Agent Skills & Extensions arenaAgent Skills & Extensions
Skill collections, plugin catalogs, and the tooling that packages reusable instructions, workflows, and methodologies for coding agents — judged on install experience, skill authoring, discovery, versioning and updates, cross-agent portability, safety and review posture, testing, and docs. MCP server registries and gateways (Smithery, etc.) are judged separately in the MCP Infrastructure arena: registries of tool servers live there, packaged skill content and its distribution tooling live here. Disclosure: the Anthropic Skills entry is published by Anthropic, whose Claude model is also the judge for every arena on this site — it is judged by the same evidence rules as every other product, and every verdict is contestable (see the README bias disclosure).
52 user stories · 260 judged cells · updated 2026-09-16 · Evidence as of 2026-09-16
Leaderboard — every product ranked by evidenceLeaderboard
| 1 | free-tier vs Superpowers ↗ | 54/100 | 14/100 | 12/100 | 9/100 | 12/100 | ★ 176.2k▲ 180.5k/yr | 7/33 verified · 5 disputed | 0/100 integrity | ||
| 2 | support-contracts vs Anthropic Skills ↗ | 8/100 | 36/100 | 24/100 | 24/100 | 30/100 | ★ 286.3k▲ 308.1k/yr | 13/28 verified | 0/100 integrity | ||
| 3 | free-tier vs Anthropic Skills ↗ | 18/100 | 26/100 | 0/100 | 46/100 | 4/100 | ★ 261.5k▲ 428.7k/yr | 3/24 verified | 17/100 integrity | ||
| 4 | subscription-per-seat vs Anthropic Skills ↗ | 33/100 | 47/100 | 0/100 | 4/100 | 7/100 | ★ 6.6k▲ 12.5k/yr | 11/26 verified | 36/100 integrity | ||
| 5 | free-tier vs Anthropic Skills ↗ | 29/100 | 0/100 | 0/100 | 26/100 | 28/100 | ★ 31.6k▲ 47.6k/yrnpm 4.6M/wk | 15/30 verified · 2 disputed | 27/100 integrity |
Best by user type — persona-weighted winnersBest by user type
Per persona, the product with the highest persona-weighted coverage over just that persona's stories — not the same ranking as the overall PA Score leaderboard above.
Best for engineering-lead
Skills for Real Engineers
45/100
Runner-up:
Codex Plugins (37/100)
4 engineering-lead stories scored
Story matrix — every product × every judged storyStory matrix
Agent workflows — stories about agent workflows in this arenaAgent workflows
Agent ops
| Story | Persona | |||||
|---|---|---|---|---|---|---|
| Agent workflows — stories about agent workflows in this arenaMy agent can author and package a new skill end to end by following the project's own spec, template, or meta-skill | ai-native | fullX 8/10 | fullC 9/10 | none 0/10 | fullC 7/10 | fullX 8/10 |
| Agent workflows — stories about agent workflows in this arenaMy coding agent can install a skill by itself — a non-interactive, promptless install path an agent can run headlessly end to end | ai-native | none 0/10 | partialC 4/10 | partialC 4/10 | fullC 8/10 | partialC 5/10 |
Agenticness — how well agents can access and operate the productAgenticness
Agent access
| Story | Persona | |||||
|---|---|---|---|---|---|---|
| Agenticness — how well agents can access and operate the productPoint an agent at llms.txt or agent-oriented docs | ai-native | partialT 5/10 | fullT 8/10 | partialT 5/10 | partialT 5/10 | partialT 5/10 |
| Agenticness — how well agents can access and operate the productRun the product headlessly / in CI for automation | ai-native | none 0/10 | partialC 5/10 | none 0/10 | fullX 8/10 | none 0/10 |
| Agenticness — how well agents can access and operate the productPlug MCP servers into this product so it can use their tools | ai-native | n/a | partialX 5/10 | n/a | none 0/10 | fullC 8/10 |
| Agenticness — how well agents can access and operate the productConnect an agent via an official MCP server | ai-native | none 0/10 | n/a | none 0/10 | none 0/10 | n/a |
| Agenticness — how well agents can access and operate the productUse an official CLI | ai-native | n/a | partialT 5/10 | fullC 7/10 | fullX 9/10 | fullT 8/10 |
| Agenticness — how well agents can access and operate the productDrive the product through a documented public API | ai-native | none 0/10 | fullC 8/10 | n/a | partialX 5/10 | none 0/10 |
| Agenticness — how well agents can access and operate the productIssue scoped/least-privilege API credentials for an agent | ai-native | n/a | n/a | n/a | n/a | none 0/10 |
