Skip to content
ProductArena

Rank #5 of 5 in Agent Skills & Extensions

skills.sh logo

skills.sh

Open Source

Vercel

skills.sh ↗Try it →
PA Score18/100AGENT-READY29/100BUILT-IN AI0/100API0/100
MCP—CLI✓API~
★ 31.6k▲ 47.6k/yrnpm 4.6M/wk★ +1knpm/wk -4.7M
ArenasAgent Skills & Extensions#5/5

Access

Open app ↗CLI docs ↗

Install

npmnpx skills add vercel-labs/agent-skills
npmnpx skills find

Compare head-to-head

Superpowers logovs SuperpowersAnthropic Skills logovs Anthropic SkillsSkills for Real Engineers logovs Skills for Real EngineersCodex Plugins logovs Codex Plugins

Alternatives to skills.sh →

Showcase

skills.sh homepage screenshot
homepage · captured Sep 2026 · view live ↗
skills.sh docs screenshot
docs · captured Sep 2026 · view live ↗

Products

Vercel, product by product →

Vercel ships more than one product — each judged line competes in its own arena on the same stories as everyone else.

LineArenaRankPA Score
VercelEdge & App Platforms#4/625/100
v0Vibe-Coding App Builders#4/621/100
Vercel SandboxAgent Sandboxes & Code Execution#5/825/100
Vercel AI GatewayModel Gateways & Routers#3/729/100
skills.shthis pageAgent Skills & Extensions#5/518/100

Try itExperimental

See what an agent can do with skills.sh before you ever sign up. Pick a story: recorded sessions replay real probe-harness transcripts; sandboxed self-drive sessions are designed and gated (docs/TRY-IT.md).

$npx -y skills --versionrecorded session — replayed, not live
recorded 2026-09-06 · exit 0 · captured verbatim by our probe harness, secrets redacted

Verified integrations

Connections to other tracked products — hover a chip for the verbatim evidence quote behind it.

Claude Code logoClaude CodeAI Coding AgentsCodex logoCodexAI Coding AgentsCursor logoCursorAI Coding AgentsGitHub logoGitHubCode HostingOpenCode logoOpenCodeAI Coding AgentsSkills for Real Engineers logoSkills for Real EngineersAgent Skills & Extensions

By theme — the product's score on each story themeBy theme

Agent workflows — stories about agent workflows in this arenaAgent workflowsevidence →

Stories about agent workflows in this arena

76.0/100

Agenticness — how well agents can access and operate the productAgenticnessevidence →

How well agents can access and operate the product

15.8/100

Automation depth — how much of the product can run unattendedAutomation depthevidence →

How much of the product can run unattended

28.0/100

Cross agent portability — stories about cross agent portability in this arenaCross agent portabilityevidence →

Stories about cross agent portability in this arena

80.0/100

Discovery distribution — stories about discovery distribution in this arenaDiscovery distributionevidence →

Stories about discovery distribution in this arena

61.1/100

Docs onboarding — stories about docs onboarding in this arenaDocs onboardingevidence →

Stories about docs onboarding in this arena

49.6/100

Install experience — stories about install experience in this arenaInstall experienceevidence →

Stories about install experience in this arena

79.5/100

Openness — open source, data portability, and self-hosting storiesOpennessevidence →

Open source, data portability, and self-hosting stories

25.8/100

Privacy posture — data-handling and privacy storiesPrivacy postureevidence →

Data-handling and privacy stories

12.0/100

Safety review — stories about safety review in this arenaSafety reviewevidence →

Stories about safety review in this arena

18.0/100

Skill authoring — stories about skill authoring in this arenaSkill authoringevidence →

Stories about skill authoring in this arena

61.4/100

Testing quality — stories about testing quality in this arenaTesting qualityevidence →

Stories about testing quality in this arena

0.0/100

Versioning updates — stories about versioning updates in this arenaVersioning updatesevidence →

Stories about versioning updates in this arena

49.8/100

Story verdicts — every judged story with its evidenceStory verdicts

What’s free: 4 free · 0 paid · 0 enterprise · 24 not stated in evidence

?

