Agent skills you can check before you install
Public SKILL.md skills from GitHub repositories with 50+ stars and from the vendors themselves, scanned and scored. Install any of them with one command in Claude Code, Cursor, Codex, GitHub Copilot or Gemini CLI.
18,363 skills from 637 repositories · updated 10 minutes ago
3,545 skills
- phx-freezeoliver-kriska/claude-elixir-phoenixApply an advisory scope in this session. Use for read-only or directory-scoped work; no enforcement hook is installed.OtherNo warnings★ 569↓ —
- phx-recalloliver-kriska/claude-elixir-phoenixRecall prior work from past sessions — how a bug was fixed, what was; Use when asked 'have we done this before'…OtherNo warnings★ 569↓ —
- phx-challengeoliver-kriska/claude-elixir-phoenixChallenge mode reviews - rigorous questioning before approving changes. Use when you want thorough scrutiny of Ecto changes, LiveView events, OTP designs, or PR readiness.OtherNo warnings★ 569↓ —
- session-deep-diveoliver-kriska/claude-elixir-phoenixDeep qualitative analysis of high-signal sessions. Spawns subagents with v2 template, synthesizes patterns, compares against known findings. Use after /session-scan.OtherNo warnings★ 569↓ —
- phx-challengeoliver-kriska/claude-elixir-phoenixChallenge mode reviews - rigorous questioning before approving changes. Use when you want thorough scrutiny of Ecto changes, LiveView events, OTP designs, or PR readiness.OtherNo warnings★ 569↓ —
- ln-41-surgical-change-implementerlevnikolaevich/claude-code-skillsImplements one scoped product feature or fix using existing contracts; not upgrades, performance tuning or establishing cross-cutting technical foundations.OtherNo warnings★ 583↓ —
- sentry-release-healthDevin-AXIS/iPolloWorkAssess release health from Sentry errors, regressions, affected users, crash evidence, and comparison with the previous stable release.OtherNo warnings★ 7.2K↓ —
- stripe-reconciliationDevin-AXIS/iPolloWorkReconcile bounded Stripe payment and payout records with supplied business records while preserving object IDs, currency, time zone, and discrepancy evidence.OtherNo warnings★ 7.2K↓ —
- phx-compoundoliver-kriska/claude-elixir-phoenixCapture solved problems as searchable solution docs. Use after fixing bugs, when "that worked", or after successful…OtherNo warnings★ 569↓ —
- phx-documentoliver-kriska/claude-elixir-phoenixDocument tested Elixir APIs; may update README/ADRs. Not for docs lookup, audits/reviews, or standalone decisions.OtherNo warnings★ 569↓ —
- ln-53-documentation-auditorlevnikolaevich/claude-code-skillsAudits documentation and comments for trust, coverage, consistency and freshness; read-only.OtherNo warnings★ 583↓ —
- ln-11-opportunity-evaluatorlevnikolaevich/claude-code-skillsEvaluates new product opportunities through demand, channels and economics before committing to build.OtherNo warnings★ 583↓ —
- compound-docsoliver-kriska/claude-elixir-phoenixSearchable Elixir/Phoenix/Ecto solution documentation system with; Use when consulting past solutions…OtherNo warnings★ 569↓ —
- phx-challengeoliver-kriska/claude-elixir-phoenixChallenge mode reviews - rigorous questioning before approving changes. Use when you want thorough scrutiny of Ecto…OtherNo warnings★ 569↓ —
- intent-detectionoliver-kriska/claude-elixir-phoenixRoute ambiguous or mixed Phoenix/LiveView/Ecto requests; Use when user is unsure where to start/how to approach work…OtherNo warnings★ 569↓ —
- ln-57-persistence-auditorlevnikolaevich/claude-code-skillsAudits queries, transactions, consistency and persistence resource lifetimes; read-only.OtherNo warnings★ 583↓ —
- challengeoliver-kriska/claude-elixir-phoenixChallenge mode reviews - rigorous questioning before approving changes. Use when you want thorough scrutiny of Ecto changes, LiveView events, OTP designs, or PR readiness.OtherNo warnings★ 569↓ —
- ln-72-product-outcome-evaluatorlevnikolaevich/claude-code-skillsEvaluates observed product outcomes against a prior hypothesis; does not run experiments or change user treatment.OtherNo warnings★ 583↓ —
- connect-appsComposioHQ/awesome-claude-skillsConnect Claude to external apps like Gmail, Slack, GitHub. Use this skill when the user wants to send emails, create issues, post messages, or take actions in external services.OtherNo warnings★ 77.7K↓ —
- phx-challengeoliver-kriska/claude-elixir-phoenixChallenge mode reviews - rigorous questioning before approving changes. Use when you want thorough scrutiny of Ecto changes, LiveView events, OTP designs, or PR readiness.OtherNo warnings★ 569↓ —Also in 1 other repo
- news-collectionnotque/vexjoy-agentCollect, filter, and freshness-qualify news items.OtherNo warnings★ 443↓ —
- create-masterxr843/Master-skill基于佛教经典文献，生成特定高僧大德的 AI 教学角色OtherNo warnings★ 470↓ —Also in 1 other repo
- sponsioSponsioLabs/SponsioDeterministic safety solutions for probabilistic AI agentsOtherNo warnings★ 455↓ —
- skillsSponsioLabs/SponsioDeterministic safety solutions for probabilistic AI agentsOtherNo warnings★ 455↓ —
prettier
a5c-ai/babysitter
OtherUpdated Sep 16, 2026
From the author
Prettier configuration and integration.
Install
npx skills add a5c-ai/babysitter --skill prettier -a claude-code
Installs to .claude/skills/prettier/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Download .zip
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
What it can touch
Instructions onlyNo network use seenLicence: MIT
Safety checks on SKILL.md
No warnings.
Why 86
Security100
Provenance79
Maintenance85
Licence100
Adoption52
Files (2)
- README.md
- SKILL.md