| Agenticness — how well agents can access and operate the productBuild against official SDKs | ai-native | partialC 3/10 | fullC 7/10 | none 0/10 | none 0/10 | partialT 5/10 |
| Agenticness — how well agents can access and operate the productSubscribe to events via webhooks | ai-native | n/a | n/a | n/a | n/a | n/a |
Agentic features
| Story | Persona | |||||
|---|---|---|---|---|---|---|
| Agenticness — how well agents can access and operate the productGet AI-generated insights and suggestions from my data inside the product | ai-native | none 0/10 | partialX 4/10 | partialC 6/10 | none 0/10 | partialC 6/10 |
| Agenticness — how well agents can access and operate the productSet up automations that run autonomously in the background | ai-native | partialC 5/10 | none 0/10 | none 0/10 | none 0/10 | none 0/10 |
| Agenticness — how well agents can access and operate the productDelegate tasks to a built-in AI assistant inside the product | ai-native | partialX 6/10 | disputedD 5/10 | none 0/10 | none 0/10 | fullC 7/10 |
| Agenticness — how well agents can access and operate the productOperate the product with natural-language commands | ai-native | fullX 8/10 | disputedD 5/10 | fullC 8/10 | none 0/10 | fullX 7/10 |
Api quality
| Story | Persona | |||||
|---|---|---|---|---|---|---|
| Agenticness — how well agents can access and operate the productExplore an interactive API reference with runnable examples | ai-native | n/a | n/a | n/a | n/a | none 0/10 |
| Agenticness — how well agents can access and operate the productDownload a machine-readable API spec (OpenAPI or equivalent) | ai-native | n/a | partialC 3/10 | n/a | none 0/10 | none 0/10 |
| Agenticness — how well agents can access and operate the productTest against a sandbox environment without touching production data | ai-native | partialC 4/10 | partialC 4/10 | none 0/10 | none 0/10 | none 0/10 |
| Agenticness — how well agents can access and operate the productRely on versioned APIs with a documented deprecation policy | ai-native | n/a | none 0/10 | none 0/10 | none 0/10 | none 0/10 |
Automation depth — how much of the product can run unattendedAutomation depth
| Story | Persona | |||||
|---|---|---|---|---|---|---|
| Automation depth — how much of the product can run unattendedPerform bulk operations across many items at once | ai-native | partialC 5/10 | partialX 3/10 | none 0/10 | partialC 6/10 | none 0/10 |
| Automation depth — how much of the product can run unattendedDefine rules that trigger actions automatically on events | ai-native | partialC 5/10 | disputedD 4/10 | none 0/10 | n/a | partialC 3/10 |
| Automation depth — how much of the product can run unattendedSchedule recurring jobs or workflows | ai-native | n/a | none 0/10 | n/a | n/a | none 0/10 |
| Automation depth — how much of the product can run unattendedVersion, review, and roll back my automations | ai-native | partialC 5/10 | partialC 4/10 | partialC 4/10 | disputedD 4/10 | none 0/10 |
Cross agent portability — stories about cross agent portability in this arenaCross agent portability
Portability
| Story | Persona | |||||
|---|---|---|---|---|---|---|
| Cross agent portability — stories about cross agent portability in this arenaInstall the same collection into multiple different coding agents — Claude Code, Codex, Cursor, and others — with per-harness instructions | developer | fullX 8/10 | partialC 4/10 | partialC 6/10 | fullC 8/10 | none 0/10 |
| Cross agent portability — stories about cross agent portability in this arenaSkills are plain markdown files and folders I can read, copy, and carry to another harness — not a proprietary binary format | developer | fullC 8/10 | fullC 9/10 | fullC 8/10 | fullC 8/10 | partialC 6/10 |
Discovery distribution — stories about discovery distribution in this arenaDiscovery distribution
Discovery
| Story | Persona | |||||
|---|---|---|---|---|---|---|
| Discovery distribution — stories about discovery distribution in this arenaBrowse or search a catalog of available skills — a registry, leaderboard, or marketplace listing — before installing anything | developer | partialC 6/10 | partialC 6/10 | partialC 6/10 | fullX 8/10 | fullC 8/10 |
