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.
45,604 skills from 2,205 repositories · updated 12 hours ago
5,657 skills
- model-inference-optimizemajiayu000/spellbook优化实际模型推理链路,将正确性对齐、分段 profiling、显存与数据搬运、TensorRT/ONNX/PyTorch 后端、attention/kernel、FP8/compile、缓存与少步采样、质量回归、GPU 成本和服务验收串成同一实验闭环。当用户要求推理提速、降低显存或 GPU 成本、复现模型效果、定位 GPU 利用率低、优化图像/视频/扩散模型或自托管 LLM 时使用,提供 model inference performance optimization 的脱敏案例。纯 API 调用、提示词或 token 用量优化,以及电脑卡顿,不进入本技能的模型推理实验流程。EngineeringNo warnings★ 288↓ —
- python-uvMindrally/skillsGuidelines for Python dependency management using uv, the fast Python package installer and resolver.EngineeringNo warnings★ 286↓ —
- react-hooks-best-practicesmajiayu000/spellbookProvides React patterns for hooks, effects, refs, and component design. Covers escape hatches, anti-patterns, and correct effect usage. Use when reading or writing React components with hooks or effects.EngineeringNo warnings★ 288↓ —
- pr-reviewMindrally/skillsFocused pull request review practices with severity-ranked, file-and-line-cited findings across four angles: security, performance, tests, and architecture. Use when asked to review a pull request, review a diff or set of changes, review "this PR," or provide a code review before merge.EngineeringNo warnings★ 286↓ —
- stata-runbrycewang-stanford/Auto-Empirical-Research-SkillsRun arbitrary Stata code or a .do file and display the result.EngineeringNo warnings★ 4.8K↓ —
- plugin-statusjmagly/aiwgList installed Claude Code marketplace plugins with version, install date, and enabled statusEngineeringNo warnings★ 225↓ —
- tech-debtsecondsky/claude-skillsUse when reworking a change to prevent tech debt, or auditing existing debt to categorize, score, and prioritize the refactor backlog.EngineeringNo warnings★ 236↓ —
- turboreposecondsky/claude-skills| Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. Use when user: configures tasks/workflows/pipelines, creates packages, sets up monorepo, shares code between apps, runs changed/affected packages, debugs cache, or has apps/packages directories.EngineeringNo warnings★ 236↓ —
- exam-reviewZeKaiNie/universal-examprep-skill考前复盘已记录错题与概念疑难:重做原题、复述疑难、更新已订正/已回顾/待回顾状态,并形成最后扫雷清单。 进入最终复习阶段或用户要求复盘、查漏补缺时使用。EngineeringNo warnings★ 318↓ —
- review-chamberathola/claude-night-marketCaptures and retrieves PR-review findings in memory palaces. Use after PR review to store architectural decisions, patterns, and standards for future reference.EngineeringNo warnings★ 343↓ —
- three-jsMindrally/skillsExpert guidance for Three.js and React Three Fiber development with modern React, TypeScript, and performance best practicesEngineeringNo warnings★ 286↓ —
- bun-runtimesecondsky/claude-skillsUse for Bun runtime, bunfig.toml, watch/hot modes, env vars, CLI flags, and module resolution.EngineeringNo warnings★ 236↓ —
- code-reviewsecondsky/claude-skillsCode review practices with technical rigor and verification gates. Use for receiving feedback, requesting code-reviewer subagent reviews, or preventing false completion claims in pull requests.EngineeringNo warnings★ 236↓ —
- gravitas-pythonudaysharmadev/GravitasGRAVITAS extension for Python projects. Adds Python-specific recon, type checking with mypy/pyright, ruff/flake8 lint, pytest patterns, and common Python failure modes. Load in addition to the base GRAVITAS skill.EngineeringNo warnings★ 344↓ —
- pr-review-analysisbreaking-brake/cc-wf-studioAnalyze PR review comments from a GitHub PR URL. Fetch review comments, verify each finding against the actual codebase, assess validity (correct/incorrect/partial), present a structured summary with recommended actions, and optionally reply to each comment on GitHub. Use when given a PR review URL or when asked to check/analyze PR feedback.EngineeringNo warnings★ 5.4K↓ —
- ccwf-clibreaking-brake/cc-wf-studioUse the `ccwf` CLI (from @cc-wf-studio/cli) to render, validate, preview, export, or run cc-wf-studio workflow JSON files from the terminal. Apply whenever the user mentions viewing, visualizing, checking, executing, or converting a workflow under `.vscode/workflows/` (or any `*workflow*.json`), wants a Mermaid diagram of a workflow, asks to "see" / "preview" / "open" a workflow, or wants to run a workflow as a Claude Code Skill without opening VSCode.EngineeringNo warnings★ 5.4K↓ —
- pr-to-mainbreaking-brake/cc-wf-studioCreate a PR to the main branch for feature/fix changes in this pnpm + Changesets monorepo. Use when the user says "PRを作成", "mainにPR", or wants to submit changes for review. Always run this in the monorepo-aware way — identify the affected package(s) and make sure a changeset exists, because the release pipeline is Changesets-driven.EngineeringNo warnings★ 5.4K↓ —
- cleanup-auditjmagly/aiwgAudit codebase for dead code, unused exports, orphaned files, and stale manifestsEngineeringNo warnings★ 225↓ —
- oauth-implementationsecondsky/claude-skillsOAuth 2.0 and OpenID Connect authentication with secure flows. Use for third-party integrations, SSO systems, token-based API access, or encountering authorization code flow, PKCE, token refresh, scope management errors.EngineeringNo warnings★ 236↓ —
- monorepoMindrally/skillsBest practices for monorepo development with TypeScript, React, Next.js, Expo, Turbo, and related technologiesEngineeringNo warnings★ 286↓ —
- typeormMindrally/skillsGuidelines for developing with TypeORM, a full-featured ORM for TypeScript and JavaScript supporting multiple databasesEngineeringNo warnings★ 286↓ —
- bun-react-ssrsecondsky/claude-skillsUse when building server-rendered React with Bun, including streaming SSR, hydration, renderToString, or custom SSR without a framework.EngineeringNo warnings★ 236↓ —
- hz-perfetto-debugmeta-quest/agentic-toolsAnalyzes Meta VR and Horizon OS VR performance using Perfetto traces — frame timing, CPU/GPU bottlenecks, render pass analysis. Use when profiling frame drops, jank, or thermal issues on Meta VR devices. Build paths: all Meta VR app stacks; use hz-quest-verify-first if the build path is unclear.EngineeringNo warnings★ 236↓ —
- kiln-batch-dispatchinstruktlabs/kilnRun requested Kiln asset batches or compare coding-agent harnesses and models in isolated workspaces. Use for repeatable trials, source-reference workflow checks, and distinguishing provider, tool, and asset-quality failures.EngineeringNo warnings★ 294↓ —