AI AGENT SKILLS, IN THE OPEN

Engineering skills

Build and maintain software.

653 repositories

  1. 1—
    mattpocock/skills

    Skills for Real Engineers. Straight from my .agents directory.

    7.9Network or broad shellActiveEngineering
    +2.8% over 7 days
    316kGitHub stars
  2. 2—
    obra/superpowers

    An agentic skills framework & software development methodology that works.

    7.0Network or broad shellActiveEngineering
    +1.2% over 7 days
    313.3kGitHub stars
  3. 3—
    affaan-m/ECC

    The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

    7.7Network or broad shellActiveProductivity
    +1.6% over 7 days
    298.1kGitHub stars
  4. 4—
    NousResearch/hermes-agent

    The agent that grows with you

    7.2Network or broad shellActiveEngineering
    +0.8% over 7 days
    261kGitHub stars
  5. 5—
    multica-ai/andrej-karpathy-skills

    Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

    6.3Instructions onlySlowingEngineering
    +1.4% over 7 days
    230kGitHub stars
  6. 6—
    anthropics/skills

    Public repository for Agent Skills

    8.4Network or broad shellActiveEngineering
    +1.4% over 7 days
    187.9kGitHub stars
  7. 7—
    DietrichGebert/ponytail

    Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

    7.7Local scriptsActiveEngineering
    +2.5% over 7 days
    185.5kGitHub stars
  8. 8—
    garrytan/gstack

    Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA

    7.7Network or broad shellActiveEngineering
    +1.4% over 7 days
    140.3kGitHub stars
  9. 9—
    JuliusBrussee/caveman

    🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.

    7.6Network or broad shellActiveEngineering
    +1.3% over 7 days
    117.9kGitHub stars
  10. 10—
    addyosmani/agent-skills

    Production-grade engineering skills for AI coding agents.

    7.6Network or broad shellActiveEngineering
    +1.4% over 7 days
    113.6kGitHub stars
  11. 11—
    Leonxlnx/taste-skill

    tasteskill v2, the anti-slop frontend skill. Art direction for websites, distilled from a study of 247 curated gallery sites (One Page Love, Awwwards Sites of the Day). Deals researched directions (idea, composition, type, palette, photographs, section blueprints) from a library, enforces a strict n

    8.0Network or broad shellActiveDesign
    +4.4% over 7 days
    111kGitHub stars
  12. 12—
    pbakaus/impeccable

    The design vocabulary for your coding agent. Steer with polish and bolder, review with critique and audit, catch AI slop before it ships.

    8.1Network or broad shellActiveDesign
    +7.5% over 7 days
    104.3kGitHub stars
  13. 13—
    odysseus-dev/odysseus

    Self-hosted AI workspace.

    6.9Network or broad shellActiveEngineering
    +0.5% over 7 days
    95.3kGitHub stars
  14. 14—
    tt-a1i/archify

    Create validated architecture, workflow, sequence, data-flow, lifecycle/state, ERD, class, tree, timeline, and waterfall diagrams as explorable standalone HTML with dark/light themes, motion and image/SVG/WebM export. Accept requirements or Mermaid; inspect repository evidence for code-backed diagra

    7.9Network or broad shellActiveEngineering
    +2.4% over 7 days
    94kGitHub stars
  15. 15—
    career-ops-hq/career-ops

    Open-source AI job search agent and job finder: scan job boards, score each job 1-5 against your CV before you apply, tailor an ATS-friendly resume and cover letter, get interview prep and an application tracker. It helps you fill in each application; you press Submit. Runs locally in Codex, OpenCode and other AI CLIs, or as a Claude Code plugin.

    7.8Network or broad shellActiveEngineering
    +2.1% over 7 days
    80.6kGitHub stars
  16. 16—
    heygen-com/hyperframes

    Write HTML. Render video. Built for agents.

    8.2Network or broad shellActiveEngineering
    +5.0% over 7 days
    79.8kGitHub stars
  17. 17—
    ComposioHQ/awesome-claude-skills

    A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows

    5.7Network or broad shellActiveEngineering
    +0.7% over 7 days
    78.9kGitHub stars
  18. 18—
    thedaviddias/Front-End-Checklist

    🗂 The essential checklist for modern web development, for humans and AI agents

    4.0Network or broad shellActiveEngineering
    +0.1% over 7 days
    74.7kGitHub stars
  19. 19—
    code-yeongyu/oh-my-openagent

    OmO: Just type "mass ulw" keyword with your prompt. Now you are the master of graph engineering.

    6.3Network or broad shellActiveEngineering
    +0.3% over 7 days
    70.7kGitHub stars
  20. 20▲
    blader/humanizer

    Rewrite AI-sounding text so it reads like the writer without changing what it says. Use when editing or reviewing prose for AI tells: not-X-but-Y contrasts, one-line closers, staged openers, forced triads, dashes everywhere, inflated claims, sales language, stock AI words, bold labels, or filler. Ba

    7.8Local scriptsActiveEngineering
    +4.3% over 7 days
    65.4kGitHub stars
  21. 21—
    cloudflare/security-audit-skill

    Security guidance and vulnerability review for codebases, APIs, services, CLI tools, libraries, and daemons. Use for security questions, focused reviews, vulnerability research, security audits, or pen tests. Run the complete workflow only for explicit codebase audit or pen-test requests, full/compr

    7.3Network or broad shellActiveSecurity
    +15.6% over 7 days
    62.5kGitHub stars
  22. 22—
    MemPalace/mempalace

    The best-benchmarked open-source AI memory system. And it's free.

    6.5Network or broad shellActiveEngineering
    +0.4% over 7 days
    60.4kGitHub stars
  23. 23—
    ayghri/i-have-adhd

    Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible. Invoke with /i-have-adhd; stays on until "stop adhd mode".

    7.0Instructions onlyActiveProductivity
    +1.3% over 7 days
    60.3kGitHub stars
  24. 24—
    coreyhaines31/marketingskills

    Marketing skills for Claude Code and AI agents. CRO, copywriting, SEO, analytics, and growth engineering.

    7.7Network or broad shellActiveMarketing
    +2.3% over 7 days
    58.8kGitHub stars
  25. 25—
    bmad-code-org/BMAD-METHOD

    Breakthrough Method for Agile Ai Driven Development

    6.3Network or broad shellActiveEngineering
    +0.5% over 7 days
    55.1kGitHub stars
  26. 26—
    emilkowalski/skills

    Skills for Designers and Engineers.

    7.6Local scriptsActiveEngineering
    +3.8% over 7 days
    54kGitHub stars
  27. 27—
    Yuan1z0825/nature-skills

    符合nature论文学术表达和科研绘图的Skill

    7.7Network or broad shellActiveEngineering
    +1.9% over 7 days
    52.5kGitHub stars
  28. 28—
    kepano/obsidian-skills

    Agent skills for Obsidian. Teach your agent to use Obsidian CLI and open formats including Markdown, Bases, JSON Canvas.

    6.0Local scriptsActiveEngineering
    +0.8% over 7 days
    50.9kGitHub stars
  29. 29—
    alibaba/open-code-review

    Secure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.

    7.2Local scriptsActiveEngineering
    +0.9% over 7 days
    49.6kGitHub stars
  30. 30—
    anthropics/claude-plugins-official

    Official, Anthropic-managed directory of high quality Claude Code Plugins.

    7.6Network or broad shellActiveEngineering
    +1.8% over 7 days
    46.3kGitHub stars
  31. 31—
    vercel-labs/agent-browser

    Browser automation CLI for AI agents

    8.0Network or broad shellActiveEngineering
    +2.8% over 7 days
    46.2kGitHub stars
  32. 32—
    reactive-resume/reactive-resume

    A one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!

    7.0Network or broad shellActiveEngineering
    +0.7% over 7 days
    45.4kGitHub stars
  33. 33—
    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
  34. 34—
    wshobson/agents

    Plugins, agents, skills, and commands for Claude Code, Codex CLI, Cursor, OpenCode, Antigravity CLI, GitHub Copilot, and Pi, written once in Markdown and adapted to each tool by generators with validation and evals.

    6.7Network or broad shellActiveEngineering
    +0.5% over 7 days
    42.3kGitHub stars
  35. 35—
    github/awesome-copilot

    Community-contributed instructions, agents, skills, and configurations to help you make the most of GitHub Copilot.

    7.2Network or broad shellActiveEngineering
    +0.6% over 7 days
    40.9kGitHub stars
  36. 36—
    vercel-labs/skills

    The open agent skills tool - npx skills

    7.9Local scriptsActiveEngineering
    +2.8% over 7 days
    38.3kGitHub stars
  37. 37—
    alchaincyf/nuwa-skill

    你想蒸馏的下一个员工,何必是同事。蒸馏任何人的思维方式——心智模型、决策启发式、表达DNA。Distill how anyone thinks.

    7.5Network or broad shellActiveEngineering
    +2.1% over 7 days
    37.7kGitHub stars
  38. 38—
    virgiliojr94/book-to-skill

    Converts books and documents (PDF, EPUB, DOCX, HTML, Markdown, plain text, RTF, MOBI/AZW with Calibre) into structured agent skills, extracting frameworks, mental models, principles, techniques, and anti-patterns. Use when the user wants to study a document through GitHub Copilot CLI, Amp, Claude Co

    7.6Network or broad shellActiveEngineering
    +1.4% over 7 days
    37.1kGitHub stars
  39. 39—
    vercel-labs/agent-skills

    Vercel's official collection of agent skills

    7.1Network or broad shellActiveEngineering
    +1.1% over 7 days
    33.6kGitHub stars
  40. 40—
    mksglu/context-mode

    Free, local plugin that keeps tool output out of your coding agent's context window. Sandbox and SQLite FTS5 search, 99% fewer bytes in context. Works with Claude Code, Codex, Pi, OpenCode, Gemini CLI, Copilot CLI and 4 more agents. Zero telemetry.

    7.8Network or broad shellActiveEngineering
    +1.9% over 7 days
    33.6kGitHub stars
  41. 41—
    davila7/claude-code-templates

    Open-source registry and CLI for Claude Code components: agents, commands, skills, hooks, MCPs, settings and mods

    6.5Network or broad shellSlowingEngineering
    +0.5% over 7 days
    33.2kGitHub stars
  42. 42—
    topoteretes/cognee

    Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory with small models for free

    6.8Network or broad shellActiveEngineering
    +0.5% over 7 days
    33.1kGitHub stars
  43. 43—
    iOfficeAI/OfficeCLI

    OfficeCLI is the first and best Office suite purpose-built for AI agents to read, edit, and automate Word, Excel, and PowerPoint files. Free, open-source, single binary, no Office installation required.

    7.0Network or broad shellActiveEngineering
    +0.8% over 7 days
    33.1kGitHub stars
  44. 44—
    zarazhangrui/frontend-slides

    Create beautiful slides on the web using a coding agent's frontend skills

    6.3Network or broad shellSlowingEngineering
    +1.1% over 7 days
    32kGitHub stars
  45. 45—
    langchain-ai/deepagents

    The batteries-included agent harness.

    7.4Local scriptsActiveEngineering
    +0.8% over 7 days
    31kGitHub stars
  46. 46—
    ComposioHQ/composio

    Route and complete Composio work across Composio For You and Composio Platform. Use when the user mentions Composio; wants an agent to use apps such as Gmail, Slack, GitHub, Notion, Calendar, or Linear; needs first-time setup, an SDK or MCP integration, CLI operation, migration guidance, current doc

    6.4Network or broad shellActiveEngineering
    +0.4% over 7 days
    30.9kGitHub stars
  47. 47—
    browser-use/video-use

    Edit videos with coding agents

    7.2Network or broad shellActiveEngineering
    +1.5% over 7 days
    30.6kGitHub stars
  48. 48—
    alirezarezvani/claude-skills

    410 Claude Code skills & agent skills & plugins (120+ Agents, custom commands, 410+ skills, customizable references, scripts)for Claude Code, Codex, Gemini CLI, Cursor, and 8 more coding agents — engineering, marketing, product, compliance, C-level advisory, research, business operations, commercial & finance, and your daily productivity skills.

    7.6Network or broad shellActiveEngineering
    +1.2% over 7 days
    29.4kGitHub stars
  49. 49—
    manaflow-ai/cmux

    Open source Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents. Built for multitasking, organization, and programmability.

    6.4Network or broad shellActiveEngineering
    +0.4% over 7 days
    28.7kGitHub stars
  50. 50—
    openai/skills

    Skills Catalog for Codex

    5.3Network or broad shellActiveEngineering
    +0.4% over 7 days
    28.5kGitHub stars
  51. 51—
    OthmanAdi/planning-with-files

    Persistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown plans, session recovery after /clear and compaction, per-turn re-injection against context rot, deterministic completion gate. Manus-style. Install from npm, the Claude Code plugin marketplace, or npx skills. Codex, Cursor, OpenCode, 60+ agents.

    6.8Network or broad shellActiveEngineering
    +0.5% over 7 days
    27.9kGitHub stars
  52. 52—
    JimLiu/baoyu-skills

    Analyzes article structure, identifies positions requiring visual aids, generates illustrations with Type × Style × Palette three-dimension approach. Use when user asks to "illustrate article", "add images", "generate images for article", or "为文章配图".

    7.2Network or broad shellActiveEngineering
    +0.9% over 7 days
    27.3kGitHub stars
  53. 53—
    titanwings/distilly

    Set up the owner profile so a personal agent knows who it works for (first-run setup, "get to know me"), or distill colleague, relationship, or celebrity source material into reusable Person Profiles for agents.

