the subagents for the self review and now does the self review in the main agent.”
   • [community] “Yeah I agree with the implementation plan not being that useful for me to read. I often just tell it to go after reading the design doc.”

   proof ↗⚑ flag

   Skills for Real Engineers✓fullcommunity7/10

   Each skill ships a SKILL.md/one-line description stating its purpose and trigger (e.g., TDD skill's red-green rules, triage skill's state machine, grilling skill's interview process, and the aihero.dev list of 25 skills each with a one-line 'what it does' summary), and activation is explicit and user-controlled via install + slash command rather than silent background changes ('Nothing updates behind your back', 'Install the ones you want, then type a slash command'). A community thread does critique the prose quality/clarity of some SKILL.md files as having 'little utility,' which tempers confidence but doesn't concretely contradict that each skill documents what/when it activates. missing for 10: independent verification that every one of the 25 skills' docs clearly states activation triggers (not just a sample), and resolution of the community critique about jargon-heavy or low-utility prose in some skill docs.

   • [claimed-docs] “Scaffold the per-repo configuration that the engineering skills assume: **Issue tracker**... **Triage labels**... **Domain docs**”
   • [claimed-docs] “Test only at pre-agreed seams. Before writing any test, write down the seams under test and confirm them with the user.”
   • [claimed-docs] “Red before green. Write the failing test first, then only enough code to pass it. Don't anticipate future tests or add speculative features.”
   • [claimed-docs] “Move issues on the project issue tracker through a small state machine of triage roles.”
   • [claimed-docs] “Move issues on the project issue tracker through a small state machine of triage roles, categorise, verify, grill if needed, and write agent…”
   • [claimed-docs] “Turn an agreed conversation into a written spec.”
   • [claimed-docs] “Works with any agent Claude Code · Cursor · Codex · Copilot · 25 skills · MIT”
   • [claimed-docs] “Install the ones you want, then type a slash command.”
   • [claimed-docs] “Nothing updates behind your back; pull my latest changes when you want them with `npx skills update`.”
   • [community] “Critique of Matt Pocock's skill files: he has a hand-wavy approach to engineering in a silo, then uses that output as a foundation for tools…”

   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 Superpowers
   Superpowers✓fullcommunity8/10

   Superpowers documents a clean one-liner install for Claude Code ('/plugin marketplace add obra/superpowers-marketplace' + '/plugin install superpowers@superpowers-marketplace') and equivalent one-liners for other harnesses (e.g. 'devin plugins install obra/superpowers'), with explicit claims that skills auto-trigger at session start via a SessionStart hook so the collection is active on the very next session without further setup. This is corroborated across multiple harness release notes (Devin, Hermes, Antigravity) and a first-party blog walkthrough. Missing for 10: independent hands-on confirmation that the one-liner installs cleanly on a fresh machine (community notes call the install mechanism for some harnesses 'interesting... like curl|bash but with added LLM agents' and note it must be repeated per-harness), and no non-vendor benchmark of session-start activation timing.

   • [claimed-docs] “/plugin marketplace add obra/superpowers-marketplace /plugin install superpowers@superpowers-marketplace”
   • [claimed-docs] “Add this marketplace to Claude Code: /plugin marketplace add obra/superpowers-marketplace”
   • [claimed-docs] “**Devin CLI**: `devin plugins install obra/superpowers` now works, and skills auto-trigger at session start.”
   • [claimed-docs] “**Hermes Agent**: install from a git clone; skills register with Hermes' native loader and the bootstrap loads on the first turn.”
   • [github] “Antigravity runs the plugin's session-start hook, so Superpowers is active from the first message. Reinstall with the same command to update…”
   • [github] “because the skills trigger automatically, you don't need to do anything special. Your coding agent just has Superpowers.”
   • [github] “Installation differs by harness. If you use more than one, install Superpowers separately for each one.”
   • [community] “The install mechanism for the superpowers plugin for codex and opencode is .... interesting... it's like curl|bash but with added LLM agents…”

   proof ↗⚑ flag

   Skills for Real Engineers~partialclaimed6/10

   First-party docs give a genuine one-liner (`claude plugins install mattpocock-skills`) now that the pack is in Claude Code's official marketplace, plus an `npx skills update` command for the managed-bundle mode, both documented as first-party. However there's no independent/hands-on confirmation that the skill set is actually active in the next session, and the exact single-command install syntax for the other supported agents (Cursor, Codex, Copilot) beyond Claude Code isn't shown — only 'install the ones you want, then type a slash command' is vague. missing for 10: independent hands-on confirmation of post-install activation, explicit one-liner install commands for non-Claude agents.

