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.
48,622 skills from 2,355 repositories · updated 13 hours ago
6,268 skills
- lov-atom-distribution-surfaceslovstudio/skills从同一 Core SDK 与参数 schema 实现 CLI、REST API 和 Agent Skill adapter，并用相同测试向量验证等价结果。触发：“补齐功能分发形态”或 “build CLI API and Agent surfaces”。EngineeringNo warnings★ 72↓ —
- react-native-setupMicrock/ordinary-claude-skillsExpert in React Native environment setup and configuration. Helps with Node.js, Xcode, Android Studio, watchman installation, CocoaPods, simulators, emulators, and troubleshooting setup issues. Activates for environment setup, installation issues, xcode setup, android studio, simulators, emulators, react-native init, expo init, development environment, SDK configuration.EngineeringNo warnings★ 408↓ —
- submittal-reviewdleerdefi/claude-code-constructionExpert PE review of a submittal (shop drawings, product data, samples, equipment brochures) against specs, drawings, code questions and trade coordination. Produces findings with both sources, trade routing and a completeness gate. Triggers: 'review submittal', 'review shop drawings'.EngineeringNo warnings★ 53↓ —
- youth-coding-education-masterswaylq/master-skill青少年编程教育 (Youth Coding Education) Master OS — automated mastery of Youth Coding Education: top builders' mental models, tool stack, current workflows, jargon, and where to keep up. Trigger this skill when the user works on Youth Coding Education problems and wants industry-grade thinking, tool selection, or workflow guidance. 触发词：「少儿编程」「青少年编程」「编程教育」「编程启蒙」「Scratch教学」EngineeringNo warnings★ 174↓ —
- az-cliCode-and-Sorts/awesome-copilot-agentsUse the Azure CLI (`az`) to manage Azure resources from the command line. Trigger this skill whenever the user asks to create, configure, manage, deploy, or interact with any Azure resource — even if they don't explicitly mention "az cli". Also trigger when the user asks about Azure CLI commands, syntax, or wants to know how to do something in Azure from the terminal.EngineeringNo warnings★ 589↓ —
- lov-app-adapterslovstudio/skills定义各语音输入法与剪辑工具的词汇表读写映射：OpenLess、Typeless 等。本地 JSON 直接读写，API 走用户凭据只读探测，未知格式先探测不编造。Trigger: 读/写 OpenLess 词库、同步到 Typeless、适配剪映词库、app vocabulary adapter.EngineeringNo warnings★ 72↓ —
- pr-review-expertborghei/Claude-SkillsSystematic PR review with blast-radius analysis, security scanning, and breaking-change and test-coverage deltas. Use when reviewing PRs that touch shared libraries, APIs, database schemas, auth, or security-sensitive code.EngineeringNo warnings★ 1K↓ —
- convertible-bond-realtime-minute-klineFTShare-Lab/FTShare-skill查询单只或批量可转债当前交易日实时 1 分钟 K 线（GET /api/v4/market/data/convertible-bond-realtime-minute-kline）。用户问可转债实时分钟行情、当下转债分钟走势、多只可转债盘中分钟 K 线时使用。必填 --symbols，按空格分隔，1～20 只。EngineeringNo warnings★ 64↓ —
- agent-activity-audithyperb1iss/sibylAudit recent agent transcripts (Claude Code and Codex) to learn how a tool, system, or skill is actually being used in the wild. Surfaces failure modes, friction, success patterns, and concrete improvement candidates from real session data. Use this when you want to improve a developer-facing system that agents interact with regularly.EngineeringNo warnings★ 68↓ —
- supply-chain-subsubindustry-companiesFTShare-Lab/FTShare-skill查询供应链子子行业公司映射。接口：GET /api/v3/market/data/supply-chain/subsubindustry-companies。所有请求必须设置 FTSHARE_API_KEY。EngineeringNo warnings★ 64↓ —
- session-profilertamdogood/builder-essential-skillsProfile and debug Hermes sessions from their JSONL transcripts. Find a session and its subagents, build a queryable event table, summarize the work as a hierarchical table of contents, break down wall time, inference, tools, tokens, and estimated cost per agent, identify errors and improvement opportunities, and export a shareable Perfetto trace. Use when a user wants to inspect what a Hermes session did, debug agent or subagent activity, understand session cost or latency, create a session timeline, generate a trace, or learn how to improve the next agent run.EngineeringNo warnings★ 227↓ —
- lov-app-optimizerlovstudio/skills用真实运行时证据系统优化交互式应用的卡顿、耗电、内存增长、后台风暴与资源泄漏，覆盖 Electron、Tauri、原生桌面、iOS、Android、React Native、Flutter、Web/PWA；适用于“应用越用越卡”“后台任务和会话不释放”“请做同负载前后验收”，不用于单纯 Lighthouse、后端调优或盲目清理。EngineeringNo warnings★ 72↓ —
- moat_strength_review_skillWind-Alice/AliceMarket评估公司竞争优势的来源、强度、可持续性与削弱风险，判断护城河是否真实存在并能转化为回报。适用于长线票初筛、优质公司研究、竞争壁垒判断等场景。EngineeringNo warnings★ 147↓ —
- quality-refinement-autoloopCheshireJCat/blenderRun a self-refinement loop when a Blender result is subpar, user expectations are not met, validation fails, or repeated issues reveal missing skill depth. The loop diagnoses the gap, decides whether to repair the artifact or acquire/refine a generic skill, sanitizes lessons for reusable publication, updates docs/versioning, validates, and prepares stage/commit/push when explicitly requested.EngineeringNo warnings★ 68↓ —
