Skip to content
ProductArena

How skills.sh’s scores are calculated

The full audit trail, recomputed from the verdict data at build time through the same code that produced the leaderboard: verdict × quality × story weight per cell, cells sum to dimension scores, dimensions blend into the PA Score. Every number on the product page is reproducible from this page alone; for why the formula looks like this, see the methodology.

verdict factors: full ×1.0 · partial ×0.6 · disputed ×0.3 · none ×0.0 · n/a excluded from both sides · cell points = weight × quality × factor · cell max = weight × 10

PA Score18/100

Agent-ready 28.8 × 0.30 = 8.64

API quality 0.0 × 0.20 = 0.00

Openness 25.8 × 0.20 = 5.16

Built-in AI 0.0 × 0.15 = 0.00

Automation 28.0 × 0.15 = 4.20

(8.64 + 0.00 + 5.16 + 0.00 + 4.20) ÷ (0.30 + 0.20 + 0.20 + 0.15 + 0.15) = 18.00 ÷ 1.00 = 18.0

Scores are stored to 1 decimal; the product page’s pills round to whole numbers for display. Each dimension below shows the stories, verdicts, and cited evidence behind its number.

Agent-ready28.8/100×0.30 of the PA blend

Outside-in: can YOUR agent reach and drive this product — API, MCP, CLI, headless runs, agent docs.

Point an agent at llms.txt or agent-oriented docsweight 2

2 (weight) × 5 (quality) × 0.6 (partial) = 6.0 of 20 max

  • [claimed-docs] https://raw.githubusercontent.com/vercel-labs/skills/HEAD/AGENTS.md“`skills experimental_install` | Restore skills from skills-lock.json”
  • [claimed-docs] https://raw.githubusercontent.com/vercel-labs/skills/HEAD/AGENTS.md“skills list | List installed skills (alias: `ls`)”
  • [claimed-docs] https://raw.githubusercontent.com/vercel-labs/skills/HEAD/AGENTS.md“skills update [skills...] | Update skills to latest versions”
  • [claimed-docs] https://raw.githubusercontent.com/vercel-labs/skills/HEAD/AGENTS.md“skills init [name] | Create a new SKILL.md template”
  • [claimed-docs] https://raw.githubusercontent.com/vercel-labs/skills/HEAD/AGENTS.md“skills experimental_sync | Sync skills from node_modules into agent dirs”
  • [probe] https://github.com/vercel-labs/skills.md“PROBE docs-md: HTTP 404 at https://github.com/vercel-labs/skills.md”

Run the product headlessly / in CI for automationweight 2

2 (weight) × 8 (quality) × 1.0 (full) = 16.0 of 20 max

  • [github] https://github.com/vercel-labs/skills“Non-interactive installation (CI/CD friendly)”
  • [github] https://github.com/vercel-labs/skills“npx skills add vercel-labs/agent-skills --skill frontend-design -g -a claude-code -y”
  • [github] https://github.com/vercel-labs/skills“# Non-interactive installation (CI/CD friendly) npx skills add vercel-labs/agent-skills --skill frontend-design -g -a claude-code -y”
  • [github] https://github.com/vercel-labs/skills“Use the same command for public and private repositories. The CLI uses the authentication already configured for the repository URL”
  • [community] https://hn.algolia.com/api/v1/items/46697908“Please make a rest API!”

Plug MCP servers into this product so it can use their toolsweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Connect an agent via an official MCP serverweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

  • [github] https://github.com/vercel-labs/skills“npx skills add vercel-labs/agent-skills”
  • [github] https://github.com/vercel-labs/skills“Target specific agents (e.g., `claude-code`, `codex`)”
  • [github] https://github.com/vercel-labs/skills“Supports **OpenCode**, **Claude Code**, **Codex**, **Cursor**, and [73 more](#supported-agents).”
  • [claimed-docs] https://agentskills.io/home“Cross-product reuse: Build a skill once and use it across any skills-compatible agent.”

Use an official CLIweight 2

2 (weight) × 9 (quality) × 1.0 (full) = 18.0 of 20 max

  • [github] https://github.com/vercel-labs/skills“npx skills add vercel-labs/agent-skills”
  • [github] https://github.com/vercel-labs/skills“Target specific agents (e.g., `claude-code`, `codex`)”
  • [github] https://github.com/vercel-labs/skills“Non-interactive installation (CI/CD friendly)”
  • [github] https://github.com/vercel-labs/skills“List all installed skills. Similar to `npm ls`.”
  • [github] https://github.com/vercel-labs/skills“Update installed skills to latest versions”
  • [github] https://github.com/vercel-labs/skills“Remove installed skills from agents”
  • [github] https://github.com/vercel-labs/skills“Supports **OpenCode**, **Claude Code**, **Codex**, **Cursor**, and [73 more](#supported-agents).”
  • [claimed-docs] https://raw.githubusercontent.com/vercel-labs/skills/HEAD/AGENTS.md“skills list | List installed skills (alias: `ls`)”
  • [claimed-docs] https://raw.githubusercontent.com/vercel-labs/skills/HEAD/AGENTS.md“skills update [skills...] | Update skills to latest versions”
  • [community] https://hn.algolia.com/api/v1/items/46697908“The leaderboard is ranked by the weekly download count from their 'npx skills' command. This is Vercel's new 'standard' skills installer so it's obvious their skills are at the top.”
  • [community] https://hn.algolia.com/api/v1/items/46697908“Why do none of these 'npm for Skills' document any way to do basic package management things like updates, version-pinning, or even uninstalls?”