   • [claimed-docs] “`mattpocock-skills` was accepted into **Claude Code's official marketplace**... `claude plugins install mattpocock-skills` is now the docume…”
   • [claimed-docs] “Nothing updates behind your back; pull my latest changes when you want them with `npx skills update`.”
   • [claimed-docs] “Nothing updates behind your back; pull my latest changes when you want them with `npx skills update`”
   • [claimed-docs] “Works with any agent Claude Code · Cursor · Codex · Copilot · 25 skills · MIT”
   • [claimed-docs] “Install the ones you want, then type a slash command.”

   proof ↗⚑ flag

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

   weight 2 · round to Skills for Real Engineers
   Superpowers—none0/10

   Evidence describes installation via harness-specific plugin managers (Claude Code marketplace, Devin CLI, Hermes) and a global `~/.agents/skills/` alias, but nowhere mentions an explicit choice between project-local (repo-committed) and user-global install scopes as a deliberate feature.

   • [claimed-docs] “Codex, Copilot CLI, and Gemini CLI all also recognize `~/.agents/skills/` as a cross-runtime alias.”
   • [github] “Installation differs by harness. If you use more than one, install Superpowers separately for each one.”
   • [claimed-docs] “/plugin marketplace add obra/superpowers-marketplace /plugin install superpowers@superpowers-marketplace”

   proof ↗⚑ flag

   Skills for Real Engineers~partialclaimed4/10

   The docs describe two install modes—copying editable skill files into a repo (project-local, committed) versus subscribing to a managed, read-only, auto-updating bundle via the Claude Code plugin marketplace—but never explicitly frame the second mode as 'user-global across all projects' vs project-local; scope (per-project vs per-user) is never directly addressed. Missing for 10: explicit documentation of a user-global/home-directory install option and confirmation that the plugin/subscribe mode applies across all projects rather than just being non-editable.

   • [claimed-docs] “installs the whole set as a managed, read-only bundle that updates when I ship, so you subscribe rather than fork”
   • [claimed-docs] “copies editable skill files into your project, so you can hack on them and make them your own”
   • [claimed-docs] “It writes the skills into your repo as ordinary files you own and can edit. Nothing updates behind your back”
   • [claimed-docs] “subscribe to the set as a read-only, always-current bundle you don't edit, rather than a fork you own”
   • [claimed-docs] “`mattpocock-skills` was accepted into **Claude Code's official marketplace**... `claude plugins install mattpocock-skills` is now the docume…”

   proof ↗⚑ flag

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

   weight 2 · round to Skills for Real Engineers
   Superpowers—none0/10

   All installation evidence describes installing the entire Superpowers plugin/skill bundle as one unit (e.g., '/plugin install superpowers@superpowers-marketplace', 'devin plugins install obra/superpowers', 'install from a git clone'), with no mechanism shown for selecting individual skills to install rather than the whole collection.

   • [claimed-docs] “/plugin marketplace add obra/superpowers-marketplace /plugin install superpowers@superpowers-marketplace”
   • [claimed-docs] “**Devin CLI**: `devin plugins install obra/superpowers` now works, and skills auto-trigger at session start.”
   • [claimed-docs] “**Hermes Agent**: install from a git clone; skills register with Hermes' native loader and the bootstrap loads on the first turn.”
   • [github] “Installation differs by harness. If you use more than one, install Superpowers separately for each one.”
   • [claimed-docs] “Add this marketplace to Claude Code: /plugin marketplace add obra/superpowers-marketplace”

   proof ↗⚑ flag

   Skills for Real Engineers~partialclaimed5/10

   The docs explicitly state "Install the ones you want, then type a slash command" (mattpocock-skills-docs-43), indicating selective installation is possible, and the file-copy mode writes only the skills you choose as editable files (mattpocock-skills-docs-24). However, the marketplace/plugin route is described as installing 'the whole set as a managed, read-only bundle' (mattpocock-skills-docs-1, docs-41), so whole-bundle install remains the primary documented path and there's no detailed CLI flag or command example showing per-skill selection. Missing for 10: a concrete CLI command/flag demonstrating selecting individual skills, and independent/hands-on confirmation that partial installs work as described.

