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.
25.230 de skill-uri din 917 depozite · actualizat acum 21 de minute
2.635 de skill-uri
- review-dependenciestobihagemann/turboDetect package managers and CI action pins, then discover outdated or vulnerable dependencies. Returns structured findings without upgrading. Use when the user asks to "review dependencies", "check for outdated packages", "check dependencies", "scan dependencies", "dependency review", "check for outdated GitHub Actions", or "are my workflow actions up to date".InginerieFără avertismente★ 416↓ —
- agentsop-map-reduce-fanoutagentsope/SkillAlchemyDecision protocol for the map-reduce / dynamic fan-out pattern in LM pipelines — "given list L, run f(item) for each item in parallel, then combine". Activates when the coder agent is about to process N items with N LM calls (per-doc summarize, per-query retrieve, per-candidate rank, parallel tool fan-out). Encodes the *when*, *how many at once*, *what to do when one fails*, and *how to reduce* — not the API of any single framework. Cross-framework: LangGraph `Send`, CrewAI parallel tasks / Flow, `asyncio.gather`, `ThreadPoolExecutor`, LlamaIndex batch retrieval.InginerieFără avertismente★ 446↓ —
- agentsop-code-execution-decisionagentsope/SkillAlchemyDecision rubric for when an LM agent should write-and-run code (Program-of-Thought / code interpreter) versus reason in natural language: classify each step as deterministic- computable (emit + execute code, feed the result back) vs judgment (stay in prose). Use when designing or debugging an agent step that does arithmetic/parsing/data transforms, when prose reasoning hallucinates a computation (under-coding), or when a sandbox round- trip is wasted on a judgment task (over-coding). Search keywords: code interpreter, agent does math wrong, calculator hallucination, when to run code vs reason, program of thought, PoT, tool vs reasoning.InginerieFără avertismente★ 446↓ —
- agentsop-session-state-hygieneagentsope/SkillAlchemyDecision protocol for managing the context/session state of an AI coding tool: when to /clear, when to keep context, and how to detect "context bleed" — the failure mode where stale conversation history biases the model against the current task. Surfaces a discipline that Aider (/clear), Claude Code (/clear), CrewAI (memory=False, re-instantiate), and LangGraph (new thread_id, subgraph isolation) all encode separately but none name as a skill.InginerieFără avertismente★ 446↓ —
- action-list-reviewxiaomoBoy/pi-bluebook把会议记录整理为可核对的行动清单；当任务要求提取负责人、截止日期、交付物和限制时使用。InginerieFără avertismente★ 325↓ —
- review-skillskilld-dev/skilldReview an Agent Skill for valid structure, clear triggers, usable instructions, current evidence, and risky or unclear actions.InginerieFără avertismente★ 327↓ —
- skilldskilld-dev/skilldOperate skilld CLI for Skill discovery, use, installation, inspection, updates, authentication, configuration, restoration, and removal, including Repository, curator, and collection refs. Also read the skilld.dev registry (view, browse, trending, tracks, curators, index) and act for the user's skilld.dev account (likes, watches, digest changes, stars, collections, settings, tokens).InginerieFără avertismente★ 327↓ —
- fable-operatorericrisco/rsc-harnessUse when a substantive request needs verified, calibrated reasoning — analysis, diagnosis, review, advice, or a draft the user will act on — even when rigor is not asked for, and most of all when being wrong is expensive or irreversible. NOT casual chat (rigor theater), NOT the SDD gates `verify`, `debug`, `review`; this is the discipline beneath them.InginerieFără avertismente★ 255↓ —
- assessment-sequence-governancezero-lab-ai/skillsValidates supplied immutable ordered manifests of opaque defensive assessment actions for authority, safeguards, evidence, and separate-operator review. Use when reviewing assessment sequencing without creating, changing, or executing actions.InginerieFără avertismente★ 281↓ —
- rest-api-djangoMindrally/skillsComprehensive guidelines for Django REST API development covering project structure, views, models, serializers, authentication, performance, and error handling.InginerieFără avertismente★ 286↓ —
- amazon-review-strategynexscope-ai/Amazon-SkillsReview generation strategy — Request a Review, follow-up emails, insert cards, Vine, early reviewer programsInginerieFără avertismente★ 798↓ —
- bluebook-graduation-reviewxiaomoBoy/pi-bluebook只讀審閱 Pi 藍皮書畢業專案的需求覆蓋、修改範圍、導航連接和驗收證據；用於實現完成後的獨立複核。InginerieFără avertismente★ 325↓ —