Sorted by importance (agentic first) (high → low) · 52/52 stories · click a row’s chevron for the rationale and evidence

Drive the product through a documented public API G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3partial5/10X

Connect an agent via an official MCP server G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3none0/10

Delegate tasks to a built-in AI assistant inside the product G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness3noneuntestednone yet

Plug MCP servers into this product so it can use their tools G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3noneuntestednone yet

Use an official CLI G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full9/10X

Run the product headlessly / in CI for automation G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full8/10X

Point an agent at llms.txt or agent-oriented docs G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partial5/10T

Download a machine-readable API spec (OpenAPI or equivalent) G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Operate the product with natural-language commands G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Rely on versioned APIs with a documented deprecation policy G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Build against official SDKs G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2noneuntestednone yet

Explore an interactive API reference with runnable examples G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness2n/auntestednone yet

Get AI-generated insights and suggestions from my data inside the product G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness2noneuntestednone yet

Issue scoped/least-privilege API credentials for an agent G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2n/auntestednone yet

Set up automations that run autonomously in the background G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness2noneuntestednone yet

Subscribe to events via webhooks G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2n/auntestednone yet

Test against a sandbox environment without touching production data G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness1noneuntestednone yet

Install 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 C

Install

developerInstall experience — stories about install experience in this arenaInstall experience3full8/10X

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

Portability

developerCross agent portability — stories about cross agent portability in this arenaCross agent portability3full8/10C

My coding agent can install a skill by itself — a non-interactive, promptless install path an agent can run headlessly end to end C

Agent ops

ai-native userAgent workflows — stories about agent workflows in this arenaAgent workflows3full8/10C

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

Updates

developerVersioning updates — stories about versioning updates in this arenaVersioning updates3full8/10X

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

Authoring

developerSkill authoring — stories about skill authoring in this arenaSkill authoring3full7/10C

A quickstart takes me from nothing to a working installed skill in under five minutes C

Onboarding

developerDocs onboarding — stories about docs onboarding in this arenaDocs onboarding3partial6/10X

Installed skills trigger automatically from task context, with descriptions engineered so the agent activates the right skill at the right moment C

Triggering

developerDiscovery distribution — stories about discovery distribution in this arenaDiscovery distribution3partialfree6/10C

Export all of my data in open formats and leave G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness3partial5/10C

Review exactly what instructions and scripts a skill will add — list contents before installing and read every file afterward C

Review

engineering-leadSafety review — stories about safety review in this arenaSafety review3partial5/10X

Self-host the core product G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness3partialfree4/10T

Define rules that trigger actions automatically on events G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth3n/auntestednone yet

Prevent my data from being used to train AI models G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture3n/auntestednone yet

Choose install scope — project-local files committed with my repo, or user-global across all projects C

Install

developerInstall experience — stories about install experience in this arenaInstall experience2full9/10C

Install only the specific skills I want from a collection instead of taking the whole bundle C

Install

developerInstall experience — stories about install experience in this arenaInstall experience2fullfree9/10C

Browse or search a catalog of available skills — a registry, leaderboard, or marketplace listing — before installing anything C

Discovery

developerDiscovery distribution — stories about discovery distribution in this arenaDiscovery distribution2full8/10X

Distribute a standard skill set to my whole team — via a marketplace, a shared repo, or files committed to the project C

Distribution

engineering-leadDiscovery distribution — stories about discovery distribution in this arenaDiscovery distribution2full8/10X

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

Portability

developerCross agent portability — stories about cross agent portability in this arenaCross agent portability2full8/10C

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

Spec

developerSkill authoring — stories about skill authoring in this arenaSkill authoring2full8/10C

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

Onboarding

developerDocs onboarding — stories about docs onboarding in this arenaDocs onboarding2fullfree7/10C

My agent can author and package a new skill end to end by following the project's own spec, template, or meta-skill C

Agent ops

ai-native userAgent workflows — stories about agent workflows in this arenaAgent workflows2full7/10C

Perform bulk operations across many items at once G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth2partial6/10C

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

Authoring

developerSkill authoring — stories about skill authoring in this arenaSkill authoring2partial5/10C

Control data retention and deletion G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture2partial4/10X

Do everything through the API that I can do in the UI G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness2partial4/10X

Read the product's source under an open license G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness2partial4/10T

The collection is actively maintained — recent releases, triaged issues, and accepted community contributions C

Maintenance

developerTesting quality — stories about testing quality in this arenaTesting quality2none0/10

The collection maintains tests or evals for its skills so changes are verified against regressions rather than shipped on vibes C

Testing

developerTesting quality — stories about testing quality in this arenaTesting quality2none0/10

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

Trust

engineering-leadSafety review — stories about safety review in this arenaSafety review2none0/10

Choose where my data is stored (region/residency) G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture2n/auntestednone yet

Opt out of telemetry and usage tracking G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture2noneuntestednone yet

Schedule recurring jobs or workflows G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth2n/auntestednone yet

List what is installed and remove skills cleanly, without orphaned files or lingering instructions C

Lifecycle

developerInstall experience — stories about install experience in this arenaInstall experience1partial6/10X

Version, review, and roll back my automations G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth1disputed4/10D