   • [claimed-docs] “Install the ones you want, then type a slash command.”
   • [claimed-docs] “It writes the skills into your repo as ordinary files you own and can edit. Nothing updates behind your back”
   • [claimed-docs] “installs the whole set as a managed, read-only bundle that updates when I ship, so you subscribe rather than fork”
   • [claimed-docs] “subscribe to the set as a read-only, always-current bundle you don't edit, rather than a fork you own”

   proof ↗⚑ flag

Lifecycle

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

   weight 1 · round drawn
   Superpowers—none0/10

   Evidence covers installation across many harnesses (plugin marketplace, git clone, devin/hermes/grok CLIs) but there is no mention of a command or mechanism to list installed skills or cleanly uninstall/remove them without leftover files or instructions. missing for 10: a list-installed-skills command, an uninstall/remove workflow, and confirmation that removal leaves no orphaned files or lingering context injections.

   • [github] “Installation differs by harness. If you use more than one, install Superpowers separately for each one.”
   • [claimed-docs] “Everything ships through the harness's own install mechanism. Never edit the user's files.”
   • [claimed-docs] “This guide explains how to add support for a new harness ... so that Superpowers skills auto-trigger there the same way they do natively.”

   proof ↗⚑ flag

   Skills for Real Engineers—none0/10

   Evidence covers installation modes (editable copy vs. read-only subscribed bundle) and updating via `npx skills update`, but there is no mention of any command or mechanism to list installed skills or cleanly uninstall/remove them without leftover files.

   ⚑ flag

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

   weight 2 · round drawn
   Superpowers—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

   Skills for Real Engineers—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

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

   weight 2 · round to Skills for Real Engineers
   Superpowers~partialprobed5/10

   The product is hosted as a public GitHub repo with source files (skills/*.md, docs/, RELEASE-NOTES.md) directly viewable and clonable, implying open readability, but no evidence pack item cites an explicit OSS license (e.g., MIT/Apache) governing the code. missing for 10: explicit license file/declaration, independent confirmation of license terms, any mention of licensing terms at all.

   • [github] “Installation differs by harness. If you use more than one, install Superpowers separately for each one.”
   • [claimed-docs] “Skills (harness-agnostic). Everything in `skills/` is the source of truth, shared verbatim by every harness.”
   • [claimed-docs] “This guide explains how to add support for a new harness ... so that Superpowers skills auto-trigger there the same way they do natively.”
   • [probe] “PROBE llms.txt: HTTP 200 at https://github.com/llms.txt # GitHub > GitHub is a developer platform for building, shipping, and maintaining s…”

   proof ↗⚑ flag

   Skills for Real Engineers✓fullclaimed8/10

   The product's source lives in a public GitHub repo (github.com/mattpocock/skills) and is explicitly described as MIT-licensed with 25 skills, confirming both open-source hosting and license terms; docs also emphasize files are 'ordinary files you own and can edit,' reinforcing readability/openness of the source. Missing for 10: no explicit LICENSE file citation or independent third-party confirmation of the license text.

   • [claimed-docs] “Works with any agent Claude Code · Cursor · Codex · Copilot · 25 skills · MIT”
   • [claimed-docs] “It writes the skills into your repo as ordinary files you own and can edit. Nothing updates behind your back”
   • [claimed-docs] “copies editable skill files into your project, so you can hack on them and make them your own”

   proof ↗⚑ flag

3. ai-native userSelf-host the core product

   weight 3 · round to Skills for Real Engineers
   Superpowers~partialclaimed6/10

   Superpowers is fully open-source (GitHub repo) and its skills are installed and run entirely locally within whatever agent harness you already run (Claude Code, Devin, Hermes, Codex, etc.) via git clone or plugin install, meaning there's no cloud service to depend on — evidence of harness-agnostic 'skills/' as source of truth and multi-harness install instructions supports this. However, there's no explicit documentation framing this as 'self-hosting' or describing any server/infra component to host, since it's not a hosted service at all. Missing for 10: explicit self-hosting/deployment guide, any discussion of infra/server components, independent confirmation of running fully offline/air-gapped.

   • [claimed-docs] “Skills (harness-agnostic). Everything in `skills/` is the source of truth, shared verbatim by every harness.”
   • [github] “Installation differs by harness. If you use more than one, install Superpowers separately for each one.”
   • [claimed-docs] “Everything ships through the harness's own install mechanism. Never edit the user's files.”
   • [claimed-docs] “Codex, Copilot CLI, and Gemini CLI all also recognize `~/.agents/skills/` as a cross-runtime alias.”

   proof ↗⚑ flag

   Skills for Real Engineers✓fullclaimed7/10

   The product is an MIT-licensed, MIT-open GitHub repo of skill files that are copied directly into the user's own repo as editable, ordinary files ('you own and can edit... nothing updates behind your back'), which is effectively full self-hosting since there is no server component to host beyond the files themselves. This is corroborated by both the docs and the ADR describing the plugin/fork model. missing for 10: no independent/hands-on confirmation of a full self-hosted install working end-to-end outside vendor docs, and no explicit statement addressing infrastructure/hosting concerns (e.g., private registries, offline use).

