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.
46.104 skill-uri din 2.198 de depozite · actualizat acum 3 minute
9.544 de skill-uri
- reacutXiangyu-CAS/rea-capcut在 Codex 右侧打开 ReaCut 本地视频编辑器，导入用户选定的素材、编辑时间线、文字和效果，并保存或导出。用于 ReaCut 项目操作，不用于其他视频应用或未授权素材搜集。AlteleFără avertismente★ 101↓ —
- hunt-authEncod3d-Sec/TORCHAuth bypass and ATO hunting - legacy protocol matrix (XMLRPC, SharePoint /_vti_bin/, EWS, Citrix, etc.), JWT manipulation, password reset poisoning, SAML auth bypass, session fixation. Wiki-first, FIND schema output.AlteleFără avertismente★ 336↓ —
- claude-md-improverEncod3d-Sec/TORCHOFFLINE FALLBACK for the claude-md-management plugin - prefer that plugin when it is installed. Audit and improve CLAUDE.md files - scan for CLAUDE.md files, evaluate quality against templates, output a report, then make targeted updates. Invoke explicitly (/claude-md-improver) when the plugin is unavailable.AlteleFără avertismente★ 336↓ —
- headless-cms-expertroedyrustam/vibes-plugExpert guide for Headless CMS integration (Sanity, Payload CMS, Strapi, Contentful, Storyblok) with modern frameworks / Panduan ahli integrasi Headless CMS (Sanity, Payload, Strapi, Contentful) dengan framework modern.AlteleFără avertismente★ 115↓ —
- kv-cache-prefix-optimizerroedyrustam/vibes-plugExpert guide for deterministic prompt prefix engineering, KV-cache locking for Gemini 4 Pro / Claude 5.5 / GPT Astra 6, canonical tool sorting, and achieving 90%+ prompt cache hit rates / Panduan ahli rekayasa prefix prompt deterministik, penguncian KV-cache untuk Gemini 4 Pro / Claude 5.5 / GPT Astra 6, pengurutan kanonikal tool, dan pencapaian 90%+ cache hit rate.AlteleFără avertismente★ 115↓ —
- d3-force-bubblecxcscmu/SkillLearnBenchGuide for creating clustered bubble charts using D3.js force simulations (v6+), including collision and categorization.AlteleFără avertismente★ 91↓ —
- evidenceEncod3d-Sec/TORCHEvidence hygiene before any FIND moves to Completed or enters a report. Cookie redaction, PII black-bar, HAR sanitization, screenshot metadata strip. Run after /triage passes and before final report assembly.AlteleFără avertismente★ 336↓ —
- hunt-smugglingEncod3d-Sec/TORCHHTTP request smuggling / desync hunting - CL.TE, TE.CL, TE.TE, CL.0, and HTTP/2 downgrade. Timing-based detection, differential confirmation, no-blind-claims. Wiki-first, FIND schema output.AlteleFără avertismente★ 336↓ —
- d3-color-legendcxcscmu/SkillLearnBenchAdd a categorical color legend to a D3 chart using colored rectangles or circles with text labels, supporting both SVG-inline and HTML overlay styles.AlteleFără avertismente★ 91↓ —
- hunt-uploadEncod3d-Sec/TORCHFile upload attack hunting - extension/content-type/magic-byte bypass to web-shell RCE, path traversal in filename, SVG/XML XSS, zip slip, and pixel-flood DoS. Wiki-first, FIND schema output.AlteleFără avertismente★ 336↓ —
- disk-cleanupmoonlight-lupin/agent-skillsUse when df says disk is above 80% full or the user wants to reclaim storage space on a VM.AlteleFără avertismente★ 113↓ —
- redteamleadEncod3d-Sec/TORCHOn-demand senior red-team lead advisor. Call at a decision point or obstacle to get wiki-grounded direction instead of hammering blindly. Dispatches a fresh RTL subagent that reads the engagement state + evidence + wiki and returns ranked directions with an explicit STOP. Use for "redteamlead", "RTL", "I'm stuck", "where do I go", "what next", "which vector", "should I keep hammering this".AlteleFără avertismente★ 336↓ —
