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.
49.539 de skill-uri din 2.407 depozite · actualizat acum 2 minute
49.541 de skill-uri
- browser-automationalirezarezvani/claude-skillsAutomate a browser: scrape websites, fill forms, pull structured data from web pages. Use whenever the user wants to grab data from a site, fill a web form or extract a table. Browser testing: playwright-pro.BrowserFără avertismente★ 29,3 K↓ —
- git-worktree-manageralirezarezvani/claude-skillsUse when running several branches or agents in parallel on one repo. Creates worktrees with isolated ports and env via worktree_manager.py and removes stale ones with worktree_cleanup.py.InginerieFără avertismente★ 29,3 K↓ —
- mcp-server-builderalirezarezvani/claude-skillsUse when exposing an API as an MCP server or scaffolding a new MCP server in Python or TypeScript, before hand-writing tool wrappers. Generates tools from OpenAPI with openapi_to_mcp.py and validates them with mcp_validator.py.RedactareFără avertismente★ 29,3 K↓ —
- jetson-optimize-memoryNVIDIA/skillsReclaim DRAM by disabling unused subsystems across MB1 BCT, MB2 BCT, kernel reserved-memory, and SWIOTLB. Use for headless or no-camera Jetson deployments; not for CPU/GPU frequency tuning.ProductivitateFără avertismente★ 3,9 K↓ —
- reportevo-hq/evoRead-only evo run reporting. Use when the user invokes /evo:report, asks what happened overnight, asks what improved recently, asks for the best/frontier candidates, asks for a quick score chart without opening the dashboard, or wants the scatter plot in chat output. Never run benchmarks, gates, Slurm commands, evo run, or ad-hoc verification scripts for report requests.MarketingFără avertismente★ 1,5 K↓ —Apare și în 1 alt depozit
- senior-securityalirezarezvani/claude-skillsCheck if a design or code is secure: STRIDE threat model, DREAD risk scores, leaked secret scan. Use whenever the user asks what could be attacked, how risky a feature is, or to find exposed keys.SecuritateFără avertismente★ 29,3 K↓ —
- eu-ai-act-specialistalirezarezvani/claude-skillsUse for EU AI Act (Regulation 2024/1689) compliance work: classifying an AI system's risk tier, planning the Art. 43 conformity route and Annex IV file, or listing obligations by role. Runs ai_system_risk_classifier.py, conformity_assessment_planner.py and ai_act_obligation_tracker.py, citing Articles.PlanificareFără avertismente★ 29,3 K↓ —
- scrum-masteralirezarezvani/claude-skillsUse for sprint and team analytics: velocity forecasts, sprint health, retrospectives, burndown or blockers. Forecasts with velocity_analyzer.py (Monte Carlo), scores with sprint_health_scorer.py and tracks retro actions with retrospective_analyzer.py.DateFără avertismente★ 29,3 K↓ —
- paid-ads-strategykostja94/marketing-skillsWhen the user wants to plan paid ads strategy, allocate ad budget, or choose paid channels. Also use when the user mentions "paid ads," "paid media," "PPC," "SEM," "web ads," "app ads," "TV ads," "CTV," "OOH," "banner ads," "ad network," "ad alliance," "Taaft ads," "Shopify App Store ads," "Google Ads," "Meta Ads," "PMF testing," "PMF validation," "test product-market fit with ads," "ad spend," "ad budget," "ROAS," "paid acquisition," "Quality Score," or "ad-to-page alignment." For Google Ads execution, use google-ads. For Meta Ads execution, use meta-ads. For landing page alignment, use landing-page-generator.MarketingFără avertismente★ 1,1 K↓ —
- devils-twinmohitagw15856/pm-claude-skillsThe strongest possible case AGAINST what you just wrote — argued to win, not to check a box. Use when a document is about to ship and everyone around it already agrees: the twin writes the opposition's best memo (not a critique of yours), so you meet the real counter-argument before your audience does. Produces the opposing memo, the map of which of your claims it defeats/dents/leaves standing, and the pre-emption paragraph worth adding.RedactareFără avertismente★ 1,5 K↓ —
- model-cardmohitagw15856/pm-claude-skillsDocument a deployed ML/AI model so others can use it responsibly. Use when asked to write a model card, document a model's intended use and limitations, or prepare an AI model for review/launch. Produces a complete model card — intended use, training data, evaluation metrics across slices, limitations, ethical considerations, and a deployment checklist.DevOpsFără avertismente★ 1,5 K↓ —
- cn-5s-auditmohitagw15856/pm-claude-skillsUse when asked 5S 检查表, 6S 管理, 现场管理检查, 5S 评分标准, 车间 6S 稽核, 做一份 5S 推行计划, or design a 5S or 6S audit for a workshop, warehouse or office in a Chinese factory. Produces an audit checklist for the area with scored criteria for 整理, 整顿, 清扫, 清洁, 素养 (and 安全 for 6S), a scoring guide with photo evidence rules, a results summary and red-tag list, a corrective-action tracker with owners and dates, and an audit rota, in Chinese.DesignFără avertismente★ 1,5 K↓ —
- mcp-oauth-triagealirezarezvani/claude-skillsUse when an MCP connector that used to authenticate now fails (tool calls 401 after a good token exchange, breaks after refresh, returns another account's data), before changing code. Classifies the fault with oauth_triage.py.InginerieFără avertismente★ 29,3 K↓ —
- claude-authenticityagentscope-ai/OpenJudgeDetect whether an API endpoint is backed by genuine Claude (not a wrapper, proxy, or impersonator) using 9 weighted rule-based checks that mirror the claude-verify project. Also extracts injected system prompts from providers that override Claude's identity. Fully self-contained — copy the code below and run, no extra packages beyond httpx. Use when the user wants to verify a Claude API key or endpoint, check if a third-party Claude service is authentic, audit API providers for Claude authenticity, test multiple models in parallel, or discover what system prompt a provider has injected.TestareFără avertismente★ 1,1 K↓ —