   • [claimed-docs] “copies editable skill files into your project, so you can hack on them and make them your own”
   • [claimed-docs] “It writes the skills into your repo as ordinary files you own and can edit. Nothing updates behind your back”
   • [claimed-docs] “Nothing updates behind your back; pull my latest changes when you want them with `npx skills update`”
   • [claimed-docs] “subscribe to the set as a read-only, always-current bundle you don't edit, rather than a fork you own”

   proof ↗⚑ flag

1. ai-native userControl data retention and deletion

   weight 2 · round drawn
   Superpowers—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

   Skills for Real Engineers—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

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 Skills for Real Engineers
   Superpowers~partialcommunity5/10

   Skills are shipped as plain-text SKILL.md files in the public GitHub repo ('skills/' is the source of truth, shared verbatim) and a skills-search tool exists for discovery, so a lead can in principle browse/clone the repo and read every file before and after install. However, there is no dedicated 'list contents before install' review command, and community commentary notes the install mechanism for some harnesses is 'like curl|bash but with added LLM agents,' which cuts against an explicit, structured audit workflow. Missing for 10: a built-in pre-install manifest/listing command, documented post-install file-audit tooling, and independent confirmation that installers don't execute anything before a human can inspect files.

   • [claimed-docs] “Skills (harness-agnostic). Everything in `skills/` is the source of truth, shared verbatim by every harness.”
   • [claimed-docs] “20+ battle-tested skills; `/brainstorm`, `/write-plan`, `/execute-plan` commands; Skills-search tool for discovery; SessionStart context inj…”
   • [claimed-docs] “20+ battle-tested skills * `/brainstorm`, `/write-plan`, `/execute-plan` commands * Skills-search tool for discovery”
   • [community] “The install mechanism for the superpowers plugin for codex and opencode is .... interesting... it's like curl|bash but with added LLM agents…”
   • [claimed-docs] “Everything ships through the harness's own install mechanism. Never edit the user's files.”

   proof ↗⚑ flag

   Skills for Real Engineers~partialclaimed6/10

   The skills ship as plain, open-source Markdown SKILL.md files (visible directly via raw GitHub links quoted in evidence) and are described as 'ordinary files you own and can edit' with no silent updates, which supports post-install readability and transparency. However, there is no documented pre-install 'list contents' or dry-run command shown in the evidence — inspection relies on browsing the public GitHub repo rather than a built-in review step. Missing for 10: an explicit CLI/list command to preview a skill's files before installing, and independent confirmation that all installed files match what's shown pre-install.

   • [claimed-docs] “copies editable skill files into your project, so you can hack on them and make them your own”
   • [claimed-docs] “It writes the skills into your repo as ordinary files you own and can edit. Nothing updates behind your back”
   • [claimed-docs] “Nothing updates behind your back; pull my latest changes when you want them with `npx skills update`”
   • [claimed-docs] “Test only at pre-agreed seams. Before writing any test, write down the seams under test and confirm them with the user.”
   • [claimed-docs] “Scaffold the per-repo configuration that the engineering skills assume: **Issue tracker**... **Triage labels**... **Domain docs**”
   • [claimed-docs] “subscribe to the set as a read-only, always-current bundle you don't edit, rather than a fork you own”

   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 Skills for Real Engineers
   Superpowers—none0/10

   No evidence pack item documents a security posture statement, execution/permission model for skills, a trust model for vetting third-party skills (e.g., marketplace skills), or any telemetry/data-collection disclosure. Items like 'never edit the user's files' or worktree safety are incidental engineering safeguards, not a documented security posture for engineering-lead review.

   ⚑ flag

   Skills for Real Engineers~partialclaimed4/10

   The docs give some trust-relevant transparency—skills are shipped as plain, ownable files that 'nothing updates behind your back' and can be pulled explicitly via `npx skills update`, plus acceptance into Claude Code's official marketplace as a vetted distribution channel—but there is no explicit security-posture document covering what skills can execute (tool/permission scope), a formal trust model for arbitrary third-party skills, or any statement on telemetry/data collection. missing for 10: explicit execution/permission model for skills, documented telemetry or data-collection policy, formal third-party skill vetting/trust framework beyond marketplace acceptance.