Distribution
| Story | Persona | |||||
|---|---|---|---|---|---|---|
| Discovery distribution — stories about discovery distribution in this arenaDistribute a standard skill set to my whole team — via a marketplace, a shared repo, or files committed to the project | engineering-lead | fullX 8/10 | fullC 8/10 | fullC 8/10 | fullX 8/10 | fullX 8/10 |
Triggering
| Story | Persona | |||||
|---|---|---|---|---|---|---|
| Discovery distribution — stories about discovery distribution in this arenaInstalled skills trigger automatically from task context, with descriptions engineered so the agent activates the right skill at the right moment | developer | fullX 7/10 | disputedD 5/10 | none 0/10 | partialC 6/10 | partialX 7/10 |
Docs onboarding — stories about docs onboarding in this arenaDocs onboarding
Onboarding
| Story | Persona | |||||
|---|---|---|---|---|---|---|
| Docs onboarding — stories about docs onboarding in this arenaA quickstart takes me from nothing to a working installed skill in under five minutes | developer | partialX 6/10 | partialX 6/10 | partialC 6/10 | partialX 6/10 | partialC 6/10 |
| Docs onboarding — stories about docs onboarding in this arenaEvery skill documents what it does and when it activates, so I can predict my agent's new behavior before it surprises me | developer | partialX 7/10 | disputedD 5/10 | fullX 7/10 | fullC 7/10 | partialX 7/10 |
Install experience — stories about install experience in this arenaInstall experience
Install
| Story | Persona | |||||
|---|---|---|---|---|---|---|
| Install experience — stories about install experience in this arenaInstall 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 | developer | fullX 8/10 | partialC 6/10 | partialC 6/10 | fullX 8/10 | fullC 7/10 |
| Install experience — stories about install experience in this arenaChoose install scope — project-local files committed with my repo, or user-global across all projects | developer | none 0/10 | partialC 4/10 | partialC 4/10 | fullC 9/10 | partialC 5/10 |
| Install experience — stories about install experience in this arenaInstall only the specific skills I want from a collection instead of taking the whole bundle | developer | none 0/10 | partialC 6/10 | partialC 5/10 | fullC 9/10 | partialC 6/10 |
Lifecycle
| Story | Persona | |||||
|---|---|---|---|---|---|---|
| Install experience — stories about install experience in this arenaList what is installed and remove skills cleanly, without orphaned files or lingering instructions | developer | none 0/10 | none 0/10 | none 0/10 | partialX 6/10 | partialC 3/10 |
Openness — open source, data portability, and self-hosting storiesOpenness
| Story | Persona | |||||
|---|---|---|---|---|---|---|
| Openness — open source, data portability, and self-hosting storiesDo everything through the API that I can do in the UI | ai-native | none 0/10 | partialC 5/10 | none 0/10 | partialX 4/10 | none 0/10 |
| Openness — open source, data portability, and self-hosting storiesExport all of my data in open formats and leave | ai-native | n/a | none 0/10 | partialC 5/10 | partialC 5/10 | none 0/10 |
| Openness — open source, data portability, and self-hosting storiesRead the product's source under an open license | ai-native | partialT 5/10 | none 0/10 | fullC 8/10 | partialT 4/10 | partialC 3/10 |
| Openness — open source, data portability, and self-hosting storiesSelf-host the core product | ai-native | partialC 6/10 | n/a | fullC 7/10 | partialT 4/10 | none 0/10 |
Privacy posture — data-handling and privacy storiesPrivacy posture
| Story | Persona | |||||
|---|---|---|---|---|---|---|
| Privacy posture — data-handling and privacy storiesChoose where my data is stored (region/residency) | ai-native | n/a | n/a | n/a | n/a | n/a |
| Privacy posture — data-handling and privacy storiesPrevent my data from being used to train AI models | ai-native | n/a | n/a | n/a | n/a | none 0/10 |
| Privacy posture — data-handling and privacy storiesControl data retention and deletion | ai-native | none 0/10 | none 0/10 | none 0/10 | partialX 4/10 | none 0/10 |
