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.
45.100 de skill-uri din 2.196 de depozite · actualizat acum 10 ore
5.443 de skill-uri
- input-sanitization-validationwpultimatesecurity/WordPress-Security-SkillsUse when reading any external input in WordPress — $_GET, $_POST, $_REQUEST, $_COOKIE, REST params, shortcode/block attributes, option/meta values, or remote API responses. Unslashes then sanitizes to the correct type (sanitize_text_field, sanitize_email, absint, sanitize_key, wp_kses_post, esc_url_raw) and validates values against expected sets. Apply proactively before storing or using any untrusted value.InginerieFără avertismente★ 53↓ —
- llm-gaterohitg00/pro-workflowLLM-powered quality verification using prompt hooks. Validates commit messages, code patterns, and conventions using AI before allowing operations. Use to set up intelligent guardrails.InginerieFără avertismente★ 2,9 K↓ —
- agent-md-refactorAxWise-GmbH/axwise-flowRefactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.InginerieFără avertismente★ 62↓ —
- speq-git-operationsmarconae/speq-skillThe git/gh operation-to-command mapping and return formats — invoked directly by /speq-plan-pr and /speq-implement-pr.InginerieFără avertismente★ 55↓ —
- product-change-monitorjoomcode/joompulse-skillsMonitors how one or a few products changed over a period — by default week over week — on JoomPulse: Mercado Livre (Brasil) or Shopee Brasil. Use when a seller tracks a named product over time, given a marketplace or JoomPulse link, or a listing, item or catalog identifier. Returns a change table: per product the current value plus the difference versus about a week ago for price, rating and review count, plus current estimated sales and revenue, time on air and the marketplace's own seller and logistics attributes. Triggers: "monitor this product", "track price changes", "what changed this week", "did the price drop"; pt-BR "monitorar este produto", "o preço caiu", "variação de avaliações", "monitorar este produto na Shopee", "acompanhar este item da Shopee". Ask which marketplace when unclear; never mix the two. Sales and revenue are JoomPulse estimates, not real transactions; price, rating and reviews are real. For a point-in-time product and competitor read, use the single-product analysis skill.InginerieFără avertismente★ 54↓ —
- dispatching-parallel-agentsarbiterForge/codeArbiterThe parallel fan-out primitive. Routed to by any skill or command that splits work across independent units and dispatches an agent per unit — subagent-driven-development, /sprint, parallel /review. It owns the dispatch/collect/funnel discipline: bound concurrency, isolate units, collect every result, dedupe overlap, and funnel through finding-triage then the read-only verdict-aggregator. Raw agent output is never consumed before the funnel runs; an agent that errors records its unit as incomplete without corrupting the batch.InginerieFără avertismente★ 149↓ —
- ops-mergedavepoon/buildwithclaudeAutonomous PR merge pipeline. Scans all repos for open PRs, dispatches subagents to fix CI, resolve conflicts, address review comments, then merges. Use --main to also sync dev↔main branches.InginerieVerifică întâi★ 3,7 K↓ —
- using-git-worktreesarbiterForge/codeArbiterOPTIONAL per-task isolation for autonomous parallel work. Routed to only on explicit opt-in by subagent-driven-development or dispatching-parallel-agents, so parallel units mutate files without colliding. Stands up one worktree per unit, works it in isolation, then integrates each unit back onto the caller's working branch for the caller's single commit-gate + finishing-a-development-branch exit. Never on the default path; it does not bypass a gate or finish per unit.InginerieFără avertismente★ 149↓ —
- vercel-react-best-practicescoco-research/cocoPointer to the upstream skill for React and Next.js performance work (data fetching, bundle size, re-renders), installed from upstream.InginerieFără avertismente★ 791↓ —
- using-git-worktreesarbiterForge/codeArbiterOPTIONAL per-task isolation for autonomous parallel work. Routed to only on explicit opt-in by subagent-driven-development or dispatching-parallel-agents, so parallel units mutate files without colliding. Stands up one worktree per unit, works it in isolation, then integrates each unit back onto the caller's working branch for the caller's single commit-gate + finishing-a-development-branch exit. Never on the default path; it does not bypass a gate or finish per unit.InginerieFără avertismente★ 149↓ —
- code-auditarcasilesgroup/ai-engineeringReview code for correctness bugs, concurrency and lifecycle errors, type-safety holes, error handling gaps, API-contract breaks, and maintainability problems, with every finding gated on a concrete failure scenario. Use when asked to review code, check a diff or branch for bugs, look for problems before committing or opening a PR, or assess code quality.InginerieFără avertismente★ 61↓ —