   • [claimed-docs] “Nothing updates behind your back; pull my latest changes when you want them with `npx skills update`.”
   • [claimed-docs] “It writes the skills into your repo as ordinary files you own and can edit. Nothing updates behind your back”
   • [claimed-docs] “Nothing updates behind your back; pull my latest changes when you want them with `npx skills update`”
   • [claimed-docs] “`mattpocock-skills` was accepted into **Claude Code's official marketplace**... `claude plugins install mattpocock-skills` is now the docume…”
   • [claimed-docs] “subscribe to the set as a read-only, always-current bundle you don't edit, rather than a fork you own”

   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 to Superpowers
   Superpowers~partialclaimed4/10

   The product ships a dedicated 'writing-skills' SKILL.md that documents a TDD-like process for authoring skills (write test cases, watch fail, write skill doc, watch pass, refactor) and there's a 'skill authoring' capability mentioned in the plugin docs, implying some documented authoring path exists. However, no evidence explicitly shows a SKILL.md template with name/description frontmatter fields, nor confirms a developer can author without referencing/reverse-engineering existing skills — missing for 10: an explicit template/schema example with frontmatter fields, and confirmation the process doesn't require studying existing skill files.

   • [claimed-docs] “You write test cases (pressure scenarios with subagents), watch them fail (baseline behavior), write the skill (documentation), watch tests …”
   • [claimed-docs] “Claude learns brainstorming, subagent development with code review, debugging, TDD, and skill authoring through Superpowers.”
   • [claimed-docs] “Codex, Copilot CLI, and Gemini CLI all also recognize `~/.agents/skills/` as a cross-runtime alias.”

   proof ↗⚑ flag

   Skills for Real Engineers—none0/10

   The evidence describes an existing bundle of pre-built skills (tdd, grilling, triage, setup) that you can install, subscribe to, or copy as editable files, but there is no documented template, generator, or guide specifically for authoring a brand-new SKILL.md with frontmatter — the closest thing to a 'template' would be reverse-engineering the shipped example skills, which the story explicitly excludes. Community commentary even critiques the prose quality of existing skill files rather than pointing to any authoring template.

   • [claimed-docs] “copies editable skill files into your project, so you can hack on them and make them your own”
   • [claimed-docs] “It writes the skills into your repo as ordinary files you own and can edit. Nothing updates behind your back”
   • [claimed-docs] “Scaffold the per-repo configuration that the engineering skills assume: **Issue tracker**... **Triage labels**... **Domain docs**”
   • [community] “Critique of Matt Pocock's skill files: he has a hand-wavy approach to engineering in a silo, then uses that output as a foundation for tools…”

   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 to Superpowers
   Superpowers✓fullclaimed7/10

   The repo ships a dedicated `writing-skills` SKILL.md meta-skill that walks through writing test cases (pressure scenarios), watching them fail, authoring the skill doc, verifying compliance, and refactoring to close loopholes — directly matching the write/improve/package-a-skill workflow — and docs confirm 'Claude learns... skill authoring through Superpowers' plus cross-runtime packaging notes (harness-agnostic skills, `~/.agents/skills/` alias). Missing for 10: independent/community hands-on validation specifically of the skill-authoring meta-skill (community evidence only discusses the brainstorm/plan/TDD workflow, not skill-creation itself), and no concrete example of an end-to-end 'packaged' new skill produced via this meta-skill.

   • [claimed-docs] “You write test cases (pressure scenarios with subagents), watch them fail (baseline behavior), write the skill (documentation), watch tests …”
   • [claimed-docs] “Codex, Copilot CLI, and Gemini CLI all also recognize `~/.agents/skills/` as a cross-runtime alias.”
   • [claimed-docs] “Claude learns brainstorming, subagent development with code review, debugging, TDD, and skill authoring through Superpowers.”
   • [claimed-docs] “Skills (harness-agnostic). Everything in `skills/` is the source of truth, shared verbatim by every harness.”
   • [claimed-docs] “20+ battle-tested skills; `/brainstorm`, `/write-plan`, `/execute-plan` commands; Skills-search tool for discovery; SessionStart context inj…”

   proof ↗⚑ flag

   Skills for Real Engineers—none0/10

   The evidence describes many individual skills (TDD, triage, grilling, spec-writing, setup-per-repo config) but none of them describe a meta-skill that guides writing, improving, or packaging new skills for the collection itself — 'setup-matt-pocock-skills' only scaffolds per-repo config for existing skills, not skill authoring.