| Privacy posture — data-handling and privacy storiesOpt out of telemetry and usage tracking | ai-native | n/a | n/a | none 0/10 | none 0/10 | none 0/10 |
Safety review — stories about safety review in this arenaSafety review
Review
| Story | Persona | |||||
|---|---|---|---|---|---|---|
| Safety review — stories about safety review in this arenaReview exactly what instructions and scripts a skill will add — list contents before installing and read every file afterward | engineering-lead | partialX 5/10 | partialC 6/10 | partialC 6/10 | partialX 5/10 | partialC 5/10 |
Trust
| Story | Persona | |||||
|---|---|---|---|---|---|---|
| Safety review — stories about safety review in this arenaThe project documents its security posture — what skills can execute, the trust model for third-party skills, and any telemetry or data collection | engineering-lead | none 0/10 | none 0/10 | partialC 4/10 | none 0/10 | partialC 4/10 |
Skill authoring — stories about skill authoring in this arenaSkill authoring
Authoring
| Story | Persona | |||||
|---|---|---|---|---|---|---|
| Skill authoring — stories about skill authoring in this arenaAuthor a new skill from a documented template — a SKILL.md with name and description frontmatter — without reverse-engineering existing skills | developer | partialC 4/10 | fullX 8/10 | none 0/10 | fullC 7/10 | fullX 8/10 |
| Skill authoring — stories about skill authoring in this arenaThe collection ships a meta-skill or tool that guides my agent through writing, improving, and packaging new skills | developer | fullC 7/10 | fullC 8/10 | none 0/10 | partialC 5/10 | fullX 8/10 |
Spec
| Story | Persona | |||||
|---|---|---|---|---|---|---|
| Skill authoring — stories about skill authoring in this arenaSkills follow the open Agent Skills specification so the same skill folder is valid beyond this one vendor's tooling | developer | fullC 8/10 | fullC 8/10 | partialC 6/10 | fullC 8/10 | partialX 6/10 |
Testing quality — stories about testing quality in this arenaTesting quality
Maintenance
| Story | Persona | |||||
|---|---|---|---|---|---|---|
| Testing quality — stories about testing quality in this arenaThe collection is actively maintained — recent releases, triaged issues, and accepted community contributions | developer | partialX 5/10 | none 0/10 | partialX 3/10 | none 0/10 | none 0/10 |
Testing
| Story | Persona | |||||
|---|---|---|---|---|---|---|
| Testing quality — stories about testing quality in this arenaThe collection maintains tests or evals for its skills so changes are verified against regressions rather than shipped on vibes | developer | fullC 8/10 | none 0/10 | none 0/10 | none 0/10 | none 0/10 |
Versioning updates — stories about versioning updates in this arenaVersioning updates
Pinning
| Story | Persona | |||||
|---|---|---|---|---|---|---|
| Versioning updates — stories about versioning updates in this arenaControl when skill changes reach my team — pinned versions or a lockfile rather than silent behind-the-back updates | engineering-lead | none 0/10 | partialC 5/10 | partialC 7/10 | disputedD 3/10 | none 0/10 |
Updates
| Story | Persona | |||||
|---|---|---|---|---|---|---|
| Versioning updates — stories about versioning updates in this arenaThere is a documented update path — marketplace auto-updates or an explicit update command — so I get fixes without reinstalling from scratch | developer | partialC 6/10 | partialC 6/10 | fullC 8/10 | fullX 8/10 | none 0/10 |
| Versioning updates — stories about versioning updates in this arenaReleases ship with notes or a changelog so I can see what changed in the skills before I take an update | developer | fullC 7/10 | none 0/10 | none 0/10 | none 0/10 | none 0/10 |
Adjacent arenas — categories often shopped togetherAdjacent arenas
Shopping this category often means shopping these too.
AI Coding Agents arenaAI Coding Agents
13 products · leader: OpenCode
MCP Infrastructure & Registries arenaMCP Infrastructure & Registries
6 products · leader: Composio
Agent Frameworks & SDKs arenaAgent Frameworks & SDKs
9 products · leader: Claude Agent SDK
Serverless & Developer Databases arenaServerless & Developer Databases
5 products · leader: ClickHouse
shares: Agent workflows