Drive the product through a documented public APIweight 3

3 (weight) × 5 (quality) × 0.6 (partial) = 9.0 of 30 max

  • [github] https://github.com/vercel-labs/skills“Non-interactive installation (CI/CD friendly)”
  • [github] https://github.com/vercel-labs/skills“# Non-interactive installation (CI/CD friendly) npx skills add vercel-labs/agent-skills --skill frontend-design -g -a claude-code -y”
  • [claimed-docs] https://raw.githubusercontent.com/vercel-labs/skills/HEAD/AGENTS.md“skills list | List installed skills (alias: `ls`)”
  • [claimed-docs] https://raw.githubusercontent.com/vercel-labs/skills/HEAD/AGENTS.md“skills update [skills...] | Update skills to latest versions”
  • [claimed-docs] https://raw.githubusercontent.com/vercel-labs/skills/HEAD/AGENTS.md“skills init [name] | Create a new SKILL.md template”
  • [claimed-docs] https://raw.githubusercontent.com/vercel-labs/skills/HEAD/AGENTS.md“skills experimental_sync | Sync skills from node_modules into agent dirs”
  • [community] https://hn.algolia.com/api/v1/items/46697908“Please make a rest API!”

Issue scoped/least-privilege API credentials for an agentweight 2

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Build against official SDKsweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Subscribe to events via webhooksweight 2

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Agent-ready = 49.0 ÷ 170 × 100 = 28.8

API quality0.0/100×0.20 of the PA blend

The programmable surface once an agent is there — machine-readable spec, interactive docs, sandbox, versioning discipline.

Explore an interactive API reference with runnable examplesweight 2

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Download a machine-readable API spec (OpenAPI or equivalent)weight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [claimed-docs] https://agentskills.io/specification.md“skills-ref validate ./my-skill”
  • [community] https://hn.algolia.com/api/v1/items/46697908“Please make a rest API!”

Test against a sandbox environment without touching production dataweight 1

1 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 10 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Rely on versioned APIs with a documented deprecation policyweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [community] https://hn.algolia.com/api/v1/items/46697908“Why do none of these 'npm for Skills' document any way to do basic package management things like updates, version-pinning, or even uninstalls?”
  • [community] https://hn.algolia.com/api/v1/items/46697908“Please make a rest API!”

API quality = 0.0 ÷ 50 × 100 = 0.0

Openness25.8/100×0.20 of the PA blend

Can you leave, inspect, or self-host — data export, open source, portability.

Do everything through the API that I can do in the UIweight 2

2 (weight) × 4 (quality) × 0.6 (partial) = 4.8 of 20 max

  • [github] https://github.com/vercel-labs/skills“npx skills add vercel-labs/agent-skills”
  • [github] https://github.com/vercel-labs/skills“Search for skills interactively or by keyword”
  • [github] https://github.com/vercel-labs/skills“List all installed skills. Similar to `npm ls`.”
  • [github] https://github.com/vercel-labs/skills“Update installed skills to latest versions”
  • [github] https://github.com/vercel-labs/skills“Remove installed skills from agents”
  • [community] https://hn.algolia.com/api/v1/items/46697908“Please make a rest API!”
  • [claimed-docs] https://skills.sh“Skills Leaderboard”

Export all of my data in open formats and leaveweight 3

3 (weight) × 5 (quality) × 0.6 (partial) = 9.0 of 30 max

  • [github] https://github.com/vercel-labs/skills“Creates symlinks from each agent to a canonical copy. Single source of truth, easy updates.”
  • [github] https://github.com/vercel-labs/skills“Symlink (Recommended) | Creates symlinks from each agent to a canonical copy. Single source of truth, easy updates.”
  • [claimed-docs] https://raw.githubusercontent.com/vercel-labs/skills/HEAD/AGENTS.md“`skills experimental_install` | Restore skills from skills-lock.json”
  • [claimed-docs] https://raw.githubusercontent.com/vercel-labs/skills/HEAD/AGENTS.md“skills experimental_install | Restore skills from skills-lock.json”
  • [github] https://github.com/vercel-labs/skills“**Project** | (default) | `./<agent>/skills/` | Committed with your project, shared with team”
  • [github] https://github.com/vercel-labs/skills“**Project** | (default) | `./<agent>/skills/` | Committed with your project, shared with team | **Global** | `-g` | `~/<agent>/skills/` | Available across all projects”