   ⚑ 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 Superpowers
   Superpowers✓fullclaimed8/10

   Docs show skills are harness-agnostic — 'Everything in skills/ is the source of truth, shared verbatim by every harness' (docs-13), porting only adds a bootstrap/tool-mapping layer and 'never reaches into skills/*/SKILL.md to swap tool names' (docs-37), and the same skill folder is confirmed working across Claude Code, Devin, Hermes, Codex, Gemini CLI, Copilot CLI and Grok Build CLI via a cross-runtime `~/.agents/skills/` alias (docs-31, docs-52-54). This directly supports the claim that the skill folder is valid beyond one vendor's tooling. Missing for 10: an explicit citation naming the 'Agent Skills' open specification itself, and independent (non-vendor) confirmation that the folder format is spec-conformant rather than just multi-harness-compatible.

   • [claimed-docs] “Skills (harness-agnostic). Everything in `skills/` is the source of truth, shared verbatim by every harness.”
   • [claimed-docs] “Codex, Copilot CLI, and Gemini CLI all also recognize `~/.agents/skills/` as a cross-runtime alias.”
   • [claimed-docs] “Porting adds a tool-mapping reference and a bootstrap injector; it never reaches into `skills/*/SKILL.md` to swap tool names.”
   • [claimed-docs] “Everything ships through the harness's own install mechanism. Never edit the user's files.”
   • [claimed-docs] “Devin CLI: `devin plugins install obra/superpowers` now works, and skills auto-trigger at session start.”
   • [claimed-docs] “Hermes Agent: install from a git clone; skills register with Hermes' native loader and the bootstrap loads on the first turn.”
   • [claimed-docs] “Grok Build CLI added to the install docs.”
   • [github] “Installation differs by harness. If you use more than one, install Superpowers separately for each one.”

   proof ↗⚑ flag

   Skills for Real Engineers~partialclaimed6/10

   Evidence shows skill folders are plain, editable files (SKILL.md) that work across multiple agents (Claude Code, Cursor, Codex, Copilot) and were accepted into Claude Code's official plugin marketplace, implying broad cross-tool portability consistent with an open skill format. However, none of the evidence explicitly names or cites conformance to the 'Agent Skills specification' itself, so spec-adherence is inferred rather than documented. Missing for 10: explicit reference to the Agent Skills spec, independent confirmation that the folder validates against that spec outside vendor claims.

   • [claimed-docs] “It writes the skills into your repo as ordinary files you own and can edit. Nothing updates behind your back”
   • [claimed-docs] “Works with any agent Claude Code · Cursor · Codex · Copilot · 25 skills · MIT”
   • [claimed-docs] “`mattpocock-skills` was accepted into **Claude Code's official marketplace**... `claude plugins install mattpocock-skills` is now the docume…”

   proof ↗⚑ flag

Maintenance

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

   weight 2 · round to Superpowers
   Superpowers~partialcommunity5/10

   RELEASE-NOTES.md shows frequent, detailed updates (new harness support, workflow fixes, workspace scoping, TDD doc rewrites) and HN community threads confirm users are tracking recent changes, indicating active maintenance and recent releases. However, there is no evidence of issue triage practices or accepted community pull requests/contributions. Missing for 10: evidence of issue triage process, evidence of merged community PRs/contributions, independent contributor activity beyond the single maintainer.

   • [claimed-docs] “Requests are classified as spike, bounded, or architectural; small tasks skip the two-document ritual. Every path still stops for your appro…”
   • [claimed-docs] “Worktree removal no longer destroys untracked files. When `git worktree remove` refuses because the tree holds uncommitted work, the skill s…”
   • [claimed-docs] “Devin CLI: `devin plugins install obra/superpowers` now works, and skills auto-trigger at session start.”
   • [claimed-docs] “Grok Build CLI added to the install docs.”
   • [community] “A recent update got rid of the subagents for the self review and now does the self review in the main agent.”

   proof ↗⚑ flag

   Skills for Real Engineers~partialcommunity3/10

   There's some indirect signal of active development — an ADR documenting a recent architectural decision (shipping as a Claude Code plugin) and acceptance into Claude Code's official marketplace, plus an update mechanism (`npx skills update`) implying ongoing releases — but no direct evidence of a release cadence, an issue tracker for the project itself being triaged, or accepted external community contributions/PRs. Community commentary (comm-1/2/3) shows engagement and critique of content quality but says nothing about maintenance cadence or contribution acceptance. missing for 10: changelog/release history, evidence of external PRs being merged, evidence of issues on the repo itself being triaged.