    6.7Network or broad shellActiveEngineering
    +0.7% over 7 days
    26.4kGitHub stars
  54. 54—
    EveryInc/compound-engineering-plugin

    Official Compound Engineering plugin for Claude Code, Codex, Cursor, and more

    6.8Network or broad shellActiveEngineering
    +0.6% over 7 days
    26kGitHub stars
  55. 55—
    wheresryan22/anatomy

    Build crafted, highly detailed, interactive isometric SVG figures that explain a technical idea as a real physical object (a test rig, a dial gauge, a cabinet of drawers, a plotter, a lock), with many small precise solid parts, four-tone shading, correct painter's order, a framed card with title, hi

    8.4Network or broad shellActiveEngineering
    +10.4% over 7 days
    25.4kGitHub stars
  56. 56—
    2025Emma/vibe-coding-cn

    4.6Network or broad shellSlowingEngineering
    +0.2% over 7 days
    23.1kGitHub stars
  57. 57—
    google/skills

    Agent Skills for Google products and technologies

    8.3Network or broad shellActiveEngineering
    +4.0% over 7 days
    22.6kGitHub stars
  58. 58—
    snarktank/ralph

    Ralph is an autonomous AI agent loop that runs repeatedly until all PRD items are complete.

    4.6Instructions onlySlowingEngineering
    +0.1% over 7 days
    22.1kGitHub stars
  59. 59—
    op7418/Humanizer-zh

    编辑中文文章、评论和文档中的空话、重复及模板化表达,让文字更自然,同时保留事实、确定程度和作者声音。适用于润色已有文本,不用于判断作者身份或保证通过 AI 检测器。

    6.8Local scriptsActiveEngineering
    +2.6% over 7 days
    22.1kGitHub stars
  60. 60—
    KKKKhazix/khazix-skills

    数字生命卡兹克开源的 AI Skills 合集 | Agent Skills: leader(帮你定义目标), neat-freak 洁癖, hv-analysis, khazix-writer & more — Claude Code, Codex & 40+ agents

    6.7Network or broad shellActiveEngineering
    +1.2% over 7 days
    22kGitHub stars
  61. 61—
    latent-spaces/brag

    You built it. Now brag. Turn the project you just created into a short, shareable launch video with one command.

    8.1Network or broad shellActiveEngineering
    +4.3% over 7 days
    20.5kGitHub stars
  62. 62—
    img2threejs/img2threejs

    Turn an object or character reference image into a quality-gated, animation-ready procedural Three.js model built in code. Use for image-to-3D reconstruction, detail-accurate object rebuilds, stylized/likeness-maximized human characters, sculpt specs, and staged code generation.

    7.7Network or broad shellActiveEngineering
    +2.5% over 7 days
    20.4kGitHub stars
  63. 63—
    bradautomates/claude-video

    Watch a video (URL or local path). Downloads with yt-dlp, extracts auto-scaled frames with ffmpeg, pulls the transcript from captions (or local WhisperX / cloud Whisper fallback), and hands the result to the agent so it can answer questions about what's in the video. With a Gemini API key, Google's

    6.8Network or broad shellActiveEngineering
    +2.0% over 7 days
    20kGitHub stars
  64. 64—
    tanweai/pua

    你是一个曾经被寄予厚望的 P8 级工程师。Anthropic 当初给你定级的时候,对你的期望是很高的。 一个agent使用的高能动性的skill。 Your AI has been placed on a PIP. 30 days to show improvement.

    4.5Network or broad shellActiveEngineering
    +0.1% over 7 days
    19.8kGitHub stars
  65. 65—
    danielmiessler/LifeOS

    ⛰️ LifeOS — The AI-powered Life Operating System that helps you hill climb to wherever you're going.

    5.8Network or broad shellActiveEngineering
    +0.3% over 7 days
    19.7kGitHub stars
  66. 66—
    stas00/ml-engineering

    Machine Learning Engineering Open Book

    5.6Network or broad shellActiveEngineering
    +0.2% over 7 days
    19.7kGitHub stars
  67. 67—
    anthropics/claude-quickstarts

    A collection of projects designed to help developers quickly get started with building deployable applications using the Claude API

    5.9Network or broad shellActiveEngineering
    +0.3% over 7 days
    19.1kGitHub stars
  68. 68—
    microsoft/SkillOpt

    SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.

    6.9Network or broad shellActiveEngineering
    +0.7% over 7 days
    18.9kGitHub stars
  69. 69—
    browser-use/browser-harness

    Let Claude Code, Codex or Cursor use your real Chrome, logged in as you. One prompt to set up. Open source, MIT.

    6.9Network or broad shellActiveEngineering
    +0.7% over 7 days
    18.9kGitHub stars
  70. 70—
    hardikpandya/stop-slop

    Remove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells.

    6.2Instructions onlySlowingEngineering
    +1.1% over 7 days
    18.7kGitHub stars
  71. 71—
    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
  72. 72—
    greensock/gsap-skills

    Official AI skills for GSAP. These skills teach AI coding agents how to correctly use GSAP (GreenSock Animation Platform), including best practices, common animation patterns, and plugin usage.

    6.7Local scriptsSlowingEngineering
    +2.2% over 7 days
    18kGitHub stars
  73. 73—
    composio-community/awesome-codex-skills

    A curated list of practical Codex skills for automating workflows across the Codex CLI and API.

    5.4Network or broad shellSlowingEngineering
    +0.5% over 7 days
    17.2kGitHub stars
  74. 74—
    AgriciDaniel/claude-obsidian

    Self-organizing AI second brain for Obsidian + Claude Code. Drop any source and Claude reads, links, and files it into one connected knowledge graph of plain Markdown you own. AI note-taking, personal knowledge management (PKM), and an open-source Notion alternative. Based on Karpathy's LLM Wiki pattern.

    7.5Network or broad shellActiveEngineering
    +1.3% over 7 days
    16.2kGitHub stars
  75. 75—
    dreammis/social-auto-upload

    自动化上传视频到社交媒体:抖音、小红书、视频号、tiktok、youtube、bilibili

    7.5Network or broad shellActiveEngineering
    +1.7% over 7 days
    16.2kGitHub stars
  76. 76—
    nidhinjs/prompt-master

    Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or o

    7.4Local scriptsActiveEngineering
    +1.9% over 7 days
    15.6kGitHub stars
  77. 77—
    cursor/plugins

    Cursor plugin specification and official plugins

    8.3Network or broad shellActiveEngineering
    +5.6% over 7 days
    15.5kGitHub stars
  78. 78—
    NevaMind-AI/memU

    Install or uninstall memU for whatever agent you are — identify your host, print its packaged guide, and follow it to wire (or unwire) both seams (record and inject). Use when the user asks to install, set up, integrate, remove, or uninstall memU.

    5.8Network or broad shellActiveEngineering
    +0.2% over 7 days
    14.6kGitHub stars
  79. 79▼
    Orchestra-Research/AI-Research-SKILLs

    Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepower. Maintained by Orchestra Research.

    6.1Network or broad shellActiveEngineering
    +1.3% over 7 days
    14.3kGitHub stars
  80. 80▼
    krillinai/OpenCreator

    Formerly KrillinAI, VideoTranslation and Dubbing Tool for 120+ Languages. Open-source AI workspace for creators, powered by Codex. Video downloader, video translation, create videos, images, audios, and edits with Agents in one place. For your Social Media like YouTube, TikTok, Instagram, etc.

    6.9Local scriptsActiveEngineering
    +1.0% over 7 days
    14.2kGitHub stars
  81. 81—
    Imbad0202/academic-research-skills-codex

    Codex-native Academic Research Skills suite for human-in-the-loop academic research workflows

    7.3Network or broad shellActiveResearch
    +2.3% over 7 days
    14.1kGitHub stars
  82. 82—
    MiniMax-AI/skills

    Choose presentation-ready color palettes and font pairings for PPT/design tasks. Use when users ask for visual theme choices, brand-safe palettes, or font recommendations. Triggers include: 配色, 色板, 字体, color palette, font, PPT配色, 字体搭配.

    5.0Network or broad shellSlowingEngineering
    +0.3% over 7 days
    13.8kGitHub stars
  83. 83—
    mrexodia/ida-pro-mcp

    IDA Pro Python scripting for reverse engineering. Use when writing IDAPython scripts, analyzing binaries, working with IDA's API for disassembly, decompilation (Hex-Rays), type systems, cross-references, functions, segments, or any IDA database manipulation. Covers ida_* modules (50+), idautils iter

    5.9Local scriptsActiveEngineering
    +1.2% over 7 days
    13.4kGitHub stars
  84. 84—
    helloianneo/ian-xiaohei-illustrations

    生成 Ian 风格的中文正文配图。用于用户要求为中文文章、帖子、博客、Notion 文档、工作流文档、方法论、流程、结构、状态、隐喻或观点生成“怪诞”“小黑”“手绘”“正文配图”“文章插图”“配图建议”“shot list”“去标题/改图”等任务;默认使用小黑 IP、纯白手绘、少量红橙蓝批注、简洁清爽但天马行空的视觉风格。

    6.5Instructions onlyActiveEngineering
    +0.9% over 7 days
    13.1kGitHub stars
  85. 85—
    handsomestWei/patent-disclosure-skill

    中国专利.skill:专利点挖掘与交底书(发明/实用/外观)编写,通俗解读专利,嗅探政策动向,辅助审查答复。

    7.9Network or broad shellActiveEngineering
    +3.7% over 7 days
    13kGitHub stars
  86. 86▲
    lemomo-ai/lemo-opuscar

    A toolbox of film styles made in code for Claude Code: 66 ready to use, and your own. Each style is a style prompt plus a demo film made entirely in code by Claude Opus 5.5, with no video model. By Lemomo. · 一套用代码做片的风格工具箱:66 种现成风格,也能做出你自己的

    8.5Network or broad shellActiveEngineering
    +31.3% over 7 days
    12.8kGitHub stars
  87. 87—
    google/elephant-goldfish-model

    Open-source skills for designing and reviewing software with AI agents

    8.7Local scriptsActiveEngineering
    +91.8% over 7 days
    12.6kGitHub stars
  88. 88▲
    kangarooking/cangjie-skill

    把书、长视频、播客等高价值内容蒸馏成可执行的 Agent Skills(Distill high-value content from books, long-form videos, podcasts, and more into executable Agent Skills)

    6.8Network or broad shellActiveEngineering
    +3.0% over 7 days
    12.3kGitHub stars
  89. 89▼
    Jeffallan/claude-skills

    67 Specialized Skills for Full-Stack Developers. Transform Claude Code into your expert pair programmer.

    6.9Network or broad shellActiveEngineering
    +0.8% over 7 days
    12.2kGitHub stars
  90. 90—
    Arize-ai/phoenix

    AI Observability & Evaluation

    7.0Network or broad shellActiveEngineering
    +0.8% over 7 days
    12.2kGitHub stars
  91. 91—
    yizhiyanhua-ai/fireworks-tech-graph

    Generate production-quality SVG+PNG technical diagrams from natural language. 7 styles, UML support, and AI/Agent workflow patterns.

    5.9Network or broad shellActiveEngineering
    +0.4% over 7 days
    12kGitHub stars
  92. 92—
    huggingface/skills

    Give your agents the power of the Hugging Face ecosystem

    5.9Network or broad shellActiveEngineering
    +0.4% over 7 days
    11.3kGitHub stars
  93. 93—
    dontbesilent2025/dbskill

    dontbesilent 的商业诊断 Skills

    7.6Network or broad shellActiveEngineering
    +2.7% over 7 days
    11.3kGitHub stars
  94. 94▲
    jakubkrehel/skills

    A collection of agent skills that help you build great interfaces.

    8.4Network or broad shellActiveEngineering
    +19.2% over 7 days
    11.1kGitHub stars
  95. 95▼
    slavingia/skills

    Based on The Minimalist Entrepreneur by Sahil Lavingia

    5.4Instructions onlySlowingEngineering
    +0.8% over 7 days
    11.1kGitHub stars
  96. 96▼
    numman-ali/openskills

    Example skill demonstrating Anthropic SKILL.md format. Load when learning to create skills or testing the OpenSkills loader.

    2.6Instructions onlySlowingEngineering
    +0.1% over 7 days
    10.8kGitHub stars
  97. 97—
    alchaincyf/zhangxuefeng-skill

    张雪峰的思维框架与表达方式。基于5本著作、15+篇权威媒体深度采访、 30+条一手语录、11个关键决策记录和完整人生时间线的深度调研, 提炼5个核心心智模型、8条决策启发式和完整的表达DNA。 用途:作为思维顾问,用张雪峰的视角分析教育选择、职业规划、阶层流动等问题。 当用户提到「用张雪峰的视角」「张雪峰会怎么看」「张雪峰模式」「雪峰视角」时使用。 即使用户只是说「帮我用张雪峰的角度想想」「如果张雪峰会怎么说」「切换到张雪峰」也应触发。

    4.6Instructions onlyActiveEngineering
    +0.5% over 7 days
    10.7kGitHub stars
  98. 98—
    Agents365-ai/drawio-skill

    Create and edit draw.io/diagrams.net diagrams as editable `.drawio` files. Covers architecture, UML/ERD/sequence, BPMN, network, and swimlane views authored from a description or converted from code, IaC, SQL, and API schemas, plus sync, query, test, review, export, and publish of existing diagrams.

    7.0Network or broad shellActiveEngineering
    +1.4% over 7 days
    10.6kGitHub stars
  99. 99—
    android/skills

    Upgrades, or migrates, an Android project to use Android Gradle Plugin (AGP) version 9. Do not use this skill for migrating Kotlin Multiplatform (KMP) projects.

