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.
45,198 skills from 2,196 repositories · updated 18 minutes ago
5,577 skills
- build-plugintechwolf-ai/ai-first-toolkitBundle skills, hooks, agents, or an MCP server into one installable Claude Code plugin and ship it. Use when asked to bundle tools into one plugin, package tools for a colleague, publish a plugin to a marketplace, share my tools with my team, or ship a plugin. Asks who it's for and where it's hosted, then walks analyze, assemble, ship, and maintain, tailored to that answer. Sibling to build-mcp.EngineeringNo warnings★ 138↓ —
- systematic-debuggingsandbaseai/sandbase-skillsPlan, implement, or review systematic debugging work in an existing codebase with compatibility, security, and verification controls. Use when the user explicitly requests systematic debugging work.EngineeringNo warnings★ 203↓ —
- surgical-changesDevelopersGlobal/ai-agent-skillsEnforces minimal code modifications — touch only what you must. Prevents drive-by refactoring, comment deletions, and style changes unrelated to the task.EngineeringNo warnings★ 216↓ —
- ci-failuresGoldziher/ai-rulezSummarizes failing CI jobs for a pull request. Use when asked why a PR build is red.EngineeringNo warnings★ 163↓ —
- ESLint Code Reviewskillmds/skillmdLint, search, and install Agent Skills (SKILL.md) — CLI + MCP server + lint engineEngineeringNo warnings★ 190↓ —
- comment-checkerwjgoarxiv/litgravityAudit code comments in a diff or named files: keep intent and reasons, remove stale narration, fix misleading text.EngineeringNo warnings★ 166↓ —
- travel-expense-auditvixues/LeAgentAudit travel / 差旅报销 claims against uploaded policy handbooks and rate tables (lodging caps, transport, per diem). Use for 差旅费审核, travel expense review, or lodging over-limit checks.EngineeringNo warnings★ 238↓ —
- fake-screencasthassancs91/claude-youtube-editorRecord the talking head, Claude Code does the rest: the cut, the visuals, the voice, the sound effects, the thumbnail, and the YouTube upload. Every screen moment is built as Remotion TSX code, never screen-recorded.EngineeringNo warnings★ 348↓ —
- source-codingparcadei/Continuous-Claude-v3Problem-solving strategies for source coding in information theoryEngineeringNo warnings★ 3.9K↓ —
- v8unpack-cfDesko77/claude-code-skills-1cРаспаковка и сборка бинарных файлов 1С (CF/CFE/EPF) через Python-утилиту v8unpack. Используй когда нужно распаковать конфигурацию, расширение или обработку в исходники, или собрать обратно.EngineeringNo warnings★ 85↓ —
- account-structure-reviewirinabuht12-oss/marketing-skillsClaude skills for marketing: 49 free marketing skills for Claude Code and claude.ai (Google Ads, Meta Ads, SEO, AI visibility) + the Ryze Google Ads MCP / Meta Ads MCP: claude mcp add ryze --transport http https://connector.get-ryze.ai/mcpEngineeringNo warnings★ 5.8K↓ —
- agentica-claude-proxyparcadei/Continuous-Claude-v3Guide for integrating Agentica SDK with Claude Code CLI proxyEngineeringNo warnings★ 3.9K↓ —Also in 1 other repo
- mini-program-debugging-skillNocodeMrLi/mini-program-engineering-skill-suiteDiagnose and fix mini-program failures through reproducible, evidence-driven root-cause analysis across source, state, asynchronous timing, caches, mock data, build versions, platform behavior, devices, cloud calls, and external services. Use when users report white screens, crashes, stale or jumping values, missing data, intermittent behavior, permission failures, performance stalls, device-only defects, API or cloud-function errors, source-versus-build mismatches, or regressions whose cause is not yet established. Freezes the observation environment, ranks competing hypotheses, runs discriminating checks, creates a failing regression test before repair, covers analogous states, and never hides a known failure with longer waits, swallowed errors, forced success, or cosmetic patches.EngineeringNo warnings★ 91↓ —