   • [claimed-docs] “`mattpocock-skills` was accepted into **Claude Code's official marketplace**... `claude plugins install mattpocock-skills` is now the docume…”
   • [claimed-docs] “subscribe to the set as a read-only, always-current bundle you don't edit, rather than a fork you own”
   • [claimed-docs] “Nothing updates behind your back; pull my latest changes when you want them with `npx skills update`.”
   • [community] “Matt Pocock is still a nice guy with reasonable opinions and shares a lot with us. I've personally learned from reading his skills.”
   • [community] “Critique of Matt Pocock's skill files: he has a hand-wavy approach to engineering in a silo, then uses that output as a foundation for tools…”

   proof ↗⚑ 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 to Superpowers
   Superpowers✓fullclaimed8/10

   The repo's testing docs describe a two-tier verification system: `tests/` for non-LLM code (bash/node/python integration tests) and `evals/` — a Python harness driving real tmux sessions across multiple agent CLIs with an LLM actor and verifier judging skill compliance — plus a documented TDD-style process for writing skills themselves (write pressure-scenario tests, watch them fail, write the skill, watch them pass, refactor to close loopholes). This is concrete, specific first-party evidence that skills aren't shipped on vibes but are eval-gated. Missing for 10: independent/community confirmation that the eval suite actually catches regressions in practice, and quantitative pass-rate or CI-run evidence beyond the docs themselves.

   • [claimed-docs] “Python harness driving real tmux sessions of Claude Code / Codex / Gemini CLI, with an LLM actor and verifier judging skill compliance.”
   • [claimed-docs] “You write test cases (pressure scenarios with subagents), watch them fail (baseline behavior), write the skill (documentation), watch tests …”
   • [claimed-docs] “tests/` — does the plugin's non-LLM code work? Bash + node + python integration tests for brainstorm-server JS, OpenCode plugin loading, cod…”
   • [claimed-docs] “evals/` — do agents behave correctly on real LLM sessions? Python harness driving real tmux sessions of Claude Code / Codex / Gemini CLI, wi…”
   • [claimed-docs] “tests/` — does the plugin's non-LLM code work? ... `evals/` — do agents behave correctly on real LLM sessions?”
   • [claimed-docs] “tests/ — does the plugin's non-LLM code work?... evals/ — do agents behave correctly on real LLM sessions? Python harness driving real tmux …”

   proof ↗⚑ flag

   Skills for Real Engineers—none0/10

   The evidence describes TDD/testing as a discipline the skills teach users to apply to their own code, but nothing shows the maintainer running automated tests, evals, or CI against the skill prompts themselves to catch regressions. A community critique even suggests the SKILL.md prose lacks rigor and 'should be checked... by another LLM,' implying no such verification pipeline exists.

   • [claimed-docs] “Red before green. Write the failing test first, then only enough code to pass it. Don't anticipate future tests or add speculative features.”
   • [claimed-docs] “Tests verify behavior through public interfaces, not implementation details.”
   • [community] “Critique of Matt Pocock's skill files: he has a hand-wavy approach to engineering in a silo, then uses that output as a foundation for tools…”

   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 Skills for Real Engineers
   Superpowers—none0/10

   The evidence describes install/update mechanisms (git clone, plugin marketplace, harness-specific installers, manual reinstall to update) but nowhere mentions version pinning, a lockfile, or any mechanism letting a lead control/freeze which skill version reaches the team versus picking up the latest on reinstall or auto-update.

   ⚑ flag

   Skills for Real Engineers~partialclaimed7/10

   Docs explicitly state skills don't auto-update and changes only land when the user runs `npx skills update`, and offer a 'copy' mode where files become editable local copies you fully own — both give an engineering lead control over rollout timing. However, there is no mention of an actual lockfile, pinned semantic versions, or per-team version pinning mechanism, so the control is manual/all-or-nothing rather than granular version pinning. Missing for 10: explicit lockfile/version-pin mechanism, ability to pin to a specific historical version rather than just delaying `update`, independent confirmation of update-control behavior in practice.

   • [claimed-docs] “Nothing updates behind your back; pull my latest changes when you want them with `npx skills update`.”
   • [claimed-docs] “It writes the skills into your repo as ordinary files you own and can edit. Nothing updates behind your back”
   • [claimed-docs] “Nothing updates behind your back; pull my latest changes when you want them with `npx skills update`”
   • [claimed-docs] “installs the whole set as a managed, read-only bundle that updates when I ship, so you subscribe rather than fork”
   • [claimed-docs] “copies editable skill files into your project, so you can hack on them and make them your own”
   • [claimed-docs] “subscribe to the set as a read-only, always-current bundle you don't edit, rather than a fork you own”

   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 Skills for Real Engineers
   Superpowers~partialclaimed6/10

   There is a documented update path — for the Antigravity harness, the docs explicitly state 'Reinstall with the same command to update,' and the marketplace install command (`/plugin marketplace add`/`/plugin install`) plus an actively maintained RELEASE-NOTES.md show a real versioning/update cadence. However, this is not a one-click marketplace auto-update: install/update differs by harness (separate reinstall per harness), and there's no first-party 'update' subcommand shown for most integrations. Missing for 10: an explicit auto-update mechanism or dedicated update command (vs. reinstall) that works uniformly across harnesses, and independent confirmation that reinstalling actually preserves user config/state.