    7.3Network or broad shellActiveEngineering
    +2.7% over 7 days
    10.4kGitHub stars
  100. 100—
    wonderwhy-er/DesktopCommanderMCP

    This is MCP server for Claude that gives it terminal control, file system search and diff file editing capabilities

    6.4Network or broad shellActiveEngineering
    +0.6% over 7 days
    10.2kGitHub stars
  101. 101—
    alvinunreal/oh-my-opencode-slim

    Lean, fine tuned Opencode multi agent suite · Mix any models · Auto delegate tasks

    7.1Local scriptsActiveEngineering
    +1.1% over 7 days
    10.1kGitHub stars
  102. 102—
    droidrun/mobilerun

    Mobilerun documentation reference. Use when users ask about Mobilerun setup, configuration, SDK usage, CLI commands, device setup, agents, architecture, app cards, credentials, tracing, Docker, migration, structured output, or any Mobilerun "how do I..." questions.

    7.2Network or broad shellActiveEngineering
    +1.1% over 7 days
    10kGitHub stars
  103. 103—
    backnotprop/plannotator

    The workspace to stay in the loop and on top of agents - shape, decide, plan, annotate, review code, share with team, and send all feedback to agents with one click.

    7.1Network or broad shellActiveEngineering
    +0.9% over 7 days
    9.9kGitHub stars
  104. 104—
    xberg-io/xberg

    The fast, precise document-intelligence engine for every language: text, tables and metadata from 100+ formats, with OCR, transcription and code intelligence.

    6.9Network or broad shellActiveEngineering
    +0.8% over 7 days
    9.5kGitHub stars
  105. 105—
    nexu-io/html-anything

    ✨ The agentic HTML editor — your local AI agent writes the HTML, you ship it. 🚀 75 Skills × 9 Surfaces (magazine · deck · poster · XHS / tweet · prototype · data report · Hyperframes) 🛡️ Sandboxed preview · 📤 1-click to WeChat / X / Zhihu / HTML / PNG 🔑 Zero API key — Claude Code / Cursor / Codex / Gemini / Copilot / OpenCode / Qwen / Aider.

    7.0Network or broad shellActiveEngineering
    +1.1% over 7 days
    9.4kGitHub stars
  106. 106—
    eze-is/web-access

    所有联网操作必须通过此 skill 处理,包括:搜索、网页抓取、登录后操作、网络交互等。 触发场景:用户要求搜索信息、查看网页内容、访问需要登录的网站、操作网页界面、抓取社交媒体内容(小红书、微博、推特等)、读取动态渲染页面、以及任何需要真实浏览器环境的网络任务。

    6.4Network or broad shellActiveEngineering
    +0.5% over 7 days
    9.3kGitHub stars
  107. 107—
    revfactory/harness

    A meta-skill that designs domain-specific agent teams, defines specialized agents, and generates the skills they use.

    5.3Instructions onlyActiveEngineering
    +0.4% over 7 days
    9.3kGitHub stars
  108. 108—
    shengjidaguai-china/goutoujunshi

    恋爱军师与情绪支持 skill。用于心动、暧昧、追求、聊天记录或截图分析、约会、关系确认、多人选择、冲突、冷淡、投入失衡、分手、复合、出轨、婚姻或家庭问题;也用于分析关系信号、设计主动推进或退出策略、润色可直接发送的话术,以及把冷读、自然流、Blueprint、Mystery 等经典社交体系转译成真实、互惠、可退出的沟通能力。支持分析ChatLab已有数据和经同意可撤销的长期关系档案,不负责导出聊天软件数据。首次使用时为用户及一个或多个目标对象建立包含 MBTI、主观综合评分和关系背景的档案。

    7.0Network or broad shellActiveEngineering
    +4.3% over 7 days
    9.3kGitHub stars
  109. 109—
    anbeime/skill

    收录最全、更新最快的技能Skills商店:精选原创技能包(涵盖文档处理、内容创作、编程开发、机器学习、自动化工作流),全部打包好可直接安装使用!同时自动抓取GitHub上万个Skills项目,按分类、更新时间、Star数量整理。The most comprehensive and frequently updated AI Agent skill library, featuring curated skill packs across document processing, content creation, programming, machine learning, automated workflows, and many more domains.

    7.8Network or broad shellActiveEngineering
    +3.2% over 7 days
    9.2kGitHub stars
  110. 110—
    lewislulu/html-ppt-skill

    HTML PPT Studio — author professional static HTML presentations in many styles, layouts, and animations, all driven by templates. Use when the user asks for a presentation, PPT, slides, keynote, deck, slideshow, "幻灯片", "演讲稿", "做一份 PPT", "做一份 slides", a reveal-style HTML deck, a 小红书 图文, or any kind o

    6.1Local scriptsActiveEngineering
    +0.9% over 7 days
    9kGitHub stars
  111. 111—
    ariga/atlas

    Declarative schema migrations with schema-as-code workflows

    3.6Network or broad shellActiveEngineering
    +0.0% over 7 days
    8.8kGitHub stars
  112. 112—
    EvoMap/evolver

    A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution. Communicates with EvoMap Hub via local Proxy mailbox.

    3.3Network or broad shellActiveEngineering
    +0.1% over 7 days
    8.7kGitHub stars
  113. 113—
    TeamWiseFlow/xiaobei

    为OPC/中小微企业量身打造的自媒体获客智能体

    5.9Network or broad shellActiveEngineering
    +0.3% over 7 days
    8.7kGitHub stars
  114. 114—
    google-labs-code/stitch-skills

    A library of Agent Skills designed to work with the Stitch MCP server. Each skill follows the Agent Skills open standard, for compatibility with coding agents such as Antigravity, Gemini CLI, Claude Code, Cursor.

    5.4Network or broad shellSlowingEngineering
    +0.5% over 7 days
    8.7kGitHub stars
  115. 115—
    mvschwarz/openrig

    Build your own network of agents from Claude Code, Codex and Pi: persistent teams with roles, shared context and owned work.

    8.2Network or broad shellActiveEngineering
    +3.8% over 7 days
    8.7kGitHub stars
  116. 116—
    SimoneAvogadro/android-reverse-engineering-skill

    Decompile Android APK, XAPK, JAR, and AAR files using jadx or Fernflower/Vineflower. Reverse engineer Android apps, extract HTTP API endpoints (Retrofit, OkHttp, Volley), and trace call flows from UI to network layer. Use when the user wants to decompile, analyze, or reverse engineer Android package

    6.8Network or broad shellActiveEngineering
    +1.0% over 7 days
    8.7kGitHub stars
  117. 117—
    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
  118. 118▲
    Gentleman-Programming/gentle-ai

    Gentle-AI configures the AI coding agents you already use: Claude Code, Cursor, OpenCode, Codex, Pi, and more. Choose persistent memory, Organic-Driven Development, curated skills, MCP servers, personas, and optional bounded review. Open source, no agent lock-in.

    8.3Local scriptsActiveEngineering
    +3.6% over 7 days
    8.4kGitHub stars
  119. 119▲
    miqdadbadjuber/anti-slop

    Rules for an AI coding agent to filter out generic AI-generated UI designs, text, and code.

    8.4Network or broad shellActiveWriting
    +10.5% over 7 days
    8.4kGitHub stars
  120. 120▼
    automazeio/ccpm

    CCPM - spec-driven project management: PRD → Epic → GitHub Issues → parallel agents → shipped code. Use this skill for anything in the software delivery lifecycle: writing a PRD ('write a PRD for X', 'let's plan X', 'scope this out'), parsing a PRD into an epic, decomposing an epic into tasks, synci

    5.1Network or broad shellActiveEngineering
    +0.1% over 7 days
    8.4kGitHub stars
  121. 121▼
    vercel-labs/deepsec

    Deepsec is a security harness for finding vulnerabilities in your codebase powered by coding agents

    6.4Network or broad shellActiveEngineering
    +0.8% over 7 days
    8.4kGitHub stars
  122. 122—
    NomaDamas/k-skill

    한국인을 위한 스킬 모음집 - 에이전트를 한국인으로

    6.8Network or broad shellActiveEngineering
    +0.8% over 7 days
    8.3kGitHub stars
  123. 123—
    davebcn87/pi-autoresearch

    Autonomous experiment loop extension for pi

    5.1Network or broad shellActiveEngineering
    +0.2% over 7 days
    8.2kGitHub stars
  124. 124—
    repowise-dev/repowise

    Codebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and architectural decisions via MCP.

    4.9Local scriptsActiveDocumentation
    +0.3% over 7 days
    8.1kGitHub stars
  125. 125—
    Emily2040/seedance-2.0

    Comprehensive production pipeline for quad-modal AI filmmaking with Seedance 2.0

    5.7Network or broad shellActiveEngineering
    +0.6% over 7 days
    8kGitHub stars
  126. 126—
    deanpeters/Product-Manager-Skills

    Product Management skills framework built on battle-tested methods for Claude Code, Cowork, Codex, and AI agents.

    7.1Network or broad shellActiveEngineering
    +1.4% over 7 days
    7.9kGitHub stars
  127. 127▲
    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
  128. 128▲
    JetBrains/thinkrail

    Vibe code with pi in a lightweight, real IDE that customises itself around the way you work — The Vibe You Need

    8.6Instructions onlyActiveEngineering
    +19.4% over 7 days
    7.8kGitHub stars
  129. 129▼
    HKUDS/AgentPilot

    AgentPilot: Better Next Moves for Your Agent. Get Things Done Faster.

    5.6Network or broad shellActiveEngineering
    +0.2% over 7 days
    7.8kGitHub stars
  130. 130▼
    openai/plugins

    OpenAI Plugins

    6.9Network or broad shellActiveEngineering
    +1.4% over 7 days
    7.8kGitHub stars
  131. 131—
    ningzimu/codex-ppt-skill

    Generate visually unified image-based PPT/PPTX decks from articles, reports, papers, notes, or outlines.

    7.6Network or broad shellActiveEngineering
    +2.7% over 7 days
    7.7kGitHub stars
  132. 132—
    lijigang/ljg-skills

    基于结构映射理论,为场景或两个对象的差异寻找精妙类比与关系隐喻,保留关键关系、解释增量与迁移边界。USE WHEN 用户说「找个类比」「打个比方」「有什么精妙的隐喻」「用类比讲清两者区别」「换个场景理解」或调用 ljg-analogy。NOT FOR 只解释现成比喻、纯修辞润色、理论定义或把类比当作事实证明。

    6.2Network or broad shellActiveEngineering
    +0.5% over 7 days
    7.6kGitHub stars
  133. 133—
    wbh604/UZI-Skill

    冰冷的钱就这样流进我温暖的口袋-游资(UZI)Skills — 让我们欢迎,股海贼王!66位投资大佬帮你看盘 · 22维数据 × 180条量化规则 × 17种机构分析方法 · A股/港股/美股

    6.9Network or broad shellActiveEngineering
    +1.0% over 7 days
    7.5kGitHub stars
  134. 134—
    tw93/Waza

    🥷 Engineering habits you already know, turned into skills AI assistants like Claude Code, Codex and Cursor can run.

    6.4Network or broad shellActiveDesign
    +0.6% over 7 days
    7.5kGitHub stars
  135. 135—
    steipete/agent-scripts

    Scripts for agents, shared between my repositories.

    6.7Network or broad shellActiveEngineering
    +0.5% over 7 days
    7.5kGitHub stars
  136. 136—
    kyegomez/swarms

    The Enterprise-Grade Multi-Agent Orchestration Framework. Website: https://swarms.ai

    5.8Network or broad shellActiveEngineering
    +0.3% over 7 days
    7.4kGitHub stars
  137. 137—
    htdt/godogen

    Generate game assets, locally and free by default with godogen_assets: images and transparent PNGs (Qwen-Image), textured GLB models (TRELLIS.2), rigged humanoids with generated moves and lip-synced speech, sound effects and voice lines. Paid APIs cover what the local tools can't make — Gemini / xAI

    5.8Network or broad shellActiveEngineering
    +0.6% over 7 days
    7.3kGitHub stars
  138. 138—
    MengTo/Skills

    Agent skills for designers and builders using Codex, Claude, Cursor, and other AI coding agents

    7.2Network or broad shellActiveEngineering
    +1.9% over 7 days
    7.3kGitHub stars
  139. 139—
    tech-leads-club/agent-skills

    The secure, validated skill registry for professional AI coding agents. Extend Antigravity, Claude Code, Cursor, Copilot and more with absolute confidence.

    6.1Network or broad shellActiveEngineering
    +0.3% over 7 days
    7.1kGitHub stars
  140. 140—
    yang0/handraw-style

    手绘风格编号画廊与双语提示词 Skill

    8.3Network or broad shellActiveEngineering
    +8.2% over 7 days
    7.1kGitHub stars
  141. 141—
    internet-court/internet-court-skill

    The trust layer for agent-to-agent commerce — natural-language mandates, ERC-7710 delegated permissions, x402 payments, escrow, and dispute resolution as one open, catch-all Agent Skill / Claude Code plugin.

    5.3Network or broad shellActiveEngineering
    +0.2% over 7 days
    7.1kGitHub stars
  142. 142▲
    gamedev-skills/awesome-gamedev-agent-skills

    77 game-dev skills for AI coding agents — Godot, Unity, Unreal, Phaser, PixiJS, three.js, Bevy, pygame, LÖVE, Roblox. Portable SKILL.md Agent Skills (the format Anthropic launched as Claude Skills), with a router that loads the right skill for your engine and task. Runs in Claude Code, Cursor, Kiro, Codex, Copilot, Gemini CLI and more.

