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.
46,700 skills from 2,243 repositories · updated 12 hours ago
10,031 skills
- search-toolsparcadei/Continuous-Claude-v3Search Tool HierarchyOtherNo warnings★ 3.9K↓ —Also in 1 other repo
- pint-computeparcadei/Continuous-Claude-v3Unit-aware computation with Pint - convert units, dimensional analysis, unit arithmeticOtherNo warnings★ 3.9K↓ —Also in 1 other repo
- morph-searchparcadei/Continuous-Claude-v3Fast codebase search via WarpGrep (20x faster than grep)OtherNo warnings★ 3.9K↓ —Also in 1 other repo
- run3_skill-1cxcscmu/SkillLearnBench[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.OtherNo warnings★ 91↓ —
- mathparcadei/Continuous-Claude-v3Unified math capabilities - computation, solving, and explanation. I route to the right tool.OtherNo warnings★ 3.9K↓ —Also in 2 other repos
- evidence-first-engineeringNocodeMrLi/mini-program-engineering-skill-suiteApply evidence-first engineering discipline to any agent-built software project: fact discovery before action, evidence-calibrated status reporting, explicit change boundaries and stage gates, controlled confirmation for risky or external actions, sensitive-information redaction for anything shared publicly, and resumable continuity after interruptions. Use when users ask an agent to take over an existing codebase, deliver a feature across stages, verify whether work is actually complete, judge release readiness, or keep conclusions honest about what is proven versus assumed. This foundation skill is domain-neutral; vertical suites (for example mini-program engineering) build on it by adding domain facts and platform rules.OtherNo warnings★ 92↓ —
- directory-build-organizationdotnet/skillsUSE ONLY for (1) two or more projects with repeated MSBuild policy, targets, or package versions, or (2) an existing Directory.Build.props/targets/rsp hierarchy with an import, placement, or layering defect. A one-project repo without an existing Directory.Build file is outside scope; do not load this skill. Covers centralizing shared policy and targets, Directory.Packages.props across projects, parent hierarchy/import structure, props-versus-targets placement, and folder/project exceptions. An existing hierarchy defect remains in scope when only one project is affected. For property value or condition semantics use property-patterns. Exclude legacy-to-SDK migration and non-MSBuild systems.OtherReview first★ 5.7K↓ —
- premortemparcadei/Continuous-Claude-v3Identify failure modes before they occur using structured risk analysisOtherNo warnings★ 3.9K↓ —Also in 1 other repo
- math-helpparcadei/Continuous-Claude-v3Guide to the math cognitive stack - what tools exist and when to use eachOtherNo warnings★ 3.9K↓ —Also in 1 other repo
- genre-strategy-simarjun988/blender-skillsArt direction for strategy, RTS, turn-based strategy, tower defense, MOBA, city builder, colony sim, and simulation games in Blender.OtherNo warnings★ 1.1K↓ —Also in 1 other repo
- onboardparcadei/Continuous-Claude-v3Analyze brownfield codebase and create initial continuity ledgerOtherNo warnings★ 3.9K↓ —Also in 1 other repo
- wiringparcadei/Continuous-Claude-v3Wiring VerificationOtherNo warnings★ 3.9K↓ —Also in 1 other repo
- passkeys-webauthn-identity-expertNewroedyrustam/vibes-plugFIDO2 / WebAuthn Passkeys, SimpleWebAuthn, and passwordless auth / Autentikasi tanpa kata sandi Passkeys FIDO2 dan SimpleWebAuthn.OtherNo warnings★ 115↓ —
- testany-caseTestAny-io/testany-agent-skillsTestany platform case 注册与 CRUD - 将已准备好的 platform case package 注册到平台，并管理 metadata、脚本与生命周期OtherNo warnings★ 82↓ —
- sse-websocket-streaming-expertroedyrustam/vibes-plugReal-time Server-Sent Events (SSE), WebSockets, and data streaming / Server-Sent Events (SSE), WebSockets, dan streaming data real-time.OtherNo warnings★ 115↓ —
- mint-unittonone-ai/tononeAudit and improve unit economics — LTV, CAC, payback period, gross margin, contribution margin. Use when asked to "are our unit economics good", "what is our LTV/CAC", or "how do we improve gross margin".OtherNo warnings★ 76↓ —
- axe-recontonone-ai/tononeSurvey a codebase for accessibility debt — missing ARIA, broken keyboard patterns, and contrast issues. Use when asked "how accessible is our codebase", "find accessibility debt", or "where are our a11y gaps".OtherNo warnings★ 76↓ —
- copy-recontonone-ai/tononeSurvey all user-facing strings in a codebase — map coverage and find gaps. Use when asked "what user-facing strings do we have", "map our copy coverage", or "find hardcoded strings".OtherNo warnings★ 76↓ —
- cm-runtimekingxiaozhe/cm-workflow用户要查看或切换 CM 自动派发偏好、单/双 AI 声明、谁写谁审，或修改用户级运行时默认时使用。只管理运行时声明，不安装工具、不测试配额、不接管正在运行的任务。OtherNo warnings★ 97↓ —
- fixing-promptGulajavaMinistudio/awesome-copilot-idPrompt: Prompt Refinement and OptimizationOtherNo warnings★ 90↓ —
- spine-perftonone-ai/tononeFind and fix performance bottlenecks — N+1 queries, missing indexes, sync bottlenecks, caching gaps. Use when asked "why is this slow", "performance issue", "optimize this endpoint", or "N+1 queries".OtherNo warnings★ 76↓ —
- deal-recontonone-ai/tononeRevenue reconnaissance — audit current sales pipeline, deal patterns, ICP definition, and revenue motion to understand what's working and where the constraint is. Use when asked to "audit our sales", "where is revenue stuck", "what's our pipeline state", "before designing a playbook".OtherNo warnings★ 76↓ —
- copy-to-output-directorydotnet/skillsChoosing an MSBuild CopyToOutputDirectory / CopyToPublishDirectory mode: Never, PreserveNewest, Always, and IfDifferent (MSBuild 17.13+), plus $(SkipUnchangedFilesOnCopyAlways). USE FOR: removing the per-build Always copy perf hit; resetting output files mutated between builds. DO NOT USE FOR: general incremental-build diagnosis (use incremental-build); non-MSBuild build systems.OtherReview first★ 5.7K↓ —
- authentication-identity-expertroedyrustam/vibes-plugAuthentication, authorization (RBAC/ABAC), OAuth2, Clerk, and Auth.js / Autentikasi, otorisasi (RBAC/ABAC), OAuth2, Clerk, dan Auth.js.OtherNo warnings★ 115↓ —
glm-runner
cxcscmu/SkillLearnBench
OtherUpdated Oct 2, 2026
From the author
A skill to execute the GLM binary and manage its simulation output.
Install
npx skills add cxcscmu/SkillLearnBench --skill glm-runner -a claude-code
Installs to .claude/skills/glm-runner/ · 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