Control when skill changes reach my team — pinned versions or a lockfile rather than silent behind-the-back updates C

Pinning

engineering-leadVersioning updates — stories about versioning updates in this arenaVersioning updates1disputed3/10D

Releases ship with notes or a changelog so I can see what changed in the skills before I take an update C

Updates

developerVersioning updates — stories about versioning updates in this arenaVersioning updates1none0/10

Opportunities — the stories that would move this product's scores, from its own judged verdictsOpportunitiestop 8 of 28 stories with headroom

What would move skills.sh’s scores — derived from its own judged verdicts, biggest headroom first. Each line quotes what the judge found missing; shipping it (or evidencing it publicly) is the fix.

  1. Agenticness — how well agents can access and operate the productDelegate tasks to a built-in AI assistant inside the product

    nonemoves Built-in AIimpact 45

    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".

  2. Agenticness — how well agents can access and operate the productPlug MCP servers into this product so it can use their tools

    nonemoves agent-readyimpact 45

    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".

  3. Agenticness — how well agents can access and operate the productConnect an agent via an official MCP server

    nonemoves agent-readyimpact 45

    skills.sh is a CLI package manager that installs skill files/prompts into agent directories (via add/use/symlink mechanisms), not an MCP server; no evidence anywhere in the pack mentions an MCP server or MCP protocol integration, only file-based/CLI installation across supported agents.

  4. Agenticness — how well agents can access and operate the productGet AI-generated insights and suggestions from my data inside the product

    nonemoves Built-in AIimpact 30

    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".

  5. Agenticness — how well agents can access and operate the productSet up automations that run autonomously in the background

    nonemoves Built-in AIimpact 30

    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".

  6. Agenticness — how well agents can access and operate the productOperate the product with natural-language commands

    nonemoves Built-in AIimpact 30

    skills.sh is a structured CLI (npm-style syntax like `npx skills add`, `--skill`, `--agent` flags) with no evidence of a natural-language command interface for operating the tool itself; all documented usage requires exact flag syntax.

  7. Agenticness — how well agents can access and operate the productBuild against official SDKs

    nonemoves agent-readyimpact 30

    Evidence shows only a CLI (`skills` npx tool) and a SKILL.md specification/validator, not an official SDK (e.g., a JS/Python library) for programmatic integration; no SDK is mentioned anywhere in the pack.

  8. Agenticness — how well agents can access and operate the productDownload a machine-readable API spec (OpenAPI or equivalent)

    nonemoves API qualityimpact 30

    Evidence shows a CLI tool and a Skill-format specification (SKILL.md schema, agentskills.io/specification.md), but no OpenAPI or machine-readable API spec for skills.sh itself; a community comment explicitly requests 'Please make a rest API!' implying none currently exists.

Showing the top 8 of 28 — every none/partial verdict in the story verdicts table is headroom.

Think a verdict is wrong? Every verdicts-table row has a Flag link — see the methodology.

Coverage map — which docs area, API section, or community source covers which judged storiesCoverage map5 surfaces · 30 covered stories

Where the cited evidence behind each covered verdict came from — the same citations the verdicts table shows, no extra judging.

GitHub README28 stories

Hacker News14 stories

Home docs8 stories

Specification docs5 stories

skills.sh4 stories

Probe proofs — replayable recordings from the probe harnessProbe proofs

Replayable recordings from our probe harness — see the Prove-It protocol to submit one.

$npx -y skills --versionreproduced
$ npx -y skills --version
\|/1.5.24
\
proves: Use an official CLIrecorded 2026-09-06
$npx -y skills add vercel-labs/agent-skills --listreproduced
$ npx -y skills add vercel-labs/agent-skills --list
\|/
███████╗██╗  ██╗██╗██╗     ██╗     ███████╗
██╔════╝██║ ██╔╝██║██║     ██║     ██╔════╝
███████╗█████╔╝ ██║██║     ██║     ███████╗
╚════██║██╔═██╗ ██║██║     ██║     ╚════██║
███████║██║  ██╗██║███████╗███████╗███████║
╚══════╝╚═╝  ╚═╝╚═╝╚══════╝╚══════╝╚══════╝