   • [github] “Antigravity runs the plugin's session-start hook, so Superpowers is active from the first message. Reinstall with the same command to update…”
   • [github] “Installation differs by harness. If you use more than one, install Superpowers separately for each one.”
   • [claimed-docs] “Add this marketplace to Claude Code: /plugin marketplace add obra/superpowers-marketplace”
   • [claimed-docs] “/plugin marketplace add obra/superpowers-marketplace /plugin install superpowers@superpowers-marketplace”
   • [claimed-docs] “Ceremony now scales to the task. Requests are classified as spike, bounded, or architectural; small tasks skip the two-document ritual.”

   proof ↗⚑ flag

   Skills for Real Engineers✓fullclaimed8/10

   Docs explicitly document an update path: `npx skills update` pulls latest changes on demand (nothing auto-updates behind your back) for the copy-into-repo mode, and a separate managed/marketplace mode (Claude Code plugin, `claude plugins install mattpocock-skills`) that updates as the author ships. Both paths are documented first-party. missing for 10: independent/hands-on confirmation that `npx skills update` or marketplace auto-update actually works in practice, and no changelog/version-diff evidence showing successful update history.

   • [claimed-docs] “Nothing updates behind your back; pull my latest changes when you want them with `npx skills update`.”
   • [claimed-docs] “Nothing updates behind your back; pull my latest changes when you want them with `npx skills update`”
   • [claimed-docs] “It writes the skills into your repo as ordinary files you own and can edit. Nothing updates behind your back”
   • [claimed-docs] “`mattpocock-skills` was accepted into **Claude Code's official marketplace**... `claude plugins install mattpocock-skills` is now the docume…”
   • [claimed-docs] “subscribe to the set as a read-only, always-current bundle you don't edit, rather than a fork you own”
   • [claimed-docs] “installs the whole set as a managed, read-only bundle that updates when I ship, so you subscribe rather than fork”

   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 to Superpowers
   Superpowers✓fullclaimed7/10

   There is a maintained RELEASE-NOTES.md with per-release entries describing specific changes (worktree removal safety, workspace scoping, batching, TDD doc rewrites) plus new harness support additions like Devin/Hermes/Grok CLI, giving developers real changelog visibility before updating. missing for 10: no independent/community corroboration that release notes are consulted or trusted pre-update, and no explicit versioning scheme (semver/version tags) tying notes to installable releases.

   • [claimed-docs] “Requests are classified as spike, bounded, or architectural; small tasks skip the two-document ritual. Every path still stops for your appro…”
   • [claimed-docs] “Non-catastrophic conflicts and ambiguities get a recorded ruling and work continues; only destructive or irreversible actions still stop for…”
   • [claimed-docs] “Small same-shape tasks batch into one dispatch, cutting subagent cost sharply on micro-task plans; batch reviews verify every file in the br…”
   • [claimed-docs] “When `git worktree remove` refuses because the tree holds uncommitted work, the skill stops, names the files, and asks — instead of reaching…”
   • [claimed-docs] “a follow-up plan in the same working tree could read the previous plan's ledger as its own progress... `sdd-workspace` now requires the plan…”
   • [claimed-docs] “The review-fix loop resumes the implementer... installs a five-round circuit breaker with controller adjudication when it trips.”
   • [claimed-docs] “**Devin CLI**: `devin plugins install obra/superpowers` now works, and skills auto-trigger at session start.”
   • [claimed-docs] “**Hermes Agent**: install from a git clone; skills register with Hermes' native loader and the bootstrap loads on the first turn.”
   • [claimed-docs] “`testing-anti-patterns.md` is now `writing-good-tests.md`. The TDD reference doc is rebuilt as a positive catalog — six rules that lead with…”
   • [claimed-docs] “Grok Build CLI added to the install docs.”

   proof ↗⚑ flag

   Skills for Real Engineers—none0/10

   Evidence describes an update mechanism (`npx skills update`, subscribing to a read-only bundle) but nothing about release notes, a changelog, or version history that would let a developer see what changed before updating.

   ⚑ flag