- api-docs-writermohitagw15856/pm-claude-skillsWrite clear, developer-facing API documentation. Use when asked to document an API endpoint, write API reference docs, create a developer guide, or turn a raw spec/Postman collection into documentation. Produces endpoint documentation with descriptions, parameters, request/response examples, and error codes.RedactareFără avertismente★ 1,5 K↓ —
- email-triagemohitagw15856/pm-claude-skillsTriage a Gmail inbox down to only what needs you. Use when asked to triage email, clear an inbox, find what needs a reply, or summarise recent mail. Produces a prioritised list of items needing action — replies, decisions, follow-ups — for a configurable window (default last 8 hours), filtering out receipts, notifications, and newsletters.ProductivitateFără avertismente★ 1,5 K↓ —
- minutes-setupsilverstein/minutesGuided first-time setup for Minutes — download whisper model, create directories, configure audio input. Use when the user says "set up minutes", "install minutes", "first time setup", "configure minutes", "get started with minutes", "how do I start using minutes", or when verify shows missing components.MediaFără avertismente★ 1,6 K↓ —Apare și în 1 alt depozit
- raci-matrixmohitagw15856/pm-claude-skillsDefine a RACI matrix for a cross-functional project or process. Use when asked to build a RACI, create a responsibility matrix, clarify ownership across teams, or document decision rights. Produces a complete RACI matrix with role definitions, decision mapping, and a process for resolving conflicts.AlteleFără avertismente★ 1,5 K↓ —
- offer-lettermohitagw15856/pm-claude-skillsDraft a job offer — the written offer letter and a verbal-offer script. Use when asked to write an offer letter, a job offer, an employment offer, or to prepare to extend/verbal an offer to a candidate. Produces a clear, warm offer letter (role, comp, start, key terms, contingencies, acceptance) plus a verbal-offer call script — flagging that employment terms need HR/legal review. Not legal advice.JuridicFără avertismente★ 1,5 K↓ —
- handbook-pagemohitagw15856/pm-claude-skillsWrite the handbook page that ends the repeated explanation — the answer-shaped structure (task-first, context second), the ownership and freshness header, and the write-once-point-forever discipline that turns tribal knowledge into infrastructure. Use when asked document how we do X, write the wiki page for this process, I explain this every month, or make this knowledge survive me. Produces the page with task-first structure, the header block, the worked example, and the pointer habit.DevOpsFără avertismente★ 1,5 K↓ —
- windfall-planmohitagw15856/pm-claude-skillsMake a smart plan for a lump sum — a bonus, inheritance, tax refund, settlement, or sale — so it builds your future instead of evaporating into lifestyle. Use when asked what should I do with a windfall, I came into some money, how to use a bonus/inheritance/tax refund, or don't want to waste this money. Produces a cool-off-first plan, a tax/obligations check, an allocation across foundation-building, goals, and a guilt-free fun slice, and cautions against the classic windfall traps and the vultures that appear. Educational — not financial advice.PlanificareFără avertismente★ 1,5 K↓ —
- add-atomic-chat-toolnanocoai/nanoclawAdd Atomic Chat MCP server so the container agent can call local models served by the Atomic Chat desktop app via its OpenAI-compatible API.InginerieFără avertismente★ 31,1 K↓ —
- add-codexnanocoai/nanoclawUse Codex (OpenAI's codex app-server) as a full agent provider — planning, tool orchestration, MCP tools, server-side history, session resume — alongside or instead of Claude. ChatGPT subscription or OpenAI API key, vault-only via the selected gateway. Per-group via `ncl groups config update --provider codex`. Distinct from using OpenAI as an MCP tool (where Claude remains the planner).PlanificareFără avertismente★ 31,1 K↓ —
- setupfcakyon/claude-codex-settingsThis skill should be used when user asks to "set up QA", "create real integration tests", or "add project QA journeys" for websites, extensions, Android apps or backends.TestareFără avertismente★ 1,2 K↓ —
01-auto-arena
agentscope-ai/OpenJudge
TestareActualizat acum 9 ore
De la autor
Automatically evaluate and compare multiple AI models or agents without pre-existing test data. Generates test queries from a task description, collects responses from all target endpoints, auto-generates evaluation rubrics, runs pairwise comparisons via a judge model, and produces win-rate rankings with reports and charts. Supports checkpoint resume, incremental endpoint addition, and judge model hot-swap. Use when the user asks to compare, benchmark, or rank multiple models or agents on a custom task, or run an arena-style evaluation.
Instalare
npx skills add agentscope-ai/OpenJudge --skill 01-auto-arena -a claude-code
Se instalează în .claude/skills/01-auto-arena/ · 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 instrucțiuniFolosește rețeauaLicență: APACHE-2.0
Verificări de siguranță pe SKILL.md
Niciun avertisment.
De ce 88
Securitate100
Proveniență76
Întreținere100
Licență100
Adopție49
Fișiere (1)
- SKILL.md