Skill-uri pentru agenți pe care le poți verifica înainte să le instalezi
Skill-uri SKILL.md publice din depozite GitHub cu peste 50 de stele și de la producători, scanate și evaluate. Instalează oricare dintre ele cu o singură comandă în Claude Code, Cursor, Codex, GitHub Copilot sau Gemini CLI.
48.168 de skill-uri din 2.325 de depozite · actualizat acum 14 ore
6.080 de skill-uri
- mcptoonactiveing123/mcptoonCompress MCP tool discovery with the mcptoon CLI. Trigger when a session has a large MCP tool catalog (many servers/tools), when the user mentions token cost, tool discovery, mcptoon, or asks to list/call MCP tools efficiently. Also route here when the user says the MCP tool list is too large, the agent context window is filling up with tool schemas, or they need the same MCP servers configured across Claude Code, Cursor, Codex, Cline, Windsurf and other agents. Also covers managing an agent's skill catalog with `mcptoon skills` (list / resolve / sync / doctor / add / remove, plus a version gate, a read-only health check, derived Roo/OpenCode views, tombstoned removals, and a gate that refuses to prune a view from an undecided removal). Also route here when a doc folder is too big to read — 文档太多、AGENTS.md / CONTEXT.md / docs/ 太大、不知道该读哪个文件、想省 token 读文档、整读一个目录太贵: `mcptoon docs index <dir>` then `mcptoon docs resolve "<question>"` returns the few files worth opening — read one chapter, not all — offline, no LLM,InginerieVerifică întâi★ 410↓ —Apare și în 2 alte depozite
- llama-cppmagnus919/agent-skillsOperate, configure, benchmark, and troubleshoot llama.cpp across CPU, Metal, CUDA, HIP/ROCm, Vulkan, SYCL, and hybrid or multi-GPU systems. Use when installing or building llama.cpp, selecting or inspecting GGUF models, running llama-cli or bounded llama-completion, serving an OpenAI-compatible API with llama-server, tuning memory and performance, or diagnosing backend, context, template, and API failures. Do not use for model training or fine-tuning, general inference-framework selection, llama-cpp-python or other bindings, LlamaIndex, Ollama, or LM Studio operation.InginerieFără avertismente★ 162↓ —
- printifywin4r/MuseAI-SkillsUse Printify to browse catalog data, manage shops and products, and review or create orders.InginerieFără avertismente★ 406↓ —
- serial-debugAdancurusul/serial-mcp-serverCLI-first serial port debugging and macro automation with serial-mcp-server for Codex and Claude Code. Use when working with UART or USB-serial devices, listing serial ports, probing STM32/Arduino/ESP32 boards, writing or reading serial data, running JSON serial macros, controlling RTS/DTR, or using serial-mcp-server through MCP tools.InginerieFără avertismente★ 95↓ —
- receiving-critical-reviewK-Dense-AI/science-superpowersUse when receiving critical feedback on an analysis or manuscript, before implementing suggestions, especially if feedback seems unclear or methodologically questionable - requires verification, not performative agreement or blind changesInginerieFără avertismente★ 364↓ —
- reticleActualizatreticlehq/reticleAI agents can generate code, but still struggle to understand what they build. Reticle brings Jev-style machine-native runtime perception to web & desktop applications.InginerieVerifică întâi★ 1,3 K↓ —
- vendor-queryGoldziher/ai-rulezQuery the Vendor API for account usage.InginerieFără avertismente★ 166↓ —
- autopromptSpielewoy/autoprompt-skillRun explicitly requested Autoprompt v2 work through the private controller. Ordinary coding and review requests do not activate this skill.InginerieVerifică întâi★ 1,2 K↓ —
- autopromptSpielewoy/autoprompt-skillRun explicitly requested Autoprompt v2 work through the private controller. Ordinary coding and review requests do not activate this skill.InginerieVerifică întâi★ 1,2 K↓ —
- receiving-code-reviewjamditis/claude-skills-journalismVerifies review feedback with technical rigor, not blind agreement. Use when receiving review before implementing suggestions.InginerieVerifică întâi★ 443↓ —
- releaseoliver-kriska/claude-elixir-phoenixCONTRIBUTOR TOOL - Cut a plugin release: bump plugin.json version, finalize CHANGELOG, update README if needed, gate on make ci, commit, tag vX.Y.Z, and create the GitHub release. Use when shipping a new plugin version. NOT distributed.InginerieVerifică întâi★ 572↓ —
- browse-xpc-style/x-mdReads public X (formerly Twitter) posts, threads, X Articles, profiles, followers, following, and search results as Markdown or JSON, with no X account and no API key. Use when a URL points at x.com, twitter.com, or t.co; when the user mentions a tweet, an X post, a thread, or an X profile; when you need an account's recent posts or connections; or when you need X search results as structured data. Read-only: it never posts, replies, follows, or reads protected accounts, direct messages, or Lists.InginerieFără avertismente★ 186↓ —
