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.
17.667 de skill-uri din 618 depozite · actualizat acum 1 minut
3.369 de skill-uri
- privacy-jpkimlawtech/korean-privacy-terms日本サービス向け（일본 서비스용） プライバシーポリシー・利用規約・同意モーダル・Cookieバナー 자동 생성. 個人情報保護法(APPI)·消費者契約法·特定商取引法 반영. Next.js 13~16 프로젝트 대상.AlteleFără avertismente★ 591↓ —
- privacy-global-jpkimlawtech/korean-privacy-terms한국+일본 병기 처리방침·이용약관 자동 생성. 한국 본사가 일본 사용자까지 대상으로 서비스할 때 사용. 한국어(PIPA)·일본어(APPI) 두 세트 문서를 동시 생성하고, Footer에 언어·관할 전환 링크 자동 삽입.AlteleFără avertismente★ 591↓ —
- content-creation-publisheranbeime/skill内容创作者与自媒体创作者在需要将网页素材转化为多平台图文时，使用本技能可自动完成网页提取、Markdown排版美化、智能配图，并一键发布至微信公众号与X/Twitter，轻松实现从采集到发布的一站式自动化工作流。AlteleFără avertismente★ 8,6 K↓ —
- agent-teamanbeime/skill产品经理与项目管理专家在应对复杂项目时，使用此技能可动态组建包含“执行、指挥、评审”的专属AI团队。实时查看多智能体辩论与决策全过程，共享统一上下文记忆，一键完成从会议决策到系统构建的全流程高效协同！AlteleFără avertismente★ 8,6 K↓ —
- hive.terminal-tools-troubleshootingaden-hive/hiveRead when a terminal-tools call returned something surprising — empty stdout despite no error, exit_code is null, output_handle came back expired, "too many jobs" / "session busy" / "too many PTYs", warning was set unexpectedly, semantic_status disagrees with exit_code. Diagnostic recipes only — load on demand. Don't preload; the foundational skill covers the happy path.AlteleVerifică întâi★ 11,1 K↓ —
- helpvibeeval/vibecosystemInteractive workspace discovery - learn what tools, workflows, agents, and hooks are availableAlteleFără avertismente★ 540↓ —
- mathvibeeval/vibecosystemMulti-layer cognitive stack for machine-verified mathematical problem solving across 14 sub-disciplines.AlteleFără avertismente★ 540↓ —
- clipboardbitwize-music-studio/claude-ai-music-skillsCopies track content (lyrics, style prompts, streaming lyrics) to the system clipboard. Use when the user needs to paste lyrics or style prompts into Suno or other external tools.AlteleFără avertismente★ 580↓ —
- nie-grassroots-logicayi-ai/nie-grassroots-logic聂辉华《基层中国的运行逻辑》方法论工具箱：政治经济学/组织经济学视角解释基层权力与治理， 并落到个人抉择（求学/考公/投资/养老/创业）。 核心框架：内外冲突的双均衡、条块结合以块为主、等级制资源配置（人跟资源走、资源跟权力走）、 职务含权量三因子、县委书记三座大山（维稳/招商/借债）、压力型体制与注意力分配、 政企四象限博弈、土地财政闭环、活力—秩序城市化权衡、上下同治。 当用户要理解基层/县域/乡镇治理、条块矛盾、属地责任、央地关系、官员晋升与考核、 一票否决、形式主义、招商引资、土地财政、地方债、街道办与村官、考公选岗、 高考志愿/选城读书、买房与区域投资风险、回哪养老、创业对接园区政府、 撤县设区/县改市对家庭影响、谁适合当村支书、大学生村官值不值得去、 新型职业农民/致富能手/回乡创业、昆山式改革/自下而上推项目/西气东输式立项、 营商环境比较、投资不过山海关、政商关系亲清、容错创新/基层敢不敢干、 抢高铁站/重大工程争夺、政策为何落地难、解读地方新闻、 或提到聂辉华/基层中国的运行逻辑/上下同治/含权量/条块结合/双均衡时使用。AlteleFără avertismente★ 572↓ —
- gate-checkvibeeval/vibecosystemPhase transition validation with artifact checklists, PASS/FAIL/CONDITIONAL gates for workflowsAlteleFără avertismente★ 540↓ —
- agent-lintervibeeval/vibecosystemAgent ve skill dosyalarinin yapisal dogrulamasi. Frontmatter kontrol, naming convention, zorunlu bolum kontrolu, tutarlilik denetimi. Yeni agent/skill eklendiginde veya mevcut dosyalar duzenlediginde otomatik calistirilir.AlteleFără avertismente★ 540↓ —
- mcp-registryvibeeval/vibecosystemMCP server registry, auto-discovery, configuration, custom server development guideAlteleFără avertismente★ 540↓ —
