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.
46,100 skills from 2,198 repositories · updated 8 hours ago
9,541 skills
- using-superpowersadriannoes/awesome-agentic-aiUse when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questionsOtherNo warnings★ 89↓ —
- verification-before-completionadriannoes/awesome-agentic-aiUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions alwaysOtherNo warnings★ 89↓ —
- contour-integralsparcadei/Continuous-Claude-v3Problem-solving strategies for contour integrals in complex analysisOtherNo warnings★ 3.9K↓ —
- latchkeyUpdatedimbue-ai/latchkeyInteract with third-party or self-hosted services (Slack, Google Workspace, Dropbox, GitHub, Linear, Coolify...) using their HTTP APIs on the user's behalf.OtherNo warnings★ 132↓ —
- swarmadriannoes/awesome-agentic-aiFan out N parallel workers, drain them, and return one report. Use for /swarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration.OtherNo warnings★ 89↓ —
- audit-agent-surfaceJoviDeCroock/prachtInventory what agents can reach in a pracht app — capability exposure (HTTP, WebMCP, remote MCP), `agents` trust config, the destructive-confirmation gate, `llms.txt`, Markdown negotiation, OpenAPI — and report where the surface is wider than intended, or confirm an opt-out app ships none. Use for "audit the agent surface", "what can agents do on my site", "is my MCP endpoint safe", "did this PR widen what agents can reach".OtherNo warnings★ 105↓ —
- aligndevpaleo/alignfirstAct as the AlignFirst assistant: delegate the work on this project to agent sessions through aligndev.OtherNo warnings★ 88↓ —
- boundary-value-problemsparcadei/Continuous-Claude-v3Problem-solving strategies for boundary value problems in odes pdesOtherNo warnings★ 3.9K↓ —
- website-operating-rulesTheGoat395/Codex-SkillsCoordinate cross-phase web execution/evidence.OtherNo warnings★ 135↓ —
- almergepaleo/alignfirstExecute the AlignFirst merge protocol.OtherNo warnings★ 88↓ —
- ask-mattadriannoes/awesome-agentic-aiAsk which skill or flow fits your situation. A router over the user-invoked skills in this repo.OtherNo warnings★ 89↓ —
- pet-friendly-filteringcxcscmu/SkillLearnBenchFiltering accommodations for pet-friendly stays by analyzing house_rules field in accommodation data.OtherNo warnings★ 91↓ —
- visual-assets-directionTheGoat395/Codex-SkillsDefine purposeful visual asset strategy.OtherNo warnings★ 135↓ —
- sigma-algebrasparcadei/Continuous-Claude-v3Problem-solving strategies for sigma algebras in measure theoryOtherNo warnings★ 3.9K↓ —
- motion-language-directorTheGoat395/Codex-SkillsDirect choreography and Viktor-style pacing.OtherNo warnings★ 135↓ —
- section-layout-systemsTheGoat395/Codex-SkillsChoose section forms from content shape.OtherNo warnings★ 135↓ —
- radix-accessible-primitivesTheGoat395/Codex-SkillsRepair Radix parts, portals and focus mechanics.OtherNo warnings★ 135↓ —
- trl-setupcxcscmu/SkillLearnBenchSetup and installation of TRL (Transformer Reinforcement Learning) library with compatible torch/transformers versions. Use when setting up preference optimization training environments.OtherNo warnings★ 91↓ —
- verification-before-completionTheGoat395/Codex-SkillsAssess nontrivial completion evidence.OtherNo warnings★ 135↓ —
- harnessadriannoes/awesome-agentic-ai하네스를 구성합니다. 전문 에이전트를 정의하며, 해당 에이전트가 사용할 스킬을 생성하는 메타 스킬. (1) '하네스 구성해줘', '하네스 구축해줘' 요청 시, (2) '하네스 설계', '하네스 엔지니어링' 요청 시, (3) 새로운 도메인/프로젝트에 대한 하네스 기반 자동화 체계를 구축할 때, (4) 하네스 구성을 재구성하거나 확장할 때, (5) '하네스 점검', '하네스 감사', '하네스 현황', '에이전트/스킬 동기화' 등 기존 하네스 운영/유지보수 요청 시 사용.OtherNo warnings★ 89↓ —
- fuzzy-fund-searchcxcscmu/SkillLearnBenchFuzzy matching techniques for finding hedge funds by name when exact names are unknownOtherNo warnings★ 91↓ —
- residuesparcadei/Continuous-Claude-v3Problem-solving strategies for residues in complex analysisOtherNo warnings★ 3.9K↓ —
- cta-language-systemsTheGoat395/Codex-SkillsMake action labels explain what happens next.OtherNo warnings★ 135↓ —
- geospatial-analysiscxcscmu/SkillLearnBenchAnalyze geospatial data using geopandas with proper coordinate projections. Use when calculating distances between geographic features, performing spatial filtering, or working with plate boundaries and earthquake data.OtherNo warnings★ 91↓ —
simpo-loss
cxcscmu/SkillLearnBench
OtherUpdated Oct 2, 2026
From the author
SimPO (Simple Preference Optimization) loss computation for LLM alignment without a reference model.
Install
npx skills add cxcscmu/SkillLearnBench --skill simpo-loss -a claude-code
Installs to .claude/skills/simpo-loss/ · 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 83
Security100
Provenance64
Maintenance100
Licence100
Adoption34
Files (1)
- SKILL.md