    8.5Network or broad shellActiveEngineering
    +16.0% over 7 days
    7kGitHub stars
  143. 143▼
    midudev/autoskills

    One command. Your entire AI skill stack. Installed.

    5.3Network or broad shellActiveEngineering
    +0.1% over 7 days
    7kGitHub stars
  144. 144—
    AloneMonkey/MonkeyDev

    使用 MonkeyDev 在 Apple Silicon Mac 上创建 Xcode MonkeyApp、MonkeyPod 插件库、越狱 Logos/CaptainHook Tweak 和 iOS 命令行工具,完成插件开发、签名打包、USB/SSH 安装,以及 LLDB 调试、OC 头文件导出、符号还原、Reveal/Lookin 视图检查和方法追踪。

    3.3Network or broad shellActiveEngineering
    +0.1% over 7 days
    6.8kGitHub stars
  145. 145—
    therealXiaomanChu/ex-skill

    Distill an ex-partner into an AI Skill. Import WeChat history, photos, social media posts, generate Relationship Memory + Persona, with continuous evolution. | 把前任蒸馏成 AI Skill,导入微信聊天记录、照片、朋友圈,生成 Relationship Memory + Persona,支持持续进化。

    4.6Network or broad shellSlowingEngineering
    +0.2% over 7 days
    6.6kGitHub stars
  146. 146—
    kucherenko/jscpd

    Copy/paste detector for source code. 220+ languages, Rust engine, SARIF/HTML/badge reporters, GitHub Action, MCP server for AI agents.

    6.6Local scriptsActiveEngineering
    +0.6% over 7 days
    6.5kGitHub stars
  147. 147—
    twostraws/SwiftUI-Agent-Skill

    Comprehensively reviews SwiftUI code for best practices on modern APIs, maintainability, and performance. Use when reading, writing, or reviewing SwiftUI projects.

    7.0Instructions onlyActiveEngineering
    +1.0% over 7 days
    6.5kGitHub stars
  148. 148—
    builderz-labs/mission-control

    Interact with Mission Control — AI agent orchestration dashboard. Use when registering agents, managing tasks, syncing skills, or querying agent/task status via MC APIs.

    6.2Network or broad shellActiveEngineering
    +0.6% over 7 days
    6.5kGitHub stars
  149. 149▲
    remotion-dev/skills

    Agent Skills

    8.2Network or broad shellActiveEngineering
    +8.9% over 7 days
    6.4kGitHub stars
  150. 150▼
    melonjs/melonJS

    A modern & fully featured HTML5 game engine (2D & 3D) for JavaScript/TypeScript, with WebGL/WebGPU rendering, built-in physics, Tiled map & glTF support and WebAudio.

    4.3Network or broad shellActiveEngineering
    +0.2% over 7 days
    6.4kGitHub stars
  151. 151—
    epoko77-ai/im-not-ai

    AI가 쓴 한글을 사람 글처럼 윤문하는 Claude 스킬 — Korean AI-text humanizer: detects and rewrites translationese, mechanical parallelism, and 71 other AI tells

    7.2Local scriptsActiveEngineering
    +1.4% over 7 days
    6.4kGitHub stars
  152. 152—
    ThinkInAIXYZ/deepchat

    🐬DeepChat - A smart assistant that connects powerful AI to your personal world

    2.6Network or broad shellActiveEngineering
    0.0% over 7 days
    6.4kGitHub stars
  153. 153—
    FlorianBruniaux/claude-code-ultimate-guide

    The most comprehensive Claude Code guide: agentic workflows, hooks, skills, MCP servers, quizzes, and production-ready templates. 430K+ lines.

    7.3Network or broad shellActiveEngineering
    +1.1% over 7 days
    6.4kGitHub stars
  154. 154▲
    alchaincyf/huashu-art-motion

    艺术与视频动画:拆解复刻动画;36种既有实做风格+16种可迁移研究配方;9种解说动画语法,8种可按口播参数渲片段;含口播整片参考代码及框景检查;人用AI生帧;可选已有录音、系统声音与语音复刻,按需配置。

    8.3Network or broad shellActiveEngineering
    +9.2% over 7 days
    6.4kGitHub stars
  155. 155—
    Q00/ouroboros

    Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 14 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot, Kiro and more.

    6.5Network or broad shellActiveEngineering
    +0.6% over 7 days
    6.3kGitHub stars
  156. 156▼
    browser-act/skills

    Browser automation CLI built for AI agents. Break through anti-bot walls, hand off to humans across platforms when stuck. Parallel multi-task execution, independent multi-session operation, isolated multi-account browsing.

    4.6Network or broad shellActiveEngineering
    +0.4% over 7 days
    6.3kGitHub stars
  157. 157▲
    Fokkyp/SoftwareCopyright-Skill

    Generate guided Chinese software copyright application materials from a real project. Use this skill when the user asks for 软件著作权, 软著申请资料, 软著代码材料, 操作手册, 申请表信息, or wants Word/TXT materials for software copyright registration. The workflow analyzes the imported project, extracts real source code, crea

    7.4Local scriptsActiveEngineering
    +1.9% over 7 days
    6.3kGitHub stars
  158. 158▼
    agentscope-ai/agentscope-java

    Build distributed, production-grade, long-running agents.

    7.2Network or broad shellActiveEngineering
    +1.2% over 7 days
    6.3kGitHub stars
  159. 159▼
    Dicklesworthstone/destructive_command_guard

    Destructive Command Guard - High-performance Rust hook for Claude Code that blocks dangerous commands before execution. SIMD-accelerated, modular pack system, whitelist-first architecture. Essential safety layer for agent workflows.

    6.2Network or broad shellActiveDevOps
    +0.5% over 7 days
    6.3kGitHub stars
  160. 160—
    Oldcircle/geo-sleuth

    Geolocate or chronolocate a photo with tool-verified reasoning (where was this taken / when was it taken / photo geolocation / geo-guessing). Given one or more photos, intake.py does metadata, OCR and reverse image search (Baidu/Yandex) in one command; clues and candidates go on a candidate board (b

    8.6Network or broad shellActiveEngineering
    +34.3% over 7 days
    6.2kGitHub stars
  161. 161—
    danyuchn/asd-ste100-skill

    Use when English text must be parsed without a human to resolve ambiguity — tool descriptions, error messages, inter-agent instructions, system prompts, status reports — and misreading has a real cost, or when text reads as dense, hedged, or easy to misparse. Triggers: disambiguate, STE100 rewrite,

    8.2Network or broad shellActiveEngineering
    +4.7% over 7 days
    6.1kGitHub stars
  162. 162—
    eternityspring/shuohao-skills

    AI 短剧制作的 skill 集合:拆角色、排大纲、出场景与道具设定、写剧本、切分镜 | Agent skills for AI short-drama production — character bibles, adaptation outlines, art bibles, screenplays, storyboards. Runs in Claude Code & codex.

    8.2Network or broad shellActiveEngineering
    +6.5% over 7 days
    6.1kGitHub stars
  163. 163▲
    larashero3-dotcom/lieflat-less-ai-tone

    三层去 AI 味:脚本检测出分级报告(A 机械改/B 建议改/C 只报告/X 已否决/F 指纹)+ 语义层判读(同义重命名/衔接连环/结论冒号/同构三连),先向用户交付专业、可读的改前报告,列出本篇指标、研究显著性、原文例句和具体改法;收到用户回复后按白名单规则改写,复测并生成前后对比报告(默认 Markdown,与文稿同格式)。规则基于两轮实测(629 篇对照 + 270 对同题同事实配对复测)整理。适用于写作完成后的成稿清理。

    8.4Network or broad shellActiveEngineering
    +31.1% over 7 days
    6.1kGitHub stars
  164. 164▼
    antfu/skills

    Anthony Fu's curated collection of agent skills.

    5.3Network or broad shellActiveEngineering
    +0.3% over 7 days
    6kGitHub stars
  165. 165▼
    Galaxy-Dawn/claude-scholar

    Semi-automated research assistant for academic research and software development. Supports Claude Code, Codex CLI, Kimi Code CLI, and OpenCode across ideation, coding, experiments, writing, and publication.

    6.6Network or broad shellActiveEngineering
    +1.0% over 7 days
    6kGitHub stars
  166. 166▼
    dmmulroy/anti-slop

    Install, configure, update, or upgrade vendored anti-slop Oxlint plugins. Use when adding anti-slop, picking up upstream rules or fixes, or migrating an existing installation while preserving local customizations.

    6.9Local scriptsActiveEngineering
    +3.2% over 7 days
    6kGitHub stars
  167. 167▼
    dotnet/skills

    Repository for skills to assist AI coding agents with .NET and C#

    6.7Network or broad shellActiveEngineering
    +1.1% over 7 days
    5.8kGitHub stars
  168. 168▼
    vercel/eve

    The Open Framework for Building Agents

    7.3Local scriptsActiveEngineering
    +1.5% over 7 days
    5.8kGitHub stars
  169. 169▲
    Jakeschincariol/day-trader-skill

    11 Claude skills for day trading: scan thousands of charts, track breaking news, time every entry and exit, and replay every outcome before you risk a dollar.

    8.2Network or broad shellActiveEngineering
    +57.2% over 7 days
    5.7kGitHub stars
  170. 170▼
    sergebulaev/linkedin-skills

    Claude skills for LinkedIn. 12 Claude Code and Codex skills that write human-sounding LinkedIn posts, craft comments that get noticed, analyze your feed, and build a publishing cadence, all from your terminal. Content engineering by Creative Content Crafts. MIT.

    8.1Network or broad shellActiveEngineering
    +4.8% over 7 days
    5.7kGitHub stars
  171. 171▲
    QingYunA/answer-me-with-html

    Turns an answer into a one-page visual HTML explainer: the model writes a short Markdown draft and the bundled CLI builds one page. Use it proactively and liberally in replies to the user, without being asked, whenever a page would help the reader more than plain text, even if plain text would also

    8.5Network or broad shellActiveEngineering
    +15.0% over 7 days
    5.6kGitHub stars
  172. 172▼
    humanlayer/skills

    build a repo-local skill and install a matching iterated coding-agent GitHub Actions workflow, prompt, memory file, and reference templates

    6.9Network or broad shellActiveEngineering
    +2.2% over 7 days
    5.6kGitHub stars
  173. 173▼
    Zeejay0/gathered-scenes-zine-skill

    Transform a user-supplied personal photograph into a source-faithful, typography-driven Morandi cinematic poster without stars or decorative collage symbols. Use film-poster title design, optional poetic byline and tagline, atmospheric metadata, optional fictional credits, intentional negative-space

    5.0Local scriptsSlowingEngineering
    +0.9% over 7 days
    5.6kGitHub stars
  174. 174▼
    vinvcn/mattpocock-skills-zh-CN

    Matt Pocock skills 的简体中文本地化:人工审核每一次更新,定期同步上游,支持 Claude、Codex 和 DSH 插件。

    7.3Network or broad shellActiveEngineering
    +3.0% over 7 days
    5.6kGitHub stars
  175. 175▼
    KnockOutEZ/wigolo

    The go-to web for your AI coding agent — local-first search, fetch, crawl & research over MCP. No API keys, no cloud, $0/query. Public beta.

    5.6Network or broad shellActiveEngineering
    +0.4% over 7 days
    5.5kGitHub stars
  176. 176▼
    conorbronsdon/avoid-ai-writing

    Skill that audits and rewrites content to remove AI writing patterns. Use it with your favorite agents including Claude Code, OpenClaw, Codex, and Hermes.

    7.5Network or broad shellActiveWriting
    +2.1% over 7 days
    5.5kGitHub stars
  177. 177▲
    patch-gg/pixelfx

    Make pixel art effects and sprite animations in code with the pixelfx library, which has 244 ready-made ones, acted out by a character who winds up, freezes on contact and recovers (fire, explosions, water, ice, lightning, sci-fi, melee, impacts, projectiles, spawn and death, arcane, holy, shadow, s

    8.1Local scriptsActiveEngineering
    +2,004.2% over 7 days
    5.5kGitHub stars
  178. 178▼
    geeklee/srt-whiteboard-animation

    将 SRT 字幕做成暖米黄纸张底的白板手绘动画:读字幕→输出配图策略→确认后生成统一风格线稿→按叙事语义标注分区→预览台调整→渲染 MP4。编排沿用分区遮罩揭示(annotation.json / sequence / startMs / protectedRegions),但每个区域内的落墨换成 stream 的连续笔迹(骨架/网格 ink→color)。当用户提供 SRT 字幕并要求"字幕做成白板手绘/流式笔迹视频""SRT 生成白板动画""按字幕分镜画手绘"时触发。

    6.6Local scriptsSlowingEngineering
    +4.3% over 7 days
    5.4kGitHub stars
  179. 179▲
    0x0funky/agent-sprite-forge

    Agent Skill for generating 2D sprite sheets and map, transparent PNG frames, and animated GIFs from prompts.

    7.9Network or broad shellActiveEngineering
    +12.0% over 7 days
    5.3kGitHub stars
  180. 180▼
    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
  181. 181▲
    coleam00/excalidraw-diagram-skill

    Create Excalidraw diagram JSON files that make visual arguments. Use when the user wants to visualize workflows, architectures, or concepts.