Read the product's source under an open licenseweight 2

2 (weight) × 4 (quality) × 0.6 (partial) = 4.8 of 20 max

  • [probe] https://github.com/vercel-labs/skills“official CLI documented at https://github.com/vercel-labs/skills”
  • [github] https://github.com/vercel-labs/skills“npx skills add vercel-labs/agent-skills”
  • [claimed-docs] https://raw.githubusercontent.com/vercel-labs/skills/HEAD/AGENTS.md“skills experimental_install | Restore skills from skills-lock.json”

Self-host the core productweight 3

3 (weight) × 4 (quality) × 0.6 (partial) = 7.2 of 30 max

  • [probe] https://github.com/vercel-labs/skills“official CLI documented at https://github.com/vercel-labs/skills”
  • [github] https://github.com/vercel-labs/skills“npx skills add vercel-labs/agent-skills”
  • [github] https://github.com/vercel-labs/skills“Use the same command for public and private repositories. The CLI uses the authentication already configured for the repository URL”
  • [claimed-docs] https://skills.sh“Skills Leaderboard”

Openness = 25.8 ÷ 100 × 100 = 25.8

Built-in AI0.0/100×0.15 of the PA blend

Inside-out: how agentic the product itself is for its users — built-in assistants, autonomous features.

Get AI-generated insights and suggestions from my data inside the productweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Set up automations that run autonomously in the backgroundweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Delegate tasks to a built-in AI assistant inside the productweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Operate the product with natural-language commandsweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [github] https://github.com/vercel-labs/skills“npx skills add vercel-labs/agent-skills”
  • [github] https://github.com/vercel-labs/skills“Install specific skills by name (use `'*'` for all skills)”
  • [github] https://github.com/vercel-labs/skills“Target specific agents (e.g., `claude-code`, `codex`)”
  • [github] https://github.com/vercel-labs/skills“npx skills add vercel-labs/agent-skills --skill frontend-design --skill skill-creator”
  • [github] https://github.com/vercel-labs/skills“npx skills add vercel-labs/agent-skills -a claude-code -a opencode”

Built-in AI = 0.0 ÷ 90 × 100 = 0.0

Automation28.0/100×0.15 of the PA blend

Depth of automation primitives — rules, scheduling, bulk operations, webhooks.

Perform bulk operations across many items at onceweight 2

2 (weight) × 6 (quality) × 0.6 (partial) = 7.2 of 20 max

  • [github] https://github.com/vercel-labs/skills“npx skills add vercel-labs/agent-skills --skill frontend-design --skill skill-creator”
  • [github] https://github.com/vercel-labs/skills“npx skills add vercel-labs/agent-skills -a claude-code -a opencode”
  • [github] https://github.com/vercel-labs/skills“Install specific skills by name (use `'*'` for all skills)”
  • [github] https://github.com/vercel-labs/skills“Search across every repository owned by an organization or user”
  • [github] https://github.com/vercel-labs/skills“npx skills find react --owner vercel”
  • [github] https://github.com/vercel-labs/skills“npx skills update frontend-design web-design-guidelines”
  • [github] https://github.com/vercel-labs/skills“npx skills remove --agent claude-code cursor my-skill”
  • [github] https://github.com/vercel-labs/skills“List all installed skills. Similar to `npm ls`.”

Define rules that trigger actions automatically on eventsweight 3

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Schedule recurring jobs or workflowsweight 2

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Version, review, and roll back my automationsweight 1

1 (weight) × 4 (quality) × 0.3 (disputed) = 1.2 of 10 max

  • [claimed-docs] https://raw.githubusercontent.com/vercel-labs/skills/HEAD/AGENTS.md“`skills experimental_install` | Restore skills from skills-lock.json”
  • [claimed-docs] https://raw.githubusercontent.com/vercel-labs/skills/HEAD/AGENTS.md“skills experimental_install | Restore skills from skills-lock.json”
  • [claimed-docs] https://raw.githubusercontent.com/vercel-labs/skills/HEAD/AGENTS.md“skills experimental_install") | Restore skills from skills-lock.json”
  • [github] https://github.com/vercel-labs/skills“Update installed skills to latest versions”
  • [github] https://github.com/vercel-labs/skills“npx skills update # Update a single skill by name npx skills update my-skill”
  • [github] https://github.com/vercel-labs/skills“**Project** | (default) | `./<agent>/skills/` | Committed with your project, shared with team”
  • [community] https://hn.algolia.com/api/v1/items/46697908“Why do none of these 'npm for Skills' document any way to do basic package management things like updates, version-pinning, or even uninstalls?”

Automation = 8.4 ÷ 30 × 100 = 28.0