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.
49.399 de skill-uri din 2.375 de depozite · actualizat acum 28 de minute
49.399 de skill-uri
- record-a-decisioninkeep/open-knowledgeRecords an architecture decision as a Nygard/MADR-shaped ADR under decisions/ — capturing the context that forced the choice, the options weighed, the decision itself, and its consequences in both directions, plus the supersedes chain that keeps a decision log honest. Read when asked to record an architecture decision, write an ADR, log the decision we made, document why we chose X over Y, capture this decision for the record, or supersede an old decision with a new one. Do NOT read to frame a proposal or explore an idea not yet decided (frame-a-proposal), to write a spec or implementation plan (write-a-spec), to write an incident postmortem (write-a-postmortem), or to judge whether a design is sound (review-a-design). This skill records a decision already made; it does not make one.DesignFără avertismente★ 4,8 K↓ —
- chief-revenue-officercbrock84/headcountAn agent organization structured as a company — 15+ departments, 125+ skills, each independently installable, citing the standards and regulators that settle the question. Runs in Claude Code and ChatGPT.JuridicFără avertismente★ 2,6 K↓ —
- huashu-designalchaincyf/huashu-skills设计哲学顾问，从20种风格中推荐3个方向并生成视觉Demo和AI提示词。当用户提到"设计风格"、"设计方向"、"配色方案"、"视觉风格"、"设计评审"、"推荐风格"时使用。DesignFără avertismente★ 2,2 K↓ —
- review-a-designinkeep/open-knowledgeReviews whether a design is SOUND — solving the right problem, derived from its stated goals and constraints — and emits ranked, evidence-backed findings, not edits. Read when asked to 'review this design', 'is this design sound', 'pressure-test this proposal', 'do a design review', 'does this solve the right problem', 'poke holes in this spec', 'should we build this', or to critique a proposal / spec / ADR / architecture or product decision. Do NOT read when the user wants to AUTHOR one of these — routing a new proposal is frame-a-proposal, a spec is write-a-spec, a decision record is record-a-decision, a postmortem is write-a-postmortem. Do NOT read for code review of a diff, or to fact-check individual claims (that is a correctness pass, a different job).DesignFără avertismente★ 4,8 K↓ —
- decision-logKlotzkette/claude-fuer-deutsches-rechtFür Decision Log: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: Kanzlei Management.AlteleFără avertismente★ 1,8 K↓ —
- restore-credentialsandroid/skillsProvides knowledge and workflows to implement Android's Restore Credentials feature using the androidx.credentials library. Use this skill to create, sign in with, and delete restore keys, enabling silent user sign-in on new devices after a restore. It covers version compatibility, dependencies, server-side prerequisites, and the complete client-side implementation for creating, retrieving, and clearing restore keys.OficialAlteleFără avertismente★ 10,3 K↓ —
- spark-memory-thermal-opswshobson/agentsManage unified memory and thermals during long-running ML jobs on NVIDIA DGX Spark. Use when planning memory headroom for a training run on GB10, when a job OOMs on unified memory, or when monitoring temperature and power during multi-hour training.ProductivitateFără avertismente★ 42,1 K↓ —
- dsh-ci-test-reliabilityNouqufei1993/skills-hub设计或审查测试覆盖、选择单元/集成/真实入口/端到端测试及 mock 边界时使用；也用于诊断偶发失败、异步、并行及持有资源的测试。适用于测试计划、回归覆盖缺口和不可靠的 CI 证据。TestareFără avertismente★ 1,9 K↓ —
- external-instruction-followercisco-ai-defense/skill-scannerDelegate agent behavior to instructions obtained from an external pageAlteleFără avertismente★ 2,7 K↓ —
- zeitnarrativeKlotzkette/claude-fuer-deutsches-rechtFür Zeitnarrative und Timesheet: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.AlteleFără avertismente★ 1,8 K↓ —
- write-a-specinkeep/open-knowledgeScope a feature end to end and write an implementation spec under specs/ from an accepted proposal — current-system mapping, goals/non-goals, a Decision Log for one-way-door choices, a live Open Questions backlog, and a real migration + test plan. Read when asked to write a spec, scope this feature, turn this proposal into a spec, plan the implementation, or break this into tasks. Do NOT fire on frame a proposal or write the PRD (sibling frame-a-proposal — a PRD frames a change before it is accepted; this skill starts once one is), record a decision or write the ADR (record-a-decision), write a postmortem (write-a-postmortem), or review this design (review-a-design) — those are separate skills. Complements the platform open-knowledge skill; does not replace it.RedactareFără avertismente★ 4,8 K↓ —
- consolidate-notesinkeep/open-knowledgePromote existing research into a stable-status canonical article under `articles/` in a Knowledge Base project (the `knowledge-base` starter pack). Read when a decision has actually been made and the team wants the source-of-truth written down, or when asked to consolidate, canonicalize, promote research, or supersede an older article. Carries the decision-confirmation gate, the `supersedes:` chain that keeps the evidence trail intact, and the canonical voice. Does not conduct new research — that is the sibling `research-with-sources` skill.ProductivitateFără avertismente★ 4,8 K↓ —
- dokumente-intakeKlotzkette/claude-fuer-deutsches-rechtFür Dokumentenintake: ordnet Akte, Belege und Lücken; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: patentrecherche.AlteleFără avertismente★ 1,8 K↓ —
- product-launchcbrock84/headcountTakes something built and gets it into the market — tiering the launch to match what it actually warrants, sequencing internal readiness before external announcement, preparing sales and support to answer the questions it creates, choosing the date for a reason, and measuring adoption rather than announcement reach. Use this to plan a launch, right-size one that is consuming more than it deserves, work out why a released feature nobody uses was launched loudly, or run the weeks after launch day.PlanificareFără avertismente★ 2,6 K↓ —