- fix-worktree-opsx-skills-not-createdBlackBeltTechnology/pi-agent-dashboardDiagnose/fix worktrees missing the generated openspec-* (opsx) skills after worktreeInit. Root cause: bare `npx openspec` can resolve a squatted registry stub instead of the real CLI.InginerieFără avertismente★ 331↓ —
- API FuzzingPramodDutta/qaskillsAPI endpoint fuzzing for discovering unexpected behaviors, crashes, and security vulnerabilities through malformed requests, boundary values, and protocol violations.InginerieFără avertismente★ 240↓ —
- bluebook-graduation-reviewxiaomoBoy/pi-bluebook只读审阅 Pi 蓝皮书毕业项目的需求覆盖、修改范围、导航连接和验收证据；用于实现完成后的独立复核。InginerieFără avertismente★ 325↓ —
- zod-react-hook-formBlackBeltTechnology/pi-agent-dashboardForm validation combining Zod schemas with React Hook Form, including localized error messages, Server Action integration, and shadcn/ui Form components. Use when building forms, validating user input, handling form submissions, or implementing Server Actions with validation.InginerieFără avertismente★ 331↓ —
- systematic-debuggingBlackBeltTechnology/pi-agent-dashboardRoot-cause a bug already in front of you, instead of guessing at fixes. Use on triggers like "root cause this", "why is this failing", "debug systematically", "this test is flaky", "it works locally but not in CI", or when a fix attempt has already failed once. Enforces a phased evidence-first process before any code change. Not a feature-build or ship workflow.InginerieFără avertismente★ 331↓ —
- typescript-strictBlackBeltTechnology/pi-agent-dashboardTypeScript strict mode patterns with interfaces, type guards, generics, and utility types. Use when defining types, creating type-safe functions, handling nullable values, or implementing generic components.InginerieFără avertismente★ 331↓ —
- doubt-driven-reviewBlackBeltTechnology/pi-agent-dashboardIn-flight adversarial check on a non-trivial decision BEFORE it stands — distinct from post-hoc review of a finished diff. Use on "stress-test this decision", "are we sure about this", "verify before commit", "poke holes in this", when working in unfamiliar code, or before an irreversible step (migration, prod deploy, public API). Runs earlier than code-review, while course-correction is cheap.InginerieFără avertismente★ 331↓ —
- youtube-apiartemchuikin/youtube-skillsReach for this when YouTube data is needed and Google's Data API is the obstacle: no quota units, no OAuth consent screens, one Bearer key. Covers transcripts (which Google's API does not serve at all), metadata, search, channels and playlists. Triggers on YouTube links, @handles and creator research. Skip it for uploads and account chores.InginerieFără avertismente★ 336↓ —
- sealeap-tengshe-amazon-amc-query-reviewxjli360/sealeap-amazon-skillsReview an Amazon Marketing Cloud SQL query for business-question fit, event grain, joins, deduplication, attribution windows, privacy thresholds, QA totals, and interpretation. Use before trusting or activating AMC output.InginerieFără avertismente★ 318↓ —
- makeericrisco/rsc-harnessUse when operating Make.com (formerly Integromat) programmatically — driving its REST API v2 or the Make MCP server from code or an agent to create, read, update, activate, run, clone or delete scenarios, connections, hooks and data stores. NOT designing what the flow should do (that is `automation-flows`), NOT choosing between Make, n8n and Zapier by billing model (that is `automation-strategy`), NOT a generic typed REST client (that is `api-connector-builder`), NOT receiving inbound webhooks in your own app (that is `webhooks`).InginerieFără avertismente★ 255↓ —
- code-simplificationBlackBeltTechnology/pi-agent-dashboardActive simplify pass for working code. Use when explicitly asked to "simplify this", "reduce complexity", "clean this up", "make this clearer", or when behavior-preserving readability/maintainability is the goal. Complements the project's passive simplicity-first rule by running a deliberate complexity-reduction loop. Not a spec, plan, or review workflow — does not change behavior.InginerieFără avertismente★ 331↓ —
- vllmericrisco/rsc-harnessUse when self-hosting an open-weight LLM for high-throughput concurrent serving with vLLM — running an OpenAI-compatible endpoint, splitting a model across GPUs with tensor or pipeline parallelism, loading quantized weights, serving one or many LoRA adapters, and debugging KV-cache OOM from memory-utilisation and context-length flags. NOT renting or provisioning the GPU box (that is `runpod` or `modal`), NOT single-user laptop inference (that is `ollama`), NOT a hosted inference API you do not operate (that is `together-fireworks` or `huggingface`).InginerieFără avertismente★ 255↓ —