- ai-codegrapharcasilesgroup/ai-engineeringSemantic code intelligence via MCP: call chains, blast radius, cross-file symbol relationships. Uses CodeGraph (colbymchenry/codegraph) — a local-first Rust server that builds a SQLite knowledge graph from tree-sitter ASTs. One tool: codegraph_explore. Use when the question involves "how does X work", "what calls Y", "if I change X what breaks", or cross-file dependency analysis. Not for literal text search — use find/grep for that. Not for file discovery — use glob. Trigger for "codegraph", "code graph", "call chain", "blast radius", "what depends on", "impact analysis".InginerieFără avertismente★ 61↓ —
- instructorKalarisLabs/research-agent-skillsExtracts structured, validated data from LLM responses using the Instructor Python library with Pydantic response models, including nested models, enums, custom validators, automatic retries with validation error feedback, and streaming of partial objects or iterables. Works with Anthropic, OpenAI, and local Ollama models. Use when pulling typed fields or entities out of free text, when classifying text into fixed categories, when an LLM must return JSON that passes schema validation, when failed extractions need automatic retry, or when streaming partial structured results. Not for prompt optimization (use DSPy) or building multi-step chains (use LangChain).InginerieFără avertismente★ 65↓ —
- speq-climarconae/speq-skillQueries specs via the speq CLI: list and read features, validate structure, run the absence check. Invoke first for any spec discovery or validation.InginerieFără avertismente★ 55↓ —
- xs-code-reviewerkaraage0703/ai-assistant-workspace複数のAI（自分/Codex/Grok/Cursor等）でPRをレビューするスキル。GitHub PRの差分を取得し、各AIの視点を統合したレビューを提供する。GitHubへの投稿はユーザーの明示OK後に行う。「PRレビューして」「コードレビューして」「PR#123をチェック」で使用。InginerieFără avertismente★ 137↓ —
- xs-github-repo-analyzerkaraage0703/ai-assistant-workspaceGitHubリポジトリの内容を詳しく分析するスキル。現行HEADを確認し、DeepWikiの索引commitの鮮度を検証して併用。リポジトリ構造・技術スタック・主要ファイルを整理して報告。「リポジトリ分析して」「このリポジトリ見て」で使用。InginerieFără avertismente★ 137↓ —
- refactorarbiterForge/codeArbiterRestructure code without changing observable behavior: rename, extract, inline, move, deduplicate, or replace an internal implementation with an equivalent one. Prove parity through unchanged pre-existing tests. Not for new behavior, bug fixes, explanation-only questions, or committing finished work.InginerieFără avertismente★ 149↓ —
- ca-refactorarbiterForge/codeArbiterRestructure code without changing observable behavior: rename, extract, inline, move, deduplicate, or replace an internal implementation with an equivalent one. Prove parity through unchanged pre-existing tests. Not for new behavior, bug fixes, explanation-only questions, or committing finished work.InginerieFără avertismente★ 149↓ —
- ca-conflictarbiterForge/codeArbiterStop everything and surface a rule conflict — persona vs. docs vs. code. Present both sides and the conflict-hierarchy level; the user resolves. No silent reconciliation.InginerieFără avertismente★ 149↓ —
- commit-gatearbiterForge/codeArbiterCreate a verified local Git commit when committing changes is requested. Not for explaining commit history, drafting a message only, or postponing a commit. Applies every commit gate and never implies a push or PR.InginerieFără avertismente★ 149↓ —
- gsd-debugcoco-research/cocoUse when a bug, failing test, or unexpected behaviour needs investigation, especially across sessions or context resets. Isolates it in a debugger subagent with persistent .planning/debug state, unlike skills/systematic-debugging.InginerieFără avertismente★ 791↓ —
- clerk-setupclerk/skillsSet up Clerk authentication in any project with the Clerk CLI and official framework quickstarts. Use when adding Clerk, initializing Clerk, scaffolding a new app with Clerk, or migrating an existing authentication system to Clerk.OficialInginerieVerifică întâi★ 89↓ —
- commit-worksoftaworks/agent-toolkitCreate high-quality git commits: review/stage intended changes, split into logical commits, and write clear commit messages (including Conventional Commits). Use when the user asks to commit, craft a commit message, stage changes, or split work into multiple commits.InginerieFără avertismente★ 2,6 K↓ —
- outlinesKalarisLabs/research-agent-skillsGenerates guaranteed-valid structured output from LLMs with Outlines (dottxt.ai), constraining token sampling via finite state machines for JSON schemas, Pydantic models, regex, choice lists, and integer/float types, on Transformers, llama.cpp, vLLM, and limited OpenAI backends. Use when you need output that always parses as valid JSON or matches a regex. Use when extracting typed data into Pydantic models from a local model. Use when classifying text into a fixed set of categories. Use when running batch structured generation on vLLM or Transformers. Use when controlling token sampling at the grammar level. Not for API models needing automatic retries (use Instructor).InginerieFără avertismente★ 65↓ —