- lmstudio-apiDesko77/claude-code-skills-1cСправочник по HTTP-API LM Studio (сервер локальных моделей, обычно порт 1234). Используй когда надо программно управлять моделями на LM Studio - узнать что загружено, загрузить или выгрузить модель, задать длину контекста и параллельность, отключить размышления модели, - а также при диагностике: модель thinking/reasoning не отключается, enable_thinking игнорируется, ответ приходит пустым а весь бюджет уходит в reasoning_content, запросы падают с HTTP 500 на холодном старте или при загрузке крупной модели, ошибка Context size has been exceeded, Model is unloaded, эндпоинт отвечает 404 или 200 с телом Unexpected endpoint, неверно определяется длина контекста. Содержит проверенные схемы эндпоинтов v1, параметр reasoning, особенности протокола и замеры на 30-35B.EngineeringNo warnings★ 85↓ —
- msbuild-antipatternsdotnet/skillsDO NOT INVOKE when the primary request explicitly asks to convert, migrate, modernize, or rewrite a legacy/old-style project to SDK style; use msbuild-modernization. Migration prompts often mention ToolsVersion, explicit Compile/Reference entries, packages.config, or Microsoft.CSharp.targets, but merely reviewing or auditing a file that contains those patterns remains in scope here. USE FOR broad review, audit, lint, or maintainability/correctness checks of project/build files, including custom targets; prioritized cross-cutting findings; discrete anti-patterns; F# ordering/FS0039; cross-platform paths; and focused Import safety verdicts. Review/audit is analysis-only unless fixes are requested. For concrete property/item defects use property-patterns/item-management; use target-authoring for implementation and extension-points for NuGet auto-import/layout discovery. Exclude non-MSBuild systems.EngineeringReview first★ 5.7K↓ —
- 1c-platform-docsDesko77/claude-code-skills-1c1C platform API documentation tools via bsl-platform-help MCP server - search, info, members, constructors. Supports keyword, semantic (embeddings), and hybrid search. Use when checking built-in functions, types, methods, or properties of the 1C platform.EngineeringNo warnings★ 85↓ —
- self-improving-agentjdrhyne/agent-skillsCaptures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.EngineeringNo warnings★ 240↓ —
- eval-codeCalibre-Labs/reforge-ai-evalsWrite deterministic, code-based evaluator functions for an AI product. Use this skill whenever you need to write evaluators that check structural properties of AI outputs (format, count, presence, schema compliance) without calling another LLM. Also use when auditing existing code-based evaluators for brittleness, coverage gaps, or false positives.EngineeringNo warnings★ 86↓ —
- bmad-walkthroughalvin-reyes/better-agentic-ideGuide a human review of a commit, PR, file, or directory. Use when invoked by nameEngineeringNo warnings★ 85↓ —Also in 1 other repo
- bmad-agent-devalvin-reyes/better-agentic-ideSenior software engineer who implements stories and code changes. Use when the user asks to talk to Amelia or requests the developer agentEngineeringNo warnings★ 85↓ —Also in 1 other repo
- mcd-gitzhutoumeme/mcd-git用本地命令行 mcd-git（git mcd --json）帮用户点麦当劳：选门店、看菜单、加购物车（去酸黄瓜、少冰、套餐换搭）、自动凑套餐挑最省的券、核价、下单拿支付链接、查取餐码、再来一单、取消订单、领券（pull，先确认），以及生成 1024 吃麦贡献图（card）。用户提到点麦当劳、麦当劳到店 / 得来速 / 麦乐送、取餐码、再来一单、取消麦当劳订单、领麦当劳的券、吃麦贡献图时使用。下单、取消和领券都必须先把确认摘要给用户看，用户明确同意后才能带 --confirm 执行。EngineeringNo warnings★ 85↓ —
- react-accessible-componentsTheGoat395/Codex-SkillsImplement semantic names, keyboard and focus.EngineeringNo warnings★ 133↓ —
- trace-codesCalibre-Labs/reforge-ai-evalsTurn free-form notes from reading agent traces into trace codes: named, yes/no failure or quality patterns with definitions, examples and counts. Use this skill whenever someone has annotated traces or review notes and asks to "cluster my notes", "create trace codes", "find the failure modes", "do error analysis on these annotations", "what patterns are in these traces", or "what should we fix first". Also use to merge new notes into an existing set of codes. Output is a trace codes file, a labeling sheet for human review, and proposed rubric updates.EngineeringNo warnings★ 86↓ —
- bmad-code-reviewalvin-reyes/better-agentic-ideReview code changes with several independent reviewers in parallel, then triage and present the findings. Use when the user says "run code review" or "review this code"EngineeringNo warnings★ 85↓ —Also in 1 other repo