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.
10,471 skills from 307 repositories · updated 21 minutes ago
927 skills
- svg-optimizera5c-ai/babysitterOptimize SVG assets, generate sprites, and convert to React componentsEngineeringNo warnings★ 1.9K↓ —
- typescripta5c-ai/babysitterTypeScript configuration, strict mode, generics, and type utilities.EngineeringNo warnings★ 1.9K↓ —
- react-hooksa5c-ai/babysitterDeep expertise in React hooks patterns including custom hooks, composition, optimization, and testing strategies.EngineeringNo warnings★ 1.9K↓ —
- react-querya5c-ai/babysitterTanStack Query (React Query) patterns for server state management, caching, mutations, optimistic updates, and infinite queries.EngineeringNo warnings★ 1.9K↓ —
- rtl-lintinga5c-ai/babysitterRTL code quality checking and linting. Runs lint rules, identifies synthesis issues, detects inferred latches, and generates lint reports with waivers.EngineeringNo warnings★ 1.9K↓ —
- cuda-toolkita5c-ai/babysitterDeep integration with NVIDIA CUDA toolkit for kernel development, compilation, and debugging. Execute nvcc compilation with optimization flags analysis, generate and validate CUDA kernel code, analyze PTX/SASS assembly output, and configure execution parameters.EngineeringNo warnings★ 1.9K↓ —
- checkpoint-managementa5c-ai/babysitterGit-backed state management for safe rollback. Create and restore checkpoints with tagged commits and metadata tracking.EngineeringNo warnings★ 1.9K↓ —
- using-git-worktreesa5c-ai/babysitterBabysitter enforces obedience on agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic, hallucination-free self-orchestrationEngineeringNo warnings★ 1.9K↓ —
- orchestrated-executiona5c-ai/babysitterExecute work units through the rigorous 4-phase Metaswarm cycle (Implement -> Validate -> Adversarial Review -> Commit) with independent quality gate enforcement.EngineeringNo warnings★ 1.9K↓ —
- systematic-debugginga5c-ai/babysitterBabysitter enforces obedience on agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic, hallucination-free self-orchestrationEngineeringNo warnings★ 1.9K↓ —
- story-reviewzenstory-ai/oh-story-claudecode多视角对抗式审查。full/lean 模式在已部署 reviewer agents 时并行 spawn；缺失/异常 agents 或 spawn 失败时自动降级 solo，参考文件不可读时使用内置 rubric fallback。触发方式：/story-review、/审查、「审查一下」「帮我审一下」。EngineeringNo warnings★ 7.8K↓ —
- context7-version-aware-implementationDevin-AXIS/iPolloWorkUse the current project dependency versions and Context7 documentation to implement or upgrade code without importing APIs from a different release line.EngineeringNo warnings★ 7.1K↓ —
- get-env-varDevin-AXIS/iPolloWorkget an env var, fetch a secret, missing env var, missing token/API key, load secrets from Infisical, infisical. Fetch secrets from the team's Infisical workspace into the shell environment so subsequent commands can use them.EngineeringNo warnings★ 7.1K↓ —
- systematic-debuggingmvschwarz/openrigUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesEngineeringNo warnings★ 8K↓ —Also in 1 other repo
- openrig-upgrademvschwarz/openrigUse when an agent is preparing or performing an OpenRig CLI/daemon upgrade and must preserve live seats, verify each mutation, or reconcile managed plugin and skill files without overwriting local work.EngineeringNo warnings★ 8K↓ —Also in 1 other repo
- claude-compaction-restoremvschwarz/openrigUse when a Claude Code session is about to compact, has just compacted, reached its context limit, resumed after /compact, or must rebuild its working picture of a long-running seat from its own restore map, its JSONL transcript and the files it touched.EngineeringNo warnings★ 8K↓ —
- labelu-data-annotationDevin-AXIS/iPolloWorkUse host MCP extension actions to create, inspect, annotate, review and export local multimodal projects.EngineeringNo warnings★ 7.1K↓ —
- douyin-ops-workerDevin-AXIS/iPolloWork用户说“发布抖音”“发到抖音”或生成视频后发布时优先使用。先复用插件已有登录账号，保存草稿、创建发布任务，再走 API 或插件账号浏览器，所有结果和验证码阻塞都回写运营台。也用于抖音搜索、数据、评论和账号登录。EngineeringNo warnings★ 7.1K↓ —
- remote-api-footgunsmaxrave-dev/kotlin-footgunsRemote API traps in Kotlin Multiplatform: Ktor clients, defensive parsing, Resource envelopes, OK responses that dropped your data, auth callbacks, retry backoff, downloads, websockets, clock sync. Use when calls succeed but data never lands.EngineeringNo warnings★ 1.5K↓ —
- desktop-and-build-footgunsmaxrave-dev/kotlin-footgunsDesktop JVM and build traps: JNA natives, bundling, memory, packaging, code signing, R8, deep links, Gradle and CI releases. Use when a desktop build fails packaged, signed, on another OS or arch, or in CI.EngineeringNo warnings★ 1.5K↓ —
- python-econ-computingbrycewang-stanford/Auto-Empirical-Research-SkillsUse when writing Python code for DSGE models, HANK models, numerical economic computation, causal inference, or quantitative economic data analysisEngineeringNo warnings★ 4.7K↓ —
- stata-runbrycewang-stanford/Auto-Empirical-Research-SkillsRun arbitrary Stata code or a .do file and display the result.EngineeringNo warnings★ 4.7K↓ —
- literature-reviewaipoch/open-scienceFind, verify, and synthesize scientific literature — from "what's the seminal paper for X" through full multi-source reviews. Covers grounding claims in real retrieved sources, avoiding fabricated citations, handling retractions, and calibrating confidence to evidence strength.EngineeringNo warnings★ 5.3K↓ —
- 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↓ —