Menu

AI AGENT SKILLS, IN THE OPEN

Testing skills

Test and debug software behavior.

39 repositories

  1. 1—
    zhaoxuya520/reverse-skill

    Reverse Engineering / Authorized Penetration Testing / Security Research Skill Router Pack AI-powered routing + On-demand toolchain bootstrapping + Self-evolving knowledge base Supports Claude Code, Kiro, Cursor, Cline, and other AI coding clients 逆向/渗透/安全技能路由包 - AI 自动路由 + 按需自举工具链 + 自动进化经验库 | 支持 Claude Code / Kiro / Cursor / Cline 等代码 AI 客户端

    6.0Network or broad shellActiveEngineering
    +0.9% over 7 days
    44.2kGitHub stars
  2. 2—
    mukul975/Anthropic-Cybersecurity-Skills

    817 structured cybersecurity skills for AI agents · Mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF & MITRE F3 (Fight Fraud) · agentskills.io standard · Works with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI & 20+ platforms · 29 security domains · Apache 2.0

    6.3Network or broad shellSlowingSecurity
    +1.1% over 7 days
    35.7kGitHub stars
  3. 3—
    h4ckf0r0day/obscura

    Operate and validate Obscura for JavaScript page loading, stealth browsing, anti-fingerprinting, tracker blocking, screenshots and visual comparison, CDP automation with Puppeteer or Playwright, screencasting, PDF export, MCP browser interaction, and web extraction. Use when running Obscura against

    7.9Network or broad shellActiveTesting
    +2.2% over 7 days
    30.4kGitHub stars
  4. 4—
    muratcankoylan/Agent-Skills-for-Context-Engineering

    A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require effective context management.

    6.1Network or broad shellActiveEngineering
    +0.3% over 7 days
    18.3kGitHub stars
  5. 5—
    jnMetaCode/superpowers-zh

    🦸 AI 编程超能力 · 中文增强版 — superpowers（250k+ ⭐）完整汉化 + 4 个中国原创 skills，让 Claude Code / Copilot CLI / Hermes Agent / Cursor / Windsurf / Kiro / Gemini CLI / Qoder 等 26 款 AI 编程工具真正会干活

    6.7Network or broad shellActiveTesting
    +0.7% over 7 days
    8.5kGitHub stars
  6. 6—
    op7418/guizang-social-card-skill

    Generate Guizang-style social card image sets, Live Photo motion cards, material-first Live Photo puzzle layouts, triple Live Photo collages, long-video-to-Live-Photo treatments, and WeChat official account cover pairs from articles, scripts, screenshots, product notes, subtitles, photos, or user-su

    7.2Network or broad shellActiveTesting
    +1.7% over 7 days
    8kGitHub stars
  7. 7▲
    Jakeschincariol/replica-skill

    Eleven free Claude skills that clone any app: reverse-engineer it, rebuild it, test it for bugs, then fix what its users hate. Free, MIT.

    7.4Network or broad shellActiveEngineering
    +17.4% over 7 days
    7.8kGitHub stars
  8. 8—
    alchaincyf/darwin-skill

    Darwin Skill 2.0 (达尔文.skill 2.0): autonomous skill optimizer, v2.0 integrates Microsoft Research SkillLens (arXiv 2605.23899) 9-dim rubric + SkillOpt (arXiv 2605.23904) validation-gated design + human-in-the-loop checkpoints. Evaluates SKILL.md files using a 9-dimension rubric (structure + effective

    6.1Network or broad shellActiveTesting
    +1.6% over 7 days
    6.8kGitHub stars
  9. 9—
    SawyerHood/dev-browser

    Browser automation with persistent named pages via the dev-browser CLI. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, log into sites, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take

    5.0Local scriptsActiveTesting
    +0.2% over 7 days
    6.7kGitHub stars
  10. 10▼
    kaankiziltug/logo-design-skill

    Professional logo and brand-mark design, from brief to production files. Guides discovery and the design brief, concept generation, choosing a mark type (wordmark, monogram, letterform, pictorial, abstract, emblem, mascot, combination), building clean geometric SVG logos, optical refinement, colour

    8.2Local scriptsActiveDesign
    +13.0% over 7 days
    6.1kGitHub stars
  11. 11▼
    awarexone/Agentic-Bug-Hunter

    AI-powered bug bounty hunting toolkit that works with or without subscription.

    7.3Network or broad shellActiveSecurity
    +2.6% over 7 days
    5.6kGitHub stars
  12. 12▼
    callstack/agent-device

    Open source device layer for AI coding agents: a CLI, MCP server, and typed Node.js API to control mobile, web, TV, and desktop apps on devices and simulators, locally or in the cloud.

    7.0Network or broad shellActiveTesting
    +1.6% over 7 days
    5.3kGitHub stars
  13. 13▼
    langwatch/langwatch

    Open-Source Agent Observability & Evals for AI Platform teams. Trace, test, route and govern every agent & coding assistant in the company.