- jimeng-loginaAAaqwq/AGI-Super-Team即梦AI平台(jimeng.jianying.com)浏览器登录。当需要操作即梦数字人、视频生成等功能前检测到未登录时触发。处理协议同意、抖音OAuth扫码、登录态持久化。AlteleFără avertismente★ 112↓ —
- zhuangxiu-jiancai-xuangouzx029w/zhuangxiu-skills装修建材选购专用 Skill。覆盖瓷砖、木地板、涂料乳胶漆、板材、门窗玻璃、五金管件、防水材料、美缝填缝、石材岩板、踢脚线等主材辅材的选购避坑，整合西安装修课堂装修知识库精华，帮用户把钱花在刀刃上，材料不踩坑。AlteleFără avertismente★ 86↓ —
- next-moveEncod3d-Sec/TORCHRanked next offensive moves from engagement state. Reads state/loot/Killchain, runs the deterministic analyzer, elaborates the top move. Use when asked "what next", "where to focus", "prioritize", or at the start of an engagement session.AlteleFără avertismente★ 336↓ —
- color-material-lighting-directionTheGoat395/Codex-SkillsDefine palette, material and lighting roles.AlteleFără avertismente★ 135↓ —
- hunt-cacheEncod3d-Sec/TORCHWeb cache poisoning + cache deception hunting - unkeyed input poisoning, cache-key analysis, path-confusion deception, header/parameter cloaking. Wiki-first, FIND schema output.AlteleFără avertismente★ 336↓ —
- affective-computing-emotion-airoedyrustam/vibes-plugAffective computing, emotion AI, and multimodal sentiment analysis / Komputasi afektif, AI emosional, dan analisis sentimen multimodal.AlteleFără avertismente★ 115↓ —
- ctf-pwn26zl/cybersec-toolkitUse when solving binary exploitation / pwn CTF challenges — buffer overflows, ROP, format strings, heap, kernel pwn. Provides a decision tree, exploit primitive catalog, and uses pwntools via the run_script(venv="pwntools") MCP path. Triggers on "ctf pwn", "binary exploit", "rop", "buffer overflow", "format string", "heap challenge".AlteleFără avertismente★ 85↓ —
- dependency-upgrade-migratorroedyrustam/vibes-plugDependency upgrades, breaking change migrations, and codemod tooling / Upgrade dependensi, migrasi breaking change, dan otomasi codemod.AlteleFără avertismente★ 115↓ —
- bounty-mobile26zl/cybersec-toolkitUse when bug-bountying an Android (APK) or iOS (IPA) app. Covers static + dynamic analysis, Frida hooking, certificate pinning bypass, deep link / intent abuse, IPC, secrets in bundles. Triggers on "bounty mobile", "android app", "ios app", "apk analysis", "frida".AlteleFără avertismente★ 85↓ —
- bounty-recon26zl/cybersec-toolkitUse at the start of a bug bounty engagement. Provides scope-aware recon methodology — passive enumeration, subdomain discovery, asset attribution, tech stack fingerprinting, content discovery. Respects scope and program rules. Triggers on "bounty recon", "subdomain enum", "attack surface map", "h1 recon", "bug bounty start".AlteleFără avertismente★ 85↓ —
- apple-intelligencershankras/claude-code-apple-skillsApple Intelligence skills for on-device AI features including Foundation Models, Visual Intelligence, App Intents, and intelligent assistants. Use when implementing AI-powered features.AlteleFără avertismente★ 840↓ —
- thinking-budget-orchestratorroedyrustam/vibes-plugDynamic thinking budget orchestrator across late-2026 frontier models / Alokasi budget penalaran dinamis pada model frontier 2026.AlteleFără avertismente★ 115↓ —
clawrouter
aAAaqwq/AGI-Super-Team
AlteleActualizat 20 oct. 2026
De la autor
Smart LLM router — save 67% on inference costs. Routes every request to the cheapest capable model across 41 models from OpenAI, Anthropic, Google, DeepSeek, and xAI.
Instalare
npx skills add aAAaqwq/AGI-Super-Team --skill clawrouter -a claude-code
Se instalează în .claude/skills/clawrouter/ · 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 83
Securitate100
Proveniență65
Întreținere100
Licență100
Adopție35
Fișiere (3)
- .clawdhub/origin.json
- SKILL.md
- _meta.json