- serenaDianel555/DSkillsSemantic code understanding with IDE-like symbol operations. Use when: (1) Large codebase analysis (>50 files), (2) Symbol-level operations (find, rename, refactor), (3) Cross-file reference tracking, (4) Project memory and session persistence, (5) Multi-language semantic navigation. Triggers: "find symbol", "rename function", "find references", "symbol overview", "project memory". IMPORTANT: Prioritize Serena's symbolic tools over file-based grep/read for code exploration.EngineeringNo warnings★ 65↓ —
- codex-ccDianel555/DSkillsDelegates coding tasks from Codex to local Claude Code in print mode while preserving Claude's normal runtime customizations by default. Use when: (1) You want Codex to call Claude Code locally, (2) You need Claude-side skills, plugins, MCP servers, custom commands, CLAUDE.md rules, or workspace settings to stay active, (3) You want resumable Claude sessions from Codex via SESSION_ID, (4) You need thin `claude mcp` / `claude plugin` passthrough from the same bridge.EngineeringNo warnings★ 65↓ —
- gtm-setupcognyai/claude-code-marketing-skillsGTM Event Tracking & Setup Reference — dataLayer fundamentals, trigger types, variable types, GA4 tag configuration, debug mode, and best practicesEngineeringNo warnings★ 112↓ —
- proofpointServosity/msp-skillsEvery TAP Threat Insight endpoint, plus a local threat store that answers the cross-endpoint questions - who is both attacked and clicking, what touched this user - inside Proofpoint's punishing daily quotas. Trigger phrases: `pull proofpoint siem events`, `who are my VAPs`, `decode this urldefense link`, `proofpoint incident brief`, `top clickers this month`, `use proofpoint`, `run proofpoint-cli`.EngineeringNo warnings★ 68↓ —
- git-pushingmhattingpete/claude-skills-marketplaceStage, commit, and push git changes with conventional commit messages. Use when user wants to commit and push changes, mentions pushing to remote, or asks to save and push their work. Also activates when user says "push changes", "commit and push", "push this", "push to github", or similar git workflow requests.EngineeringNo warnings★ 689↓ —
- reviewer-routingapache/magpieGiven an open issue or PR, scores the project's configured reviewer roster across three signals — touched-area eligibility, git-history familiarity with the changed paths, and current open-review load — and proposes a primary reviewer (plus an optional backup). Read-only, propose-then-confirm: nothing is assigned, labelled, or requested without confirmation. An unresolved roster yields an explicit NO ELIGIBLE REVIEWER signal, never a fabricated handle.EngineeringReview first★ 133↓ —
- od-pr-reviewckryptickunal/OpenDesignerReview pull requests to the OpenDesigner repo and merge the ones that pass. Checks for malicious code, prompt injection, unrelated or off-goal changes, broken project rules and unverified claims. Use for "review PRs", "check this contribution", "should we mergeEngineeringNo warnings★ 56↓ —
- fortinetServosity/msp-skillsUse when the user asks to audit, inventory or back up client FortiGate firewalls, or read FortiManager or FortiGate Cloud: grades every FortiGate in a devices file for firmware, SSL-VPN exposure, admin accounts and license expiry in one read-only pass, plus HA, tunnel and certificate health, policy hygiene and config changes. Trigger phrases: `audit our fortigates`, `which client firewalls are exposing ssl-vpn`, `which fortigates need a firmware update`, `fortiguard license expiry across clients`, `back up every fortigate config`, `what changed on the firewall`, `list fortimanager managed devices`, `use fortinet`, `run fortinet-cli`.EngineeringNo warnings★ 68↓ —
- shared-config-syncapache/magpieCommit and push the user's shared Claude config to the `~/.claude-config` sync repo, rebasing first so a push never buries work from another machine. Bootstraps the repo when it is missing. Never force-pushes, never rewrites pushed history, never creates a public remote, and touches nothing outside `~/.claude-config/`.EngineeringReview first★ 133↓ —
- using-cap-evolveskillberry-ai/cap-evolveFront door for cap-evolve: routes an optimization request to the right pipeline phase. Use when someone wants an agent, skill, system prompt, tool surface, or MCP toolset to score higher on an eval, benchmark, or task suite — "optimize my skill", "raise the pass rate on these tasks", "my agent keeps failing these cases", "get this prompt's accuracy up on my evals" — even when they never say "optimize", and whenever a .capevolve/ project or an unfinished run is in the tree. Routes to intake, the check gate, a resumed run, or the report; optimizes nothing itself. Not for making code or a query faster, and not for rewording one prompt with no eval to score it against. When the user names a phase or algorithm outright (baseline, gate, hill-climb, gepa), use that skill directly.EngineeringNo warnings★ 67↓ —