    4.4Network or broad shellActiveData
    +0.3% over 7 days
    5kGitHub stars
  14. 14▲
    Manavarya09/design-extract

    Extract any website's complete design system with one command. DTCG tokens, semantic+primitive+composite, MCP server for Claude Code/Cursor/Windsurf, multi-platform emitters (iOS SwiftUI, Android Compose, Flutter, WordPress), Tailwind v4, Figma variables, shadcn/ui, CSS health audit, WCAG remediation, Chrome extension. MIT, Playwright, Node 20+.

    8.2Network or broad shellActiveDesign
    +8.4% over 7 days
    4.8kGitHub stars
  15. 15▼
    remorses/playwriter

    Chrome extension & CLI to let agents control your browser. Runs Playwright snippets in a stateful sandbox. Available as CLI or MCP

    5.6Network or broad shellActiveTesting
    +0.4% over 7 days
    4.1kGitHub stars
  16. 16—
    Netw0rkNoob/VulnClaw

    基于 AI Agent + MCP 工具链 + 渗透 Skill 编排， 配合大语言模型， 自然语言输入 → 自动完成「信息收集 → 漏洞发现 → 漏洞利用 → 报告生成」全流程。

    5.7Network or broad shellActiveSecurity
    +1.3% over 7 days
    3.9kGitHub stars
  17. 17▼
    CyberStrikeus/CyberStrike

    Open-source AI-powered offensive security harness for automated penetration testing.

    7.5Network or broad shellActiveOffensive securitySecurity
    +2.8% over 7 days
    3.4kGitHub stars
  18. 18▼
    lackeyjb/playwright-skill

    Complete browser automation with Playwright. Auto-detects dev servers, writes reusable test scripts, and supports screenshots, responsive checks, UX validation, login flows, link checks, and arbitrary browser automation. Use when the user wants to test a website, automate browser interactions, valid

    4.8Network or broad shellActiveEngineering
    +0.4% over 7 days
    3.3kGitHub stars
  19. 19▼
    addyosmani/web-quality-skills

    Agent Skills for optimizing web quality based on Lighthouse and Core Web Vitals.

    5.6Network or broad shellSlowingTesting
    +1.1% over 7 days
    3kGitHub stars
  20. 20▲
    Jakeschincariol/founder-skill

    Eleven free Claude skills that test a business before you launch it: a board trained on Hormozi, Thiel and Jobs, a marketing director, a CFO, and a consumer panel of 100 buyer agents. Free, MIT.

    7.4Local scriptsActiveMarketing
    +13.2% over 7 days
    2.5kGitHub stars
  21. 21▼
    antonbabenko/terraform-skill

    Use when writing, reviewing, or debugging Terraform/OpenTofu modules, tests, CI, scans, or state ops - diagnoses failure mode (identity churn, secrets, blast radius, CI drift, state corruption) with version-aware guards.

    5.9Network or broad shellActiveDevOps
    +0.6% over 7 days
    2.4kGitHub stars
  22. 22▼
    stas00/the-art-of-debugging

    Systematic methodology and concrete tool recipes for debugging Unix, Python, and PyTorch programs - crashes, hangs, segfaults, wrong output, CUDA OOM, NaN/Inf, slowness, and multi-node/multi-GPU issues. Use when a program crashes, hangs, deadlocks, segfaults, runs out of memory (OOM), produces NaN/I

    2.6Network or broad shellActiveTesting
    +0.1% over 7 days
    1.7kGitHub stars
  23. 23—
    daveebbelaar/bama

    BAMA: Build Any Mac App. Agent skills to research, clone, design, build, optimize, and test native macOS apps with Swift and SwiftUI.

    8.2Network or broad shellActiveDesign
    +66.5% over 7 days
    1.6kGitHub stars
  24. 24▼
    openclaw/crabbox

    Crabbox: warm a box, sync the diff, run the suite.

    4.3Network or broad shellActiveTesting
    +0.3% over 7 days
    1.5kGitHub stars
  25. 25—
    microsoft/waza

    CLI / Framework for Agent Skills - create, test, measure and improve skill quality and effectiveness

    4.2Network or broad shellActiveTesting
    +0.3% over 7 days
    1.5kGitHub stars
  26. 26—
    first-fluke/oh-my-agent

    Agent skills and specialist teams for Claude Code, Codex, Cursor and other coding agents. Load one skill or install domain presets, project hooks and parallel workflows with test gates.