┌   skills 
│
◇  Source: https://github.com/vercel-labs/agent-skills.git
│

[
3
5
m
◒

[
3
9m

F
e
t
c
h
i
n
g

s
k
i
l
l
s
…
[
3
5
m
◐

[
3
9m

F
e
t
c
h
i
n
g

s
k
i
l
l
s
…
[
3
5
m
◓

[
3
9m

F
e
t
c
h
i
n
g

s
k
i
l
l
s
…
[
3
5
m
◑

[
3
9m

F
e
t
c
h
i
n
g

s
k
i
l
l
s
…
[
3
5
m
◒

[
3
9m

F
e
t
c
h
i
n
g

s
k
i
l
l
s
…
[
3
5
m
◐

[
3
9m

F
e
t
c
h
i
n
g

s
k
i
l
l
s
…
[
3
5
m
◓

[
3
9m

F
e
t
c
h
i
n
g

s
k
i
l
l
s
…◇  Found 9 skills

│
◇  Available Skills
│
│    vercel-composition-patterns
│
│      React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.
│
│    deploy-to-vercel
│
│      Deploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment".
│
│    vercel-react-best-practices
│
│      React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
│
│    vercel-react-native-skills
│
│      React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.
│
│    vercel-react-view-transitions
│
│      Guide for implementing smooth, native-feeling animations using React's View Transition API (`<ViewTransition>` component, `addTransitionType`, and CSS view transition pseudo-elements). Use this skill whenever the user wants to add page transitions, animate route changes, create shared element animations, animate enter/exit of components, animate list reorder, implement directional (forward/back) navigation animations, or integrate view transitions in Next.js. Also use when the user mentions view transitions, `startViewTransition`, `ViewTransition`, transition types, or asks about animating between UI states in React without third-party animation libraries.
│
│    vercel-cli-with-[redacted]s
│
│      Deploy and manage projects on Vercel using [redacted]-based authentication. Use when working with Vercel CLI using access [redacted]s rather than interactive login — e.g. "deploy to vercel", "set up vercel", "add environment variables to vercel".
│
│    vercel-optimize
│
│      Use for Vercel cost and performance optimization on deployed projects, especially Next.js, SvelteKit, Nuxt, and limited Astro apps. Collect Vercel metrics, usage, project config, and code scan results first; investigate only metric-backed candidates; produce ranked recommendations grounded in verified files and version-aware Vercel/framework docs. Trigger for Vercel bill reduction, slow or expensive routes, caching opportunities, Function Invocations, Build Minutes, Fast Data Transfer, Core Web Vitals, Bot Management, Fluid compute, or cost breakdown requests.
│
│    web-design-guidelines
│
│      Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
│
│    writing-guidelines
│
│      Review docs/prose for Writing Guidelines compliance. Use when asked to "review my docs", "check writing style", "audit prose", "review docs voice and tone", or "check this page against the writing handbook".

│
└  Use --skill <name> to install specific skills

\
proves: Browse or search a catalog of available skills — a registry, leaderboard, or marketplace listing — before installing anythingproves: Review exactly what instructions and scripts a skill will add — list contents before installing and read every file afterwardrecorded 2026-09-06

Claims vs evidence — vendor claims reconciled against independent verdictsClaims vs evidence

6 of 15 testable claims verified · 1 contradicted → integrity 27/100

26 distinct capability claims found in skills.sh’s own claimed-docs/GitHub materials, reconciled against our judge’s independent verdicts.

6

Verified

8

Unverified

1

Contradicted

14

Undersold

Verified (12)
Unverified (12)
Contradicted (1)
Undersold (14)
Claims outside our story set (3)

Real capability claims found in skills.sh’s own materials, but no story in this arena’s taxonomy covers them yet — that’s feedback on the taxonomy, not a mark against the product.

  • “Same install command works for public and private repos using existing configured auth”

    source ↗

  • “Installs create symlinks from each agent to one canonical skill copy, giving a single source of truth for updates”

    source ↗

  • “Install a skill directly from a raw SKILL.md file or archive download URL”

    source ↗
Suggest a story for these →

Business model

open-sourcefree-tier

MIT open-source CLI (npm "skills") plus the free skills.sh registry and leaderboard for the open agent-skills ecosystem; no paid tier — Vercel monetizes its hosting platform, not the CLI.

pricing ↗

Score trend

How this product’s scores have moved as evidence and verdicts are re-derived — a point per change, not per day.

PA Score19 (Sep 7 '26)18 (Sep 16 '26)
Agent-ready30 (Sep 7 '26)29 (Sep 16 '26)

Try Experimental

Run it in the microterminal →

Recorded agent sessions — and a live MCP handshake where the vendor ships one.

Flag

⚑ Flag a verdict

Think a verdict is wrong? Opens a prefilled GitHub issue — or use the ⚑ next to any verdict above.

Badge

Embed this product's score badge →

Hotlinked SVG — always shows the live current score.

For agents

This page as markdown/llms.txt

Data

Evidence (JSON)Verdicts (JSON)

Agent surface uptime llms.txt 100% (30d, checked every 6h since Sep 8 '26)