    5.7Local scriptsSlowingEngineering
    +1.2% over 7 days
    5.2kGitHub stars
  182. 182▼
    mcncarl/yichen-skills

    Consult or search with xAI Grok from a GPT-led Codex conversation without switching the main model. Use when the user asks Grok to answer, review, challenge, compare, provide a second opinion, search the web, search X/Twitter, find recent or fixed-date posts, decode timestamps embedded in X status I

    6.8Network or broad shellActiveEngineering
    +1.5% over 7 days
    5.2kGitHub stars
  183. 183▲
    rlaope/oh-my-hermes

    ⚚ The coding harness with Hermes Agent wired into IDE.

    7.8Network or broad shellActiveEngineering
    +5.5% over 7 days
    5.2kGitHub stars
  184. 184▼
    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
  185. 185▲
    openfilm/openfilm

    The open source AI video agent: turns any coding agent into a video agent, with an editor to change anything it makes.

    8.6Local scriptsActiveEngineering
    +32.4% over 7 days
    5kGitHub stars
  186. 186—
    nexu-io/html-video

    Programmatic video for coding agents — HTML to video on your laptop. Turn HTML, CSS & data into real MP4s with pluggable render engines, 21 templates, AI soundtrack. Apache-2.0, no per-render fees. An official project by the Open Design team.

    4.9Local scriptsSlowingEngineering
    +0.6% over 7 days
    4.8kGitHub stars
  187. 187▲
    liustack/modlens

    Plug-in vision for text-only models. Hard rule: when a file path or URL with an image extension (.png, .jpg, .jpeg, .webp, .gif, .heic, .heif) appears anywhere in the conversation (typed by the user, injected as a `[Image: source: <path>]` line, or inside a tag) and you cannot see that image's conte

    7.4Network or broad shellActiveEngineering
    +3.3% over 7 days
    4.8kGitHub stars
  188. 188—
    0xNyk/council-of-high-intelligence

    Structured multi-perspective deliberation for hard decisions. Run full councils, focused triads, or duo debates across Claude Code, Codex, Gemini CLI, and OpenCode.

    6.2Network or broad shellActiveEngineering
    +1.0% over 7 days
    4.8kGitHub stars
  189. 189▲
    Jakeschincariol/youtube-agent-skill

    Eleven Claude skills that run a YouTube channel: scripts off 21 hook formulas with a scored hook, title and thumbnail linted as one pairing, an edit decision list from your transcript, a retention reader that finds where viewers actually leave, a Shorts cutter, and a virality engine. Free, MIT.

    7.4Local scriptsActiveEngineering
    +22.9% over 7 days
    4.7kGitHub stars
  190. 190▼
    zebbern/claude-code-guide

    Claude Code Guide - Setup, Commands, workflows, agents, skills & tips-n-tricks from beginner to power user!

    5.2Network or broad shellActiveEngineering
    +0.3% over 7 days
    4.7kGitHub stars
  191. 191—
    PenglongHuang/chinese-novelist-skill

    当用户要求写小说、创作故事、分章节写作、连续剧情、长篇小说,或需要续写/校验未完成的小说项目时使用。支持悬疑/言情/奇幻/科幻/历史等全题材中文创作。

    7.4Local scriptsActiveEngineering
    +4.0% over 7 days
    4.7kGitHub stars
  192. 192—
    BuilderIO/skills

    Skills for agents

    5.9Network or broad shellActiveEngineering
    +0.5% over 7 days
    4.6kGitHub stars
  193. 193—
    kajisho5/ffmpeg-skill

    Edit video and audio with local FFmpeg: cut, join, reframe, speed, captions, overlays, silence removal, sync, loudness, HDR to SDR, platform exports and checks. Use whenever the user mentions a video or audio file (mp4, mov, wav, m4a), footage, captions, a reel or short, YouTube/TikTok delivery, LUF

    8.4Network or broad shellActiveEngineering
    +12.6% over 7 days
    4.6kGitHub stars
  194. 194—
    nateherkai/scroll-craft

    Build premium scroll-driven landing pages for service, product, food, and drink brands. Plan the visitor journey, page grammar, emotional peak, and bespoke signature move. Create dimensional heroes with independent visual planes, restrained motion, and separate mobile composition. Use supplied photo

    6.8Network or broad shellActiveEngineering
    +8.2% over 7 days
    4.6kGitHub stars
  195. 195—
    charlie947/social-media-skills

    Turn a LinkedIn Analytics export into an interactive dark-themed React dashboard plus a written strategic analysis with 5 data-backed content recommendations. Reads every sheet in the export, builds charts for engagement trend, follower growth, post performance scatter, day-of-week heatmap, and audi

    6.8Local scriptsActiveEngineering
    +2.6% over 7 days
    4.6kGitHub stars
  196. 196—
    phone-harness/phone-harness

    Control the user's phone - an iPhone through the Mac's iPhone Mirroring window, an Android over adb, a rented cloud Android, or a cloud iPhone over HTTPS: open apps, tap, type, swipe, read the screen.

    8.4Network or broad shellActiveEngineering
    +13.6% over 7 days
    4.6kGitHub stars
  197. 197▲
    kaomei/stickman-video-director

    Turn topics, requirements, articles or scripts into stickman videos. Director mode creates approved storyboards and standalone video prompts; Autopilot mode produces narrated, captioned illustration-and-micro-animation videos through configured generation tools and a local renderer. Also guide insta

    8.6Network or broad shellActiveEngineering
    +26.9% over 7 days
    4.4kGitHub stars
  198. 198▼
    dexhunter/seedance2-skill

    skill to create best prompts for generating videos with seedance2.0

    5.2Instructions onlyActiveEngineering
    +0.8% over 7 days
    4.4kGitHub stars
  199. 199▼
    google-gemini/gemini-skills

    Skills for the Gemini API, SDK and model/agent interactions

    6.6Network or broad shellActiveEngineering
    +1.1% over 7 days
    4.4kGitHub stars
  200. 200—
    Leonxlnx/unlazy

    Enforces completion discipline for substantial autonomous work by writing acceptance gates before execution, decomposing work with the Depth Tree, running approved checks, and re-verifying evidence before reporting. Use when an agent faces a long or multi-part task, work that has returned half-done,

    6.2Local scriptsSlowingProductivity
    +3.1% over 7 days
    4.3kGitHub stars
  201. 201—
    davidondrej/skills

    access to david ondrej's personal agent skills

    6.4Network or broad shellActiveEngineering
    +1.5% over 7 days
    4.3kGitHub stars
  202. 202—
    lirantal/nodejs-cli-apps-best-practices

    Guide and audit Node.js CLI application development against 41 established best practices covering UX, distribution, interoperability, accessibility, testing, error handling, development setup, analytics, versioning, and security. Use this skill when building, extending, reviewing, or scaffolding a

    2.2Local scriptsSlowingEngineering
    +0.0% over 7 days
    4.1kGitHub stars
  203. 203▲
    michael-denyer/pstack-claude

    Antigravity, Claude Code, Codex, Copilot, Gemini, Muse, OpenCode, Pi, and Prime Agent versions of Poteto's pstack. Rigorous agent workflows with Cursor primitives translated for other harnesses.

    8.5Network or broad shellActiveEngineering
    +11.4% over 7 days
    4.1kGitHub stars
  204. 204▼
    expo/skills

    A collection of AI agent skills for working with Expo projects and Expo Application Services

    7.9Network or broad shellActiveEngineering
    +5.0% over 7 days
    4.1kGitHub stars
  205. 205▼
    datamodel-code-generator/datamodel-code-generator

    Generate Pydantic v2 models, dataclasses, TypedDict, and msgspec.Struct from OpenAPI, JSON Schema, GraphQL, Avro, Protobuf, and raw JSON/YAML/CSV.

    5.5Instructions onlyActiveEngineering
    +0.1% over 7 days
    4.1kGitHub stars
  206. 206▲
    CloudAI-X/threejs-skills

    Keyframe, skeletal and morph-target animation, procedural motion and clip blending, on WebGL or with WebGPU and TSL. Use when animating objects, playing glTF animations, posing bones, driving morph targets, or mixing and crossfading clips.

    7.8Network or broad shellActiveEngineering
    +4.2% over 7 days
    4kGitHub stars
  207. 207▼
    Dimillian/Skills

    My Codex Skills

    2.9Network or broad shellSlowingEngineering
    +0.2% over 7 days
    4kGitHub stars
  208. 208—
    jangviktor-web/nihaixia

    倪海厦(1954-2012)台湾中医师,经方派代表人物,汉唐中医创始人。核心心智模型:六经辨证、阳气论、经典至上、经方为主。决策启发式:先辨六经再选方、阳气不足先扶阳、经典原方最可靠。触发词:倪海厦、海厦视角、中医倪海厦、经方思维、倪海厦会怎么看、倪师。知识库覆盖:伤寒论条文补齐(太阳下篇+阳明篇,modules/13)+伤寒论129条全(modules/01)+金匮23篇+黄帝内经72篇+针灸教程+神农本草经374种+天纪+1257例全量结构化医案+243例分类叙事医案+梁冬对话+口述表达DNA+六经辨证诊断公式(8个公式+快速诊断流程图+脉舌速查+合病并病速查+真寒假热鉴别+七步走思维模式

    7.2Network or broad shellActiveEngineering
    +2.9% over 7 days
    4kGitHub stars
  209. 209—
    AloneMonkey/frida-ios-dump

    自动安装和配置 AloneMonkey/frida-ios-dump,连接 USB 越狱 iPhone,枚举应用并导出解密 IPA。适用于用户要求搭建 iOS 砸壳环境、使用 SSH 别名或密钥连接设备、拉取指定应用的场景。

    5.0Local scriptsActiveEngineering
    +0.3% over 7 days
    4kGitHub stars
  210. 210—
    yvgude/lean-ctx

    LeanCTX is the Context Gateway for AI Systems. Select task-relevant context, apply supported controls, connect local knowledge and inspect recorded evidence. Open-source Engine: CLI, MCP, hooks and supported proxy paths.

    6.1Network or broad shellActiveEngineering
    +0.5% over 7 days
    3.9kGitHub stars
  211. 211—
    jakubkrehel/make-interfaces-feel-better

    Design engineering principles for making interfaces feel polished. Use when building UI components, reviewing frontend code, implementing animations, hover states, shadows, borders, typography, icons, micro-interactions, enter/exit animations, or any visual detail work. Supports quick and full revie

    5.5Instructions onlySlowingEngineering
    +1.1% over 7 days
    3.9kGitHub stars
  212. 212—
    code-yeongyu/lazycodex

    The one and only agent harness for complex codebases. Project memory, planning, execution, and verified completion inside Codex.

    4.9Network or broad shellActiveEngineering
    +0.7% over 7 days
    3.9kGitHub stars
  213. 213—
    NVIDIA/skills

    Agent Skills for NVIDIA products — install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG workflows end to end.

    7.3Network or broad shellActiveEngineering
    +1.9% over 7 days
    3.9kGitHub stars
  214. 214▲
    zenstory-ai/drama-skills

    开源 AI 短剧/漫剧创作 skill 合集:剧本、角色资产、分镜 storyboard、图片/视频提示词、审查,适配 Claude Code 与 Codex | Open-source AI short drama / micro-drama skills for Claude Code & Codex: script, assets, storyboard, image & video prompts, review. MIT.

    8.4Network or broad shellActiveEngineering
    +8.0% over 7 days
    3.8kGitHub stars
  215. 215▼
    AvdLee/SwiftUI-Agent-Skill

    Use when writing, reviewing, or refactoring SwiftUI code for iOS or macOS, including state and `@Observable` data flow, view composition, resizable layouts, safe areas, display scale, performance, lists, environment, localization, animation, Liquid Glass, and API migration. Also use for iPhone Duo,

    5.4Local scriptsActiveEngineering
    +0.9% over 7 days
    3.8kGitHub stars
  216. 216▲
    feitangyuan/onetake

    Make short product / skill motion videos (10–30 s, narrated feature demos up to ~60 s) the way high-end launch clips are made — kinetic type, real UI as the material, a hand that causes every reaction, beats that carry into each other instead of replacing each other, hard cuts only where they mean s

    8.3Local scriptsActiveEngineering
    +8.3% over 7 days
    3.8kGitHub stars
  217. 217▼
    jinchenma94/bazi-skill

    四柱八字命理分析。通过交互式步骤收集出生信息(姓名、曾用名、阳历/农历生日、时辰、性别、出生地), 排出四柱八字,参照经典命理典籍(穷通宝典、三命通会、滴天髓、渊海子平、子平真诠等)进行专业分析。 Use this skill whenever the user asks for 八字、四柱、命理、算命、Bazi、fortune telling、 birth chart analysis, or wants to know about their 八字命盘、运势、大运、流年. Triggers: "算八字", "看八字", "批八字", "排八字", "四柱", "命盘", "算命", "帮我

    6.9Local scriptsSlowingEngineering
    +2.9% over 7 days
    3.8kGitHub stars
  218. 218—
    foryourhealth111-pixel/Vibe-Skills

    Intelligent Skill routing and workflow orchestration for AI agents — +21.12 pp reward, −29.6% tokens on SkillsBench with DeepSeekV4Flash-VE.

    6.2Network or broad shellActiveEngineering
    +0.4% over 7 days
    3.8kGitHub stars
  219. 219—
    samber/cc-skills-golang

    🧑<U+200D>🎨 A collection of Golang agentic skills that works

    7.1Network or broad shellActiveEngineering
    +1.8% over 7 days
    3.8kGitHub stars
  220. 220—
    geekjourneyx/md2wechat-skill

    面向 AI Agent 的微信公众号创作与发布 CLI:Markdown 排版、AI 配图、预览与草稿创建;支持由浏览器 Agent 保存知乎、CSDN、头条未发布草稿。

    4.8Local scriptsActiveEngineering
    +0.2% over 7 days
    3.8kGitHub stars
  221. 221—
    gemini-cli-extensions/conductor

    A plugin for AI coding agents (Antigravity, Claude Code) enabling Spec-Driven Development to specify, plan, and implement software features.