    6.0Network or broad shellActiveEngineering
    +0.5% over 7 days
    1.4kGitHub stars
  27. 27▼
    uphiago/recon-skills

    Recon & pentest skill pack. CORS, XSS, SQLi, SSRF, RCE, WordPress, MCP, cloud, subdomain takeover, and more. Field-tested. MIT. Full write-up at hiago.sh

    4.2Network or broad shellSlowingOffensive securitySecurity
    +0.3% over 7 days
    1.3kGitHub stars
  28. 28—
    conorluddy/ios-simulator-skill

    Build, test, and drive iOS apps in the Simulator with 30 token-efficient scripts. Use when asked to build or test an Xcode project, launch an app on a simulator, tap/type/swipe through its UI by accessibility label, take screenshots or visual diffs, audit accessibility, read logs or diagnose hangs,

    5.2Network or broad shellActiveTesting
    +0.5% over 7 days
    1.3kGitHub stars
  29. 29▼
    xalgorix/xalgorix

    Autonomous AI pentesting agents — real-time reconnaissance, vulnerability detection, and exploitation orchestration. Go + TypeScript.

    6.9Network or broad shellActiveSecurity
    +2.0% over 7 days
    1.3kGitHub stars
  30. 30▼
    pashov/skills

    Pashov Audit Group Skills

    5.2Network or broad shellActiveSecurity
    +0.8% over 7 days
    1.3kGitHub stars
  31. 31▲
    NiazMorshed2007/reanimate

    Clone a section, widget, page or animation from any reference (a live website URL, a screen recording, an mp4/mov/webm, a gif, a Lottie file, a prototype export) frame by frame into the user's own codebase, then record the clone and verify it against the reference frame by frame, iterating until tim

    8.2Network or broad shellActiveTesting
    +1,119.2% over 7 days
    1.3kGitHub stars
  32. 32▼
    reticlehq/reticle

    AI agents can generate code, but still struggle to understand what they build. Reticle brings Jev-style machine-native runtime perception to web & desktop applications.

    1.2Network or broad shellActiveTesting
    -3.0% over 7 days
    1.2kGitHub stars
  33. 33▼
    Spark-To-Paper-Skills/paperjury

    Three modes for CS-conference papers (CVPR/ICCV/ECCV vision, ACL/EMNLP/NAACL NLP, ICLR/NeurIPS/ICML/AAAI ML). DIRECT-EDIT mode (common): the user describes a change in Chinese or English and the manuscript (LaTeX or Markdown) is edited directly through a CS-venue writing toolkit with author sign-off

    2.3Network or broad shellSlowingResearch
    +0.2% over 7 days
    1.2kGitHub stars
  34. 34▲
    Spielewoy/autoprompt-skill

    Autoprompt is a coding-agent skill that cuts failures by 45% on agentic coding tasks.

    1.8Network or broad shellActiveEngineering
    -0.8% over 7 days
    1.2kGitHub stars
  35. 35▼
    larlarua/AutoCVE

    Agent-driven automated CVE discovery platform for source code auditing, vulnerability verification, and report generation.

    2.2Network or broad shellActiveSecurity
    +0.2% over 7 days
    1.2kGitHub stars
  36. 36▼
    JuliusBrussee/cavekit

    Frozen — compressed spec-driven development plugin for Claude Code. Still works; active development moved to JuliusBrussee/caveman.

    2.7Instructions onlySlowingTesting
    +0.3% over 7 days
    1.2kGitHub stars
  37. 37▼
    massgen/MassGen

    🚀 MassGen is an open-source multi-agent scaling system that runs in your terminal, autonomously orchestrating frontier models and agents to collaborate, reason, and produce high-quality results. | Join us on Discord: discord.massgen.ai

    1.5Network or broad shellSlowingTesting
    +0.1% over 7 days
    1.1kGitHub stars
  38. 38▲
    HeyChengC/vibe-knowledge-film

    抖音「Vibe知识大赏」式的无旁白知识短片：2–5 分钟、16:9、没有人声，观众读底部一行字幕，同时看屏上把这句话演出来。 核心是讲解设计：给每个概念找一个外行认得的形象，画得像它本身（不用点、线、圈代替），句子里说到什么屏上就是什么、动词真的发生； 提问、命名、结论不硬配图。全片由代码逐帧画出（Canvas + seek(t) + Playwright + ffmpeg）。 内含四条参考片的逐句拆解、六种画法、找形象的方法、分镜表格式、两套外观、渲染引擎和合成配乐。 用户说"做一条 vibe 知识大赏的视频""像《信息论·惊奇之学》《运气的形状》《超常刺激》《自指》那样的片子""代码直出的

    7.8Network or broad shellActiveTesting
    +32.8% over 7 days
    1.1kGitHub stars
  39. 39—
    Kappaemme-git/codex-startup-pressure-test-skill

    Brutally evaluate and refine startup ideas with practical early-stage startup frameworks. Use when Codex is asked to pressure-test a startup idea, validate whether the problem is real, map competitors and current customer behavior, find the first 10 customers, define an MVP, create a 2-week launch p

    0.3Instructions onlySlowingTesting
    0.0% over 7 days
    995GitHub stars

Ranked by stars. Sponsorship never changes the order.

EngineeringDesignMarketingLegalFinanceOperationsSalesWritingDataDevOpsSecurityTestingDocumentationProductivityResearchEducationClaude CodeCodexCursorGemini CLIGitHub CopilotOpenCode
Back to top