- activate-sitemicrosoft/power-platform-skillsActivates and provisions a Power Pages website in a Power Platform environment via the Power Platform REST API. Use when the user wants to activate, provision, turn on, or enable a Power Pages website or portal.InginerieVerifică întâi★ 1,1 K↓ —
- agent-councilmagnus919/agent-skillsRun a structured multi-agent debate by spawning a panel of expert agents on any question, with convergence-aware iteration and typed synthesis output via the `agent-council` CLI. Use when a decision has genuine tradeoffs, high stakes, or hidden assumptions worth adversarial collaboration, or when confidence diagnostics matter more than a single recommendation. Compatible with any AI agent harness that supports agentskills.io skills (Claude Code, Cursor, Hermes Agent, OpenHands, etc.). Do not use for simple factual lookups, tasks with a clear correct answer, routine single-perspective work, or code execution and tool orchestration beyond debate.InginerieFără avertismente★ 162↓ —
- scan-codemicrosoft/power-platform-skillsScans a Power Pages site project for security issues in source code and dependencies. Runs static analysis and dependency scanning, then surfaces findings by category (code patterns, vulnerable packages, secrets, license issues). Use when the user wants to review code for security problems, check for vulnerable packages, find hard-coded secrets, run a code scan, or asks "is my code safe?", "check my dependencies", "find security issues in my source" — even if they say "audit my code" without mentioning specific tools.InginerieVerifică întâi★ 1,1 K↓ —
- autopromptSpielewoy/autoprompt-skillRun explicitly requested Autoprompt v2 work through the private controller. Ordinary coding and review requests do not activate this skill.InginerieVerifică întâi★ 1,2 K↓ —
- open-agent-teamsAI-Builder-Club/skillsDelegate tasks to ANY CLI agent (claude, codex, aider, ...) running in a detached tmux session, with a race-safe done-signal protocol and multi-turn iteration. Use when delegating work to a non-Claude CLI agent, when the user says "tmux delegate", "run agent in tmux", "delegate to codex/aider", or when executor work should run in an observable background terminal instead of the Agent tool.InginerieFără avertismente★ 1,3 K↓ —
- building-github-index-v2oaustegard/claude-skillsDEPRECATED - Use building-github-index instead. Superseded per-file GitHub API implementation of progressive disclosure repository indexes.InginerieFără avertismente★ 157↓ —
- acme-statusGoldziher/ai-rulezCheck whether the Acme API is up.InginerieFără avertismente★ 166↓ —
- bluebubblesComeOnOliver/skillshub🧠 The right skill, one API call. AI agent skills registry with token-efficient skill resolution. 5,000+ skills from 500+ top repos.InginerieFără avertismente★ 64↓ —
- safe-debuglllllllama/RigorPilot-SkillsRigor Debug / Rigor Audit skill for deep learning research work. Use when the user pastes a traceback, terminal error, CUDA OOM, checkpoint load failure, shape mismatch, NaN loss symptom, or training failure and wants conservative diagnosis before any patching, with debug fixes clearly separated from research contributions. Do not use for broad refactoring, speculative adaptation, automatic exploratory patching, or general repository familiarization.InginerieFără avertismente★ 487↓ —
- deciding-with-confidenceoaustegard/claude-skillsRoutes, triages, flags and rates a piece of text with a probability for every option: which department or queue a ticket goes to, which intent a message expresses, whether a yes/no condition holds (is this tool call grounded, should the agent ask first, is the customer angry), and how severe or urgent it is on a rubric, each with a calibrated confidence. Runs Claude Haiku in the request and response shapes of OpenAI's Decisions API, for when no purpose-built decision model is at hand. Use for "route this ticket", "triage these", "classify with a confidence", "give me a probability that", "rate the severity", "score against this rubric", guardrail checks before a tool call, or "a Decisions API without OpenAI".InginerieFără avertismente★ 157↓ —Apare și în 2 alte depozite
- orchestrating-agentsoaustegard/claude-skillsDEPRECATED, renamed to orchestrating-chat-agents. Kept so existing imports of its scripts keep working; every module here loads the same module from orchestrating-chat-agents. Use orchestrating-chat-agents for parallel Claude calls over the API from claude.ai, and dispatching-subagents for fan-out in Claude Code.InginerieFără avertismente★ 157↓ —Apare și în 1 alt depozit
- inspecting-skillsoaustegard/claude-skillsDiscovers and indexes Python code in skills, enabling cross-skill imports. Use when importing functions from other skills or analyzing skill codebases.InginerieFără avertismente★ 157↓ —Apare și în 1 alt depozit