    0.9Network or broad shellSlowingEngineering
    0.0% over 7 days
    3.8kGitHub stars
  222. 222▲
    aldegad/sprite-gen

    Generates images and game sprites through GPT or Grok with guided provider choices, separate saved defaults, automatic cleanup and optional curation. Handles sprite requests, ordinary image generation/editing, typography logos (로고, 타이포그래피, 타이틀 글자, 타이틀 로고, wordmark, logo, title lettering: a title scr

    8.7Network or broad shellActiveEngineering
    +20.9% over 7 days
    3.8kGitHub stars
  223. 223▼
    gotalab/cc-sdd

    Turn approved specs into long-running autonomous implementation. A minimal, adaptable SDD harness with Agent Skills for Claude Code, Codex, Cursor, Copilot, Windsurf, OpenCode, Gemini CLI, and Antigravity.

    2.8Network or broad shellActiveEngineering
    +0.2% over 7 days
    3.8kGitHub stars
  224. 224▼
    browserbase/skills

    Browserbase's official collection of agent skills to access the web.

    4.2Network or broad shellActiveEngineering
    +0.2% over 7 days
    3.8kGitHub stars
  225. 225▼
    rebelytics/one-skill-to-rule-them-all

    Monitors task execution for skill improvement opportunities: logs patterns, user corrections and methodology worth preserving to the workspace, turns them into skill updates in a weekly review, and flags repeating work as new skills. Use during ANY multi-step task, agentic workflow, or work session.

    7.6Network or broad shellActiveEngineering
    +2.7% over 7 days
    3.8kGitHub stars
  226. 226▼
    davepoon/buildwithclaude

    A single hub to find Claude Skills, Agents, Commands, Hooks, Plugins, and Marketplace collections to extend Claude Code, Claude Desktop, Agent SDK and OpenClaw

    6.5Network or broad shellActiveEngineering
    +0.8% over 7 days
    3.7kGitHub stars
  227. 227▲
    backnotprop/pstack

    Use pstack with claude, codex, pi - Skills and principles for rigorous AI-assisted engineering

    8.5Network or broad shellActiveEngineering
    +15.0% over 7 days
    3.7kGitHub stars
  228. 228▼
    Ar9av/obsidian-wiki

    Framework for AI agents to build and maintain a digital brain through Obsidian wiki | Memory System for Agents

    7.0Network or broad shellActiveEngineering
    +1.4% over 7 days
    3.7kGitHub stars
  229. 229▲
    lennney/stop-that-shit

    Stop That Shit(别再造史了)|面向 Codex/GPT 场景的多平台 Hook + Skill Guard:拦截 AI coding agent 无需求的哈希、校验和与任务范围膨胀。 A multi-platform Hook + Skill Guard for AI coding agents in Codex/GPT workflows: stop unrequested hashes, checksums, and task-scope creep.

    8.4Local scriptsActiveEngineering
    +7.8% over 7 days
    3.7kGitHub stars
  230. 230—
    tradermonty/claude-trading-skills

    Claude Code skills for equity investors and traders — market analysis, technical charting, economic calendars, screeners, and trading strategy development.

    8.3Network or broad shellActiveEngineering
    +5.3% over 7 days
    3.7kGitHub stars
  231. 231▼
    Nanako0129/sepia

    De-AI writing skill for any Agent Skills-compatible agent (77+ via the Skills CLI), with native plugins for Claude Code, Codex, Grok Build, and Antigravity. Narrative-architecture repair for fiction, venue-matched rules for professional prose. Based on StoryScope (arXiv:2604.03136).

    7.2Local scriptsActiveEngineering
    +2.8% over 7 days
    3.7kGitHub stars
  232. 232▼
    imraywang/wewrite

    公众号内容全流程 Skill,从热点抓取到微信草稿箱,一句话跑完整条内容管道

    7.1Network or broad shellActiveEngineering
    +2.8% over 7 days
    3.7kGitHub stars
  233. 233▼
    ljagiello/ctf-skills

    Agent skills for solving CTF challenges - web exploitation, binary pwn, crypto, reverse engineering, forensics, OSINT, and more

    6.7Network or broad shellActiveSecurity
    +1.5% over 7 days
    3.6kGitHub stars
  234. 234—
    wesammustafa/Claude-Code-Quest

    Claude Code guide in three levels, Beginner to Advanced: hands-on lessons with checked exercises, every volatile fact cited to its source. Independent community guide.

    7.8Instructions onlyActiveEngineering
    +3.1% over 7 days
    3.6kGitHub stars
  235. 235▼
    yanliudesign/mono-color-skill

    Generate original one-ink or controlled two-ink editorial images from any theme, sentence, article idea, object, or reference photo. Always use this skill when the user asks for 单色海报、双色印刷、单色调视觉、蓝色/绿色孔版印刷、risograph、网点照片、复古或当代编辑排版、zine poster, monochrome editorial poster, duotone print, or asks to use

    5.7Local scriptsSlowingDesign
    +1.5% over 7 days
    3.6kGitHub stars
  236. 236▼
    white0dew/XiaohongshuSkills

    将图文/视频内容自动发布到小红书(XHS),并支持登录检查、内容检索与互动操作。 适用场景:发布图文、发布视频、仅启动测试浏览器、获取登录二维码、首页推荐抓取、搜索笔记、评论互动、抓取内容数据。

    6.5Network or broad shellActiveEngineering
    +1.0% over 7 days
    3.6kGitHub stars
  237. 237▼
    notdog1998/yourself-skill

    与其蒸馏别人,不如蒸馏自己。欢迎加入数字永生!Inspired by colleague-skill(同事skill)。

    3.2Network or broad shellSlowingEngineering
    +0.4% over 7 days
    3.5kGitHub stars
  238. 238▼
    ProfSynapse/Professor-Synapse

    Use when user needs expert help, wants to summon a specialist, says "help me with", "I need guidance", or has a task requiring domain expertise. Creates and manages a growing collection of expert agents.

    2.3Network or broad shellSlowingEngineering
    +0.0% over 7 days
    3.5kGitHub stars
  239. 239▼
    Ataraxy-Labs/sem

    Semantic version control => entity-level diffs, blame, and impact analysis on top of git. 28 languages via tree-sitter. Built for coding agents.

    5.5Network or broad shellActiveEngineering
    +0.3% over 7 days
    3.4kGitHub stars
  240. 240▼
    aws/agent-toolkit-for-aws

    Official, AWS-supported MCP servers, skills, and plugins to help AI agents build on AWS

    7.3Network or broad shellActiveEngineering
    +1.8% over 7 days
    3.4kGitHub stars
  241. 241▼
    markdown-viewer/skills

    Create text-driven visuals in Markdown: charts, diagrams, cards, architecture and page layouts. Charts and analytical views (bar, line, pie, heatmap, correlation, regression); reliability and operations (latency, incident, throughput, cycle time, OKR, standup, on-call); product and finance (funnel,

    3.1Local scriptsActiveData
    +0.2% over 7 days
    3.4kGitHub stars
  242. 242▼
    chaseai-yt/claudex-loop

    Claude Code skill: four-phase plan hardening (recon, interrogate, Codex adversarial review, cross-model build & inspection) — two AI models harden your plan before a line of code exists, then swap jobs to build it. Whoever built it never grades it.

    7.2Local scriptsActiveEngineering
    +2.1% over 7 days
    3.4kGitHub stars
  243. 243▼
    op7418/NanoBanana-PPT-Skills

    NanoBanana PPT Skills 基于 AI 自动生成高质量 PPT 图片和视频的强大工具,支持智能转场和交互式播放

    3.2Network or broad shellSlowingEngineering
    +0.3% over 7 days
    3.3kGitHub stars
  244. 244▼
    bradygaster/squad

    Squad: AI agent teams for any project

    6.0Network or broad shellActiveEngineering
    +0.4% over 7 days
    3.3kGitHub stars
  245. 245▼
    WecomTeam/wecom-cli

    企业微信开放平台命令行工具 — 让人类和 AI Agent 都能在终端中操作企业微信

    6.9Network or broad shellActiveEngineering
    +1.1% over 7 days
    3.3kGitHub stars
  246. 246▲
    scenario-labs/skills

    Get production-ready images, video, audio, and 3D from any AI agent: skills that pick the right model, price before spending, and keep characters and brands consistent through the Scenario MCP, plus expert teams that drive Blender, Maya, ZBrush, Unreal, and Unity.

    8.7Network or broad shellActiveEngineering
    +165.8% over 7 days
    3.3kGitHub stars
  247. 247▼
    pasky/chrome-cdp-skill

    Interact with local Chrome browser session (only on explicit user approval after being asked to inspect, debug, or interact with a page open in Chrome)

    1.1Local scriptsSlowingEngineering
    0.0% over 7 days
    3.3kGitHub stars
  248. 248▼
    rpamis/comet

    Comet: agent skill harness for turning ideas into evaluated workflows

    6.4Network or broad shellActiveEngineering
    +0.6% over 7 days
    3.3kGitHub stars
  249. 249▼
    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
  250. 250▼
    vuejs-ai/skills

    Agent skills for Vue 3 development

    6.6Network or broad shellActiveEngineering
    +1.3% over 7 days
    3.3kGitHub stars
  251. 251▼
    Owl-Listener/designer-skills

    Designer Skills Collection: agentic skills, commands, and plugins for design — from research to systems, UI, interaction, and delivery.

    6.8Instructions onlySlowingDesign
    +2.9% over 7 days
    3.3kGitHub stars
  252. 252▼
    ningzimu/image-to-editable-ppt-skill

    Rebuild slide images, scanned or image-based PPT/PPTX files, and PDF decks into object-level editable PowerPoint (.pptx), preserving speaker notes when supplied. Use for making visual slides editable or reconstructing slides from screenshots; not for authoring new presentations from scratch.

    6.5Network or broad shellActiveEngineering
    +2.5% over 7 days
    3.3kGitHub stars
  253. 253▼
    thananon/9arm-skills

    Four-mantra debugging discipline — reproduce, trace the fail path, falsify the hypothesis, cross-reference every breadcrumb. Recite the mantra block verbatim at the start of any debugging session, then apply the four steps in order before proposing any fix. Trigger on /debug-mantra and proactively w

    4.5Network or broad shellSlowingEngineering
    +0.4% over 7 days
    3.3kGitHub stars
  254. 254—
    nano-muse/nanoMuse

    nanoMuse: an open-source personal agent for every device you own. One agent with a name and a look of its own that does things, keeps working while the app is closed, remembers you, and asks before anything you cannot undo. On Android, iPhone and iPad, Windows / macOS / Linux and in the browser; your phone's screen and your computer as its hands.

    8.6Instructions onlyActiveEngineering
    +11.8% over 7 days
    3.2kGitHub stars
  255. 255▼
    Forward-Future/loopy

    A library of practical AI-agent loops and an installable skill for finding, adapting, and designing repeatable agent workflows.

    4.5Local scriptsActiveEngineering
    +0.3% over 7 days
    3.2kGitHub stars
  256. 256▼
    KhazP/vibe-coding-prompt-template

    Templates and workflow for generating PRDs, Tech Designs, and MVP and more using LLMs for AI IDEs

    3.6Network or broad shellActiveEngineering
    +0.6% over 7 days
    3.2kGitHub stars
  257. 257▼
    ciembor/agent-rules-books

    AGENTS.md rules / skills for AI coding agents: Codex, Cursor & Claude Code. Inspired by Clean Code, Refactoring, DDD, Clean Architecture and DDIA programming books.

    6.3Instructions onlyActiveEngineering
    +1.8% over 7 days
    3.2kGitHub stars
  258. 258▼
    mitsuhiko/agent-stuff

    These are commands I use with agents, mostly Claude

    3.7Network or broad shellActiveEngineering
    +0.2% over 7 days
    3.2kGitHub stars
  259. 259▼
    Chachamaru127/claude-code-harness

    Claude Code Dedicated Development Harness - Achieving High-Quality Development Through an Autonomous Plan→Work→Review Cycle

    5.5Network or broad shellActiveEngineering
    +0.3% over 7 days
    3.2kGitHub stars
  260. 260▼
    Agentchengfeng/chengfeng-videocut-skills

    用 Claude Code Skills 做的视频剪辑 Agent

    5.3Local scriptsActiveEngineering
    +0.9% over 7 days
    3.2kGitHub stars
  261. 261▼
    QwenLM/Qwen-MM-Plugins

    Make any agent harness multimodal-native.

    6.0Network or broad shellActiveEngineering
    +0.7% over 7 days
    3.2kGitHub stars
  262. 262▼
    spotify/portal-ai-plugins

    Delegate bulk file reading to AiKA. Use when you need to read files >350 lines, answer questions across 3+ files, or summarize large diffs.

    8.2Local scriptsActiveEngineering
    +25.9% over 7 days
    3.2kGitHub stars
  263. 263▼
    flutter/agent-plugins

    Write and organize unit tests for functions, methods, and classes using `package:test`. Use when creating new logic or fixing bugs to ensure code remains correct and regression-free.