- rag-patternsvibeeval/vibecosystemChunking strategies, embedding model selection, hybrid search, reranking, eval metricsAlteleFără avertismente★ 540↓ —
- token-budgetvibeeval/vibecosystemAgent basina token kullanimi takibi, maliyet optimizasyonu, butce limitleri ve ROI analizi. Session ve proje bazinda harcama raporlari. Hangi agent ne kadar token tuketiyor, hangisi verimli, hangisi israf.AlteleFără avertismente★ 540↓ —
- loogle-searchvibeeval/vibecosystemSearch Mathlib for lemmas by type signature pattern using Loogle.AlteleFără avertismente★ 540↓ —
- create-handoffvibeeval/vibecosystemCreate handoff document for transferring work to another sessionAlteleFără avertismente★ 540↓ —
- oauth-patternsvibeeval/vibecosystemOIDC flows, PKCE implementation, token refresh strategies, social login integration, and secure session management.AlteleFără avertismente★ 540↓ —
- redis-patternsvibeeval/vibecosystemData structure selection, pub/sub patterns, Lua scripting, pipelining, and cluster topology strategies.AlteleFără avertismente★ 540↓ —
- agent-benchmarkvibeeval/vibecosystemFramework for measuring and tracking agent response quality over time. Detects regressions before they reach production. Use when evaluating agent changes, auditing quality, or establishing performance baselines.AlteleFără avertismente★ 540↓ —
- circuit-breakervibeeval/vibecosystemAgent hata toleransi ve devre kesici pattern. Ust uste hata yapan agent'i durdur, cooldown uygula, fallback'e gec. Kaskatli hatalari ve sonsuz retry dongularini onler.AlteleFără avertismente★ 540↓ —
- factcheck-guardvibeeval/vibecosystemUse this skill when making any factual claim about the codebase — existence, absence, or behavior. Converts the claim-verification rule into a systematic action protocol that prevents false assertions from grep-only results.AlteleFără avertismente★ 540↓ —
- golang-patternsvibeeval/vibecosystemIdiomatic Go patterns, best practices, and conventions for building robust, efficient, and maintainable Go applications.AlteleFără avertismente★ 540↓ —
- harvest-monitorvibeeval/vibecosystemWeb change monitoring - track changes on pages, detect updates, changelog diffsAlteleFără avertismente★ 540↓ —
- skill-evolutionvibeeval/vibecosystemSelf-evolving skill system. Skills are scored after execution (0-100) on 5 dimensions. Score 90+ over 5 runs = crystallized (locked). Score below 30 = auto-repair attempted. Skills improve themselves through usage feedback.AlteleFără avertismente★ 540↓ —
agent-benchmark
vibeeval/vibecosystem
AlteleActualizat 8 aug. 2026
De la autor
Framework for measuring and tracking agent response quality over time. Detects regressions before they reach production. Use when evaluating agent changes, auditing quality, or establishing performance baselines.
Instalare
npx skills add vibeeval/vibecosystem --skill agent-benchmark -a claude-code
Se instalează în .claude/skills/agent-benchmark/ · 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
Doar instrucțiuniNu am văzut acces la rețeaLicență: MIT
Verificări de siguranță pe SKILL.md
Niciun avertisment.
De ce 84
Securitate100
Proveniență73
Întreținere85
Licență100
Adopție45
Fișiere (1)
- SKILL.md