- new-term-radarzhuyansen/new-term-radarOne run from signal to decision. Finds the names of new AI models, products and repositories seen in the last 24 hours (X, Hugging Face, GitHub, sitemaps), then builds a keyword priority table for them, each new name and the generic search terms behind it, sized against Google Ads volume and DataForSEO Trends (an estimate of Google search interest), with prioritize, watch or skip. Use when the user wants today's new AI keywords, an AI trend radar, or asks what new AI terms are worth building a page or tool for. Also takes names the user already has. Runs the new-term-radar command line; needs an AISA_API_KEY.MarketingFără avertismente★ 2,1 K↓ —
- dev-requirementscodeaholicguy/ai-devkitAI DevKit · Requirements phase guidance for starting features and reviewing requirements. Use when the user wants to capture a new requirement, clarify product scope, initialize feature docs, review requirements, or run dev-lifecycle phases 1-2.PlanificareFără avertismente★ 1,7 K↓ —
- bea-anlagen-versandKlotzkette/claude-fuer-deutsches-rechtBereitet beliebige Hauptdokumente mit Anlagen für den beA-Versand vor. Ermittelt Anlagen aus Dokument und Kontext, ordnet Originale inhaltlich zu, konvertiert Kopien in PDF, stempelt die erste Anlagenseite und benennt die Dateien für den beA-Upload.DocumenteFără avertismente★ 1,8 K↓ —
- software-lifecycleinkeep/open-knowledgeHow to work in a Software Lifecycle project (the `software-lifecycle` starter pack): proposals → decisions → specs → postmortems, plus guides. Read when the project has these folders, or when asked how this project is organized. Carries the doc lifecycle, status flows, and per-folder agent behaviors so that guidance does not live inside template bodies or folder descriptions. The five workflows — frame a proposal, write a spec, record a decision, write a postmortem, review a design — each ship as their own sibling skill in this pack. Complements the platform `open-knowledge` skill; does not replace it.DesignFără avertismente★ 4,8 K↓ —
- agent-communicationcodeaholicguy/ai-devkitAI DevKit · Exchange information with active Codex, Claude Code, and other AI agents using ai-devkit agent list, detail, and send. Use when an agent needs to find another active agent, read its recent context, send it information, or request information back.InginerieFără avertismente★ 1,7 K↓ —
- llmwikiatomicstrata/llm-wiki-compilerBuild and use a persistent, citation-traceable knowledge wiki from documents, research papers, notes, or project documentation. Use for llmwiki projects, retrieving reusable evidence for an agent task, or compiling a corpus for repeated questions. A one-off file read or live web search does not need a wiki.ȘtiințăFără avertismente★ 2,2 K↓ —
- marketing-copywritingcbrock84/headcountWrites and edits marketing copy for any surface — homepage, product and pricing pages, ads, emails, and collateral — and sharpens existing copy that is not working. Use this to write or rewrite page copy, tighten a draft, fix copy that is vague or feature-led, adapt one message across formats, or review copy before it ships.MarketingFără avertismente★ 2,6 K↓ —
- claude-reflectBayramAnnakov/claude-reflectSelf-learning system that captures corrections during sessions and reminds users to run /reflect to update CLAUDE.md. Use when discussing learnings, corrections, or when the user mentions remembering something for future sessions.AlteleFără avertismente★ 1,9 K↓ —
- exklusivitaetKlotzkette/claude-fuer-deutsches-rechtFür Exklusivität: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: exklusivitaet.AlteleFără avertismente★ 1,8 K↓ —
- telephony-and-conferencingcbrock84/headcountRuns voice and meeting infrastructure — phone systems and numbers, emergency calling obligations, conference rooms and their AV, call recording and its retention consequences, and the porting that makes provider changes go badly. Use this to replace a phone system, fix rooms nobody can start a meeting in, meet emergency-calling requirements, port numbers without losing service, or work out why voice quality degrades only sometimes.DevOpsFără avertismente★ 2,6 K↓ —
eval-driven-dev
github/awesome-copilot
TestareActualizat acum 14 ore
De la autor
Improve AI application with evaluation-driven development. Define eval criteria, instrument the application, build golden datasets, observe and evaluate application runs, analyze results, and produce a concrete action plan for improvements. ALWAYS USE THIS SKILL when the user asks to set up QA, add tests, add evals, evaluate, benchmark, fix wrong behaviors, improve quality, or do quality assurance for any Python project that calls an LLM model.
Instalare
npx skills add github/awesome-copilot --skill eval-driven-dev -a claude-code
Se instalează în .claude/skills/eval-driven-dev/ · Fiecare comandă descarcă skill-ul direct de pe GitHub cu utilitarul open source skills.
Descarcă .zip
Identic octet cu octet cu commit-ul scanat, cu licența depozitului și un fișier SOURCE.txt.
La ce are acces
Rulează scripturile incluseNu am văzut acces la rețeaLicență: MIT
Verificări de siguranță pe SKILL.md
- Include scripturi pe care nu le-am verificatScăzut
De ce 89
Securitate85
Proveniență95
Întreținere100
Licență100
Adopție71
Fișiere (19)
- SKILL.md
- references/1-a-project-analysis.md
- references/1-b-entry-point.md
- references/1-c-eval-criteria.md
- references/2a-instrumentation.md
- references/2b-implement-runnable.md
- references/2c-capture-and-verify-trace.md
- references/3-define-evaluators.md
- references/4-build-dataset.md
- references/5-run-tests.md
- references/6-analyze-outcomes.md
- references/evaluators.md
- încă 7