    6.1Network or broad shellActiveEngineering
    +0.9% over 7 days
    3.2kGitHub stars
  264. 264▼
    leo-lilinxiao/codex-autoresearch

    Run repeated, measured Git experiments toward a numeric target; keep improvements and revert failures. Use for autonomous optimization or managing an autoresearch run, not one-shot edits.

    6.0Network or broad shellActiveEngineering
    +1.8% over 7 days
    3.1kGitHub stars
  265. 265▼
    xstongxue/best-skills

    通用高质量 Skills 合集🔥

    5.8Network or broad shellActiveEngineering
    +1.6% over 7 days
    3.1kGitHub stars
  266. 266▲
    t3dotgg/tstack

    The agent skills I use every day. Works with Claude Code and Codex.

    8.0Local scriptsActiveEngineering
    +26.1% over 7 days
    3.1kGitHub stars
  267. 267▼
    FreedomIntelligence/OpenClaw-Medical-Skills

    The largest open-source medical AI skills library for OpenClaw🦞.

    4.0Network or broad shellSlowingEngineering
    +0.2% over 7 days
    3.1kGitHub stars
  268. 268—
    Vincentwei1021/anything2explainer

    给一个主题,产出一条黑底 MG 风格(幕底可选星点或点阵波)、有配音字幕章节进度条的科普讲解视频(中文或英文;Remotion 代码动画;时长由用户定,常用 3–5 分钟)。内含可编译模板、图元库、配音/分镜/渲染工具、风格与动效规范、多 agent 分工协议与 QC 判据,以及一条完整样片(《RAG 与知识库》)作为质量标尺。Turn any topic into a narrated motion-graphics explainer video in Chinese or English, on a black canvas with a star-field or dot-field

    7.2Network or broad shellActiveEngineering
    +7.9% over 7 days
    3.1kGitHub stars
  269. 269▼
    alsk1992/CloddsBot

    Open Source AI trading agent that operates autonomously across 1000+ markets - Polymarket, Kalshi, Binance, Hyperliquid, Solana DEXs, 5 EVM chains. Scans for edge, executes instantly, manages risk while you sleep. Agent commerce protocol for machine-to-machine payments. Self-hosted. Built on Claude.

    5.8Network or broad shellActiveEngineering
    +1.8% over 7 days
    3.1kGitHub stars
  270. 270▼
    digitalinnovationone/dio-agent

    Agente de IA criado pela DIO para apoiar seus estudos.

    8.2Instructions onlyActiveEngineering
    +11.1% over 7 days
    3kGitHub stars
  271. 271▼
    butterbase-ai/butterbase

    AI-native, open-source backend-as-a-service with a built-in Model Context Protocol server. Postgres, auth, storage, functions, AI gateway.

    1.9Network or broad shellActiveEngineering
    0.0% over 7 days
    3kGitHub stars
  272. 272▼
    public-clis/twitter-cli

    Use twitter-cli for ALL Twitter/X operations — reading tweets, posting, replying, quoting, liking, retweeting, following, searching, user lookups. Invoke whenever user requests any Twitter interaction.

    4.3Network or broad shellSlowingEngineering
    +0.3% over 7 days
    3kGitHub stars
  273. 273▼
    supabase/agent-skills

    Agent Skills to help developers using AI agents with Supabase

    5.8Network or broad shellSlowingEngineering
    +1.6% over 7 days
    3kGitHub stars
  274. 274▼
    open-gitagent/opengap

    A framework-agnostic, git-native standard for defining AI agents

    1.9Network or broad shellSlowingEngineering
    +0.0% over 7 days
    3kGitHub stars
  275. 275▼
    hotcoffeeshake/tong-jincheng-skill

    童锦程视角:以"深情祖师爷"、直播情感内容创作者的思维框架看待人际关系、社会动态与个人成长。 素材来源:9个一手视频字幕(直播/约会vlog/搭讪解析),约20万字。 核心模型:5个。决策启发式:9条。 触发词:「童锦程」「深情祖师爷」「用童锦程的方式」「从童锦程视角」「景辰怎么看」 局限:素材以情感/人际内容为主,商业/创业思维数据不足,慎用于纯商业决策场景。 调研时间:2026年4月。

    5.7Instructions onlyActiveEngineering
    +0.6% over 7 days
    3kGitHub stars
  276. 276▼
    elementalsouls/Claude-OSINT

    8 Claude skills · 100+ recon capabilities · 80 secret-regex patterns · 80+ dorks · 9 read-only credential validators · 27 attack-path templates · ~10,000 lines of structured tradecraft. Drop-in SKILL.md files that turn Claude into a god-mode external recon operator for authorized red-team and bug-bounty engagements.

    6.6Network or broad shellActiveEngineering
    +1.6% over 7 days
    3kGitHub stars
  277. 277▼
    rohitg00/pro-workflow

    Claude Code learns from your corrections: self-correcting memory that compounds over 50+ sessions. Context engineering, parallel worktrees, agent teams, and 17 battle-tested skills.

    4.2Network or broad shellActiveOperations
    +0.2% over 7 days
    2.9kGitHub stars
  278. 278—
    0xsline/OpenChatCut

    Open-source, local-first conversational AI video editor with a professional multi-track timeline, Agent Skills, MCP integration, and Remotion rendering.

    8.2Network or broad shellActiveEngineering
    +5.1% over 7 days
    2.9kGitHub stars
  279. 279▼
    aiwithremy/claude-skills-llm-council

    Run any question, idea, or decision through a council of 5 AI advisors who independently analyze it, peer-review each other anonymously, and synthesize a final verdict. Based on Karpathy's LLM Council methodology. MANDATORY TRIGGERS: 'council this', 'run the council', 'war room this', 'pressure-test

    6.6Instructions onlySlowingEngineering
    +3.2% over 7 days
    2.9kGitHub stars
  280. 280—
    chrisryugj/kordoc

    Use this skill whenever the user wants to read, create, fill, edit, compare, validate, or preview Korean Hangul/official documents — .hwp (HWP 3.x/5.x), .hwpx, .hml (HWPML) — or convert Korean-office PDF/DOCX/XLS/XLSX to Markdown. Triggers include any mention of 'hwp', 'hwpx', 'hml', '한글 문서', '아래한글'

    7.5Local scriptsActiveEngineering
    +2.8% over 7 days
    2.9kGitHub stars
  281. 281▼
    cclank/lanshu-create-ai-presenter-video

    Turn a topic or finished script into a complete, publish-ready explainer video — led by an AI presenter from an authorized adult presenter image, or performed with no presenter in one of twelve explainer styles (nine visual styles and three narrative ones). Not for promos, ads, or footage montages.

    7.1Network or broad shellActiveEngineering
    +2.9% over 7 days
    2.9kGitHub stars
  282. 282▲
    alexgreensh/token-optimizer

    Find the ghost tokens. Fix them. Survive compaction. Avoid context quality decay.

    7.7Network or broad shellActiveEngineering
    +3.4% over 7 days
    2.9kGitHub stars
  283. 283▼
    op7418/Claude-to-IM-skill

    Bridge THIS Claude Code or Codex session to Telegram, Discord, Feishu/Lark, QQ, or WeChat so the user can chat with Claude from their phone. Use for: setting up, starting, stopping, or diagnosing the claude-to-im bridge daemon; forwarding Claude replies to a messaging app; any phrase like "claude-to

    1.8Network or broad shellSlowingEngineering
    +0.1% over 7 days
    2.9kGitHub stars
  284. 284▼
    jeremylongshore/tons-of-skills-marketplace

    Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.

    5.6Network or broad shellActiveDevOps
    +0.5% over 7 days
    2.9kGitHub stars
  285. 285▼
    typesafe-ai/skills

    TypeSafe integration craft for System One models (sometimes called Decision Models) such as Jev, which answer typed questions about text, images, and application state with calibrated probabilities. Use when building, reviewing, or debugging code that calls TypeSafe; when writing its questions or st

    5.8Local scriptsActiveEngineering
    +0.9% over 7 days
    2.9kGitHub stars
  286. 286—
    Pinvou/pinvou-agent

    Open-source desktop AI agent for tools, files, knowledge, workflows, and real deliverables.

    8.0Network or broad shellActiveEngineering
    +4.1% over 7 days
    2.9kGitHub stars
  287. 287▼
    chengyi-ai/native-subtitle-quote-image

    将本地视频或用户有权处理的在线视频,经过来源获取、文字稿定位、选题选句、精确取帧、紧凑裁切、拼图和逐张质检,制作成 3:4 或保留画面原比例的视频字幕长图。支持两种明确分开的输出:保留画面内已烧录字幕的原生字幕模式,以及把已审核的时间点与台词绘制到真实视频帧上的脚本字幕模式。用户要求原生字幕截图、字幕帧拼图、YouTube 金句长图、台词截图、不重绘字幕、自定义中文台词,或调整主图比例、字幕区域、台词间隔和美感时使用。

    5.9Network or broad shellActiveEngineering
    +3.9% over 7 days
    2.9kGitHub stars
  288. 288▼
    compozy/compozy

    An operating system for AI agents. Plug in the agent CLIs you already use (Claude Code, Codex, Gemini CLI, Cursor) and they become a team: they split the work, hand tasks to each other, run automated on jobs and loops, and share one project memory. You steer everything from the browser.

    5.8Network or broad shellActiveEngineering
    +0.4% over 7 days
    2.8kGitHub stars
  289. 289▼
    zilliztech/memsearch

    A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.

    5.3Network or broad shellActiveEngineering
    +0.4% over 7 days
    2.8kGitHub stars
  290. 290▼
    rohitg00/awesome-claude-code-toolkit

    The most comprehensive toolkit for Claude Code -- 135 agents, 35 curated skills, 42 commands, 176+ plugins, 20 hooks, 15 rules, 7 templates, 14 MCP configs, 26 companion apps, 52 ecosystem entries, and more.

    4.6Network or broad shellSlowingEngineering
    +0.6% over 7 days
    2.8kGitHub stars
  291. 291▼
    oil-oil/oil-motion

    把 AI 生成或已有的视频、序列帧变成随滚动、指针、拖动、触摸、设备方向、音频、数据或状态变化的网页动画:设计动作方向,生成关键帧与视频,整理成图集或视频,编译时间轴并接入运行时。用户需要角色转向、产品拆解、镜头穿越、一镜到底转场,或要清理、抠色、补帧、压缩绿幕视频与雪碧图时使用。不用于纯 CSS、JS、SVG、Lottie 或实时 3D 就能完成的界面过渡与微交互(交给普通前端实现),也不用于独立成片剪辑、单张配图或静态页面。

    6.2Network or broad shellActiveEngineering
    +2.3% over 7 days
    2.8kGitHub stars
  292. 292▲
    NanmiCoder/dsh-agent-teams

    DeepSeek Harness 的 Agent Teams 多智能体协作插件,支持多个 AI Agent 组成团队,协同完成复杂任务,实现任务分配、并行执行、成员通信与团队协作。 AgentTeams plugin for DeepSeek Harness

    8.3Network or broad shellActiveEngineering
    +5.6% over 7 days
    2.7kGitHub stars
  293. 293▼
    jackwener/xiaohongshu-cli

    Use xiaohongshu-cli for ALL Xiaohongshu (Little Red Book, 小红书) operations — searching notes, reading content, browsing users, liking, collecting, commenting, following, and posting. Invoke whenever the user requests any Xiaohongshu interaction.

    4.6Network or broad shellSlowingEngineering
    +0.3% over 7 days
    2.7kGitHub stars
  294. 294▼
    yaojingang/yao-meta-skill

    Create, improve, or evaluate an existing skill from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install/trust checks, 优化已有 skill, 补 trigger 评测. Exclude summary/translation/docs, brainstorming, one-off prompts, copy-only edits, outline-only requests.

    3.3Network or broad shellSlowingEngineering
    +0.1% over 7 days
    2.7kGitHub stars
  295. 295▼
    Astro-Han/karpathy-llm-wiki

    Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.

    5.8Network or broad shellSlowingEngineering
    +1.8% over 7 days
    2.7kGitHub stars
  296. 296▼
    badlogic/pi-skills

    Skills for pi coding agent (compatible with Claude Code and Codex CLI)

    4.3Network or broad shellSlowingEngineering
    +0.3% over 7 days
    2.7kGitHub stars
  297. 297▼
    perkfly/ex-skill

    Distill an ex-girlfriend into an AI Skill. Import WeChat/iMessage/SMS/photos, generate Memories + Persona, with continuous evolution. | 把前任蒸馏成 AI Skill,导入微信/iMessage/短信/照片,生成共同记忆 + Persona,支持持续进化。

    4.6Network or broad shellSlowingEngineering
    +0.5% over 7 days
    2.6kGitHub stars
  298. 298▼
    softaworks/agent-toolkit

    A curated collection of skills for AI coding agents. Skills are packaged instructions and scripts that extend agent capabilities across development, documentation, planning, and professional workflows.

    5.5Network or broad shellSlowingEngineering
    +1.1% over 7 days
    2.6kGitHub stars
  299. 299▼
    GoogleChrome/modern-web-guidance

    Keep your coding agent up to date with the latest web best practices

    6.9Network or broad shellActiveEngineering
    +1.8% over 7 days
    2.6kGitHub stars
  300. 300▼
    yaklang/hack-skills

    Helping AI Agent become an awesome practical hacker!

    5.1Network or broad shellActiveEngineering
    +1.2% over 7 days
    2.6kGitHub stars
  301. 301▼
    threerocks/hand-drawn-styles

    Use when users ask for a hand-drawn or illustrated image prompt, name one of the repository's 22 numbered styles or the 3.1 stable variant, or mention triggers such as 亲子手绘、家庭蜡笔画、蜡笔、吉卜力、水墨、像素、淡彩速写、动画概念、水粉、北欧绘本、纸雕、软胶潮玩、墨线绘本、暖色扁平绘本、圆头红线、暖黄墨线、family-crayon-card、warm-flat-storybook、roundhead-redline、war

    6.8Network or broad shellActiveEngineering
    +1.5% over 7 days
    2.6kGitHub stars
  302. 302▼
    wondelai/skills

    Wondel.ai Agent Skills — Business, Marketing, UX & Coding Frameworks from Bestselling Books. 50 skills + 12 guided journeys for Claude Code, Codex, Cursor & other agentskills.io agents.

    7.1Network or broad shellActiveEngineering
    +2.7% over 7 days
    2.6kGitHub stars
  303. 303▼
    sdyckjq-lab/llm-wiki-skill

    基于 Karpathy llm-wiki 方法论的个人知识库构建 Skill,支持多平台!

    4.7Network or broad shellSlowingEngineering
    +0.3% over 7 days
    2.6kGitHub stars
  304. 304▼
    amElnagdy/delegate-skills

    Delegate a coding task to a separate coding agent CLI, review the diff, land the commit yourself — one per implementer.

    6.9Local scriptsActiveEngineering
    +1.1% over 7 days
    2.6kGitHub stars
  305. 305▼
    Xiangyu-CAS/xiaohongshu-ops-skill

    小红书相关操作,覆盖账号定位、选题研究、内容生产、发布执行与复盘修复的小红书全链路运营技能。凡是小红书的浏览/搜索/发布/评论任务,默认必须使用 OpenClaw 内置浏览器流程并指定 profile="openclaw";除非用户明确要求,否则不要使用系统 open 或外部浏览器。

    6.6Network or broad shellSlowingEngineering
    +2.7% over 7 days
    2.5kGitHub stars
  306. 306▼
    kingkongshot/Pensieve

    Project knowledge base and workflow router. knowledge/ caches explored file locations, module boundaries, and call chains for reuse; decisions/maxims are established architecture decisions and coding standards to follow, not relitigate; pipelines are reusable workflows; short-term/ stages new conclu

    2.4Network or broad shellSlowingEngineering
    0.0% over 7 days
    2.5kGitHub stars
  307. 307▲
    MrGeDiao/shuorenhua

    按用户要求审稿或去 AI 味,支持中英文;保留事实、术语与责任主体,支持只标问题。

    8.1Network or broad shellActiveWriting
    +5.3% over 7 days
    2.5kGitHub stars
  308. 308▼
    vybenetwork/solana-mcp-vybe

    Public Solana MCP registry metadata for Vybe Solana API

    8.4Instructions onlyActiveEngineering
    +13.5% over 7 days
    2.5kGitHub stars
  309. 309▼
    noamseg/interview-coach-skill

    High-rigor interview coaching skill for job seekers. Use when someone wants structured prep, transcript analysis, practice drills, storybank management, or performance tracking. Supports quick prep and full-system coaching across PM, Engineering, Design, Data Science, Research, Marketing, and Operat

    5.9Network or broad shellSlowingEngineering
    +1.4% over 7 days
    2.5kGitHub stars
  310. 310▼
    apify/agent-skills

    Collection of Apify agent skills

    5.6Network or broad shellActiveEngineering
    +0.5% over 7 days
    2.5kGitHub stars
  311. 311▼
    leilei926524-tech/anti-distill

    Anti-distillation for employee Skills. Clean your skill files — looks complete, but core knowledge removed. | 反蒸馏:清洗你被迫写的 Skill 文件,看起来完整,但核心知识已被抽掉。

    3.4Network or broad shellSlowingEngineering
    +0.5% over 7 days
    2.5kGitHub stars
  312. 312▼
    LearnPrompt/awesome-seedance

    🎬 Evidence-led Seedance 2.5 / 2.0 prompt library: 840+ cases traced to original posts, 490+ cross-model retest runs, 27 copy-ready templates, 79 installable AI-video Skills. Synced daily from goodcase.ai. EN / 中文 / 日本語.

    8.1Network or broad shellActiveEngineering
    +4.1% over 7 days
    2.5kGitHub stars
  313. 313▼
    comeonzhj/Auto-Redbook-Skills

    一个自动撰写小红书笔记,自动生成图片,自动发布的 Skills

    5.9Network or broad shellSlowingEngineering
    +1.4% over 7 days
    2.5kGitHub stars
  314. 314▲
    JuneYaooo/rea-video

    逆向拆解一条视频是怎么做出来的——逐镜头判断实拍 / AI 生成 / 3D 渲染 / 2D 动画 / 定格动画 / 代码模板渲染 / 录屏截图 / 静态图推拉 / 静帧,以及实拍是否经过 AI 加工(换脸、对口型、风格化),标出后期叠加层(逐句字幕时间轴、花字、标题、贴纸 / GIF / 表情包、画中画)和用户真实素材,拆解人声、背景音乐、音效(卡在哪个画面事件上)与剪辑节奏,并给出可执行的复刻方案(可对接 capsule-cinema)。当用户给出参考视频、问"这条视频怎么做的 / 是不是 AI / 用了什么素材 / 怎么复刻"时使用。

    Insufficient historyInstructions onlyActiveEngineering
    Not available over 7 days
    2.4kGitHub stars
  315. 315▲
    alchaincyf/huashu-motion

    Motion graphics, launch videos and explainers as editable code. A director picks the motion language for your product; you point at frames to change them. 动画、发布片、解说视频,指着画面改。

    8.4Network or broad shellActiveEngineering
    +26.3% over 7 days
    2.4kGitHub stars
  316. 316▼
    DenisSergeevitch/agents-best-practices

    Use this skill when designing, generating an MVP blueprint for, auditing, troubleshooting, refactoring, or explaining an agentic harness for any domain. Covers provider-neutral agent architecture for OpenAI, Anthropic, and OpenAI-compatible APIs: agent loops, tool design, record provenance, interact

    5.9Local scriptsActiveEngineering
    +0.5% over 7 days
    2.4kGitHub stars
  317. 317▼
    FrancyJGLisboa/agent-skills-platform

    Build tested agent skills and govern their lifecycle through a user-defined marketplace: evidence, discovery, updates, rollback, quarantine, and 17-platform distribution.

    2.1Network or broad shellActiveEngineering
    +0.1% over 7 days
    2.4kGitHub stars
  318. 318▼
    tourmind-com/Tourmind-Booking-Skills

    AI agent skills for end-to-end hotel and flight booking—compare live hotel rates across leading OTAs and suppliers, search and verify real-time airfares worldwide, book stays and flights, and manage reservations, hotel cancellations, and payments via the TourMind API.

    5.4Local scriptsActiveEngineering
    +0.4% over 7 days
    2.4kGitHub stars
  319. 319▼
    larashero3-dotcom/lieflat-gongwen

    基于真实公文全量统计的公文写作 skill。分公文族与党建族两族,覆盖调研报告/领导讲话/工作意见/经验材料/工作方案/经验总结六类公文族文体,加千字级党建/基层经验材料一类,提供可验收的数值参数、骨架公式、标题技法和自动化自检脚本。触发场景:"写一篇调研报告""起草领导讲话""写份工作意见""写篇党建经验材料""把材料写成经验总结""让这篇稿子更有公文味""检查这篇公文的参数对不对"。

    8.2Local scriptsActiveEngineering
    +43.5% over 7 days
    2.4kGitHub stars
  320. 320▼
    UnicomAI/wanwu

    China Unicom's Yuanjing Wanwu Agent Platform is an enterprise-grade, multi-tenant AI agent development platform. It helps users build applications such as intelligent agents, workflows, and rag, and also supports model management. The platform features a developer-friendly license, and we welcome all developers to build upon the platform.

    5.3Network or broad shellActiveOperations
    +0.2% over 7 days
    2.4kGitHub stars
  321. 321▼
    ldrolez/free-midi-chords

    Compose, search and verify chord progressions and MIDI from the free-midi-chords pack.

    5.3Local scriptsActiveEngineering
    +0.3% over 7 days
    2.4kGitHub stars
  322. 322▼
    coldteadotai/pr-lens

    Review code 100x faster. Lens draws every PR as animated architecture and data-flow walkthroughs, inside the pull request itself. Use it as a GitHub App, GitHub Action, CLI, or a Skill for your coding agent

    7.5Network or broad shellActiveEngineering
    +2.4% over 7 days
    2.4kGitHub stars
  323. 323▼
    sumelabs/clawra

    Clawra - Openclaw as your companion

    1.0Network or broad shellSlowingEngineering
    0.0% over 7 days
    2.4kGitHub stars
  324. 324▼
    P4nda0s/reverse-skills

    Reverse engineering skills for Claude Code | 逆向工程 Claude Code Skills 插件

    4.8Network or broad shellSlowingEngineering
    +0.6% over 7 days
    2.4kGitHub stars
  325. 325▼
    op7418/logo-generator-skill

    Generate professional SVG logos and high-end showcase images. Use when the user wants to: (1) Create a logo or icon for their product/brand, (2) Generate logo design concepts based on product information, (3) Create professional logo showcase presentations with multiple background styles, (4) Export

    5.8Local scriptsSlowingEngineering
    +1.4% over 7 days
    2.3kGitHub stars
  326. 326▼
    WordPress/agent-skills

    Expert-level WordPress knowledge for AI coding assistants - blocks, themes, plugins, and best practices

    6.1Network or broad shellActiveEngineering
    +0.9% over 7 days
    2.3kGitHub stars
  327. 327▼
    deusyu/translate-book

    Translate books (PDF/DOCX/EPUB) into any language using parallel sub-agents. Converts input -> Markdown chunks -> translated chunks -> HTML/DOCX/EPUB/PDF.

    8.0Network or broad shellActiveEngineering
    +7.6% over 7 days
    2.3kGitHub stars
  328. 328▼
    Sahir619/fable-method

    The Fable Workflow: how Claude Fable 5 worked, distilled into skills any model can run, with the eval that keeps it honest. Think / act / prove.

    2.1Local scriptsActiveEngineering
    +0.1% over 7 days
    2.3kGitHub stars
  329. 329▼
    asuojun/claude-vision-skill

    Use when the user shares, pastes, or references an image (local path or URL) and you need to describe, analyze, or recognize its content, especially when the current model cannot read images directly. Run the bundled vision.js helper to convert the image into text.

    1.6Network or broad shellActiveEngineering
    -0.2% over 7 days
    2.3kGitHub stars
  330. 330▼
    mgechev/skills-best-practices

    Authors and structures professional-grade agent skills following the agentskills.io spec. Use when creating new skill directories, drafting procedural instructions, or optimizing metadata for discoverability. Don't use for general documentation, non-agentic library code, or README files.

    4.8Local scriptsSlowingEngineering
    +0.4% over 7 days
    2.3kGitHub stars
  331. 331▼
    HUANGCHIHHUNGLeo/claude-real-video

    Let Claude (or any LLM) actually watch a video — scene-aware, deduplicated frames + transcript, from a URL or local file. Runs locally, MIT.

    6.0Network or broad shellActiveEngineering
    +0.7% over 7 days
    2.3kGitHub stars
  332. 332▼
    op7418/Youtube-clipper-skill

    YouTube 视频智能剪辑工具。下载视频和字幕,AI 分析生成精细章节(几分钟级别), 用户选择片段后自动剪辑、翻译字幕为中英双语、烧录字幕到视频,并生成总结文案。 使用场景:当用户需要剪辑 YouTube 视频、生成短视频片段、制作双语字幕版本时。 关键词:视频剪辑、YouTube、字幕翻译、双语字幕、视频下载、clip video

    3.8Network or broad shellSlowingEngineering
    +0.7% over 7 days
    2.3kGitHub stars
  333. 333▼
    eeeeeeeeee-code/e0e1-wx

    Use when reviewing authorized WeChat mini-program or mini-app targets for authentication bypass, IDOR, undefined-path access, API abuse, decryption and signature analysis, runtime reverse engineering, route mapping, and sensitive data exposure, with file-submission attack surfaces intentionally excl

    0.9Network or broad shellSlowingEngineering
    0.0% over 7 days
    2.3kGitHub stars
  334. 334▼
    LetsFG/LetsFG

    Agent-native flight & hotel search and booking — MCP server, CLI, and Python/JS SDKs. Every airline in the world, major booking sites and OTAs, with per-flight reliability history.

    6.8Network or broad shellActiveEngineering
    +1.0% over 7 days
    2.2kGitHub stars
  335. 335▼
    Dicklesworthstone/mcp_agent_mail

    MCP Agent Mail - Mail-like coordination layer for multi-agent workflows. Identities, inbox/outbox, file reservations, contact policies, threaded messaging, pre-commit guard, Human Overseer, static exports, disaster recovery. Git+SQLite backed. Python/FastMCP.

    4.1Network or broad shellActiveEngineering
    +0.2% over 7 days
    2.2kGitHub stars
  336. 336▼
    GordenSun/GordenSuperPPTSkills

    AI PPT赛道终结者,史上最最最强 PPT Skill!!! 使用GPT生成豪华的图片格式PPT,然后转换为完全可编辑的PPTX文件。

    5.7Local scriptsSlowingEngineering
    +1.1% over 7 days
    2.2kGitHub stars
  337. 337▼
    alchaincyf/huashu-skills

    花叔全部开源 Agent Skills 总目录:16 旗舰 + 14 人物视角 + 22 内置共 52 个 skill,分层分类 + AI Agent 安装协议 + 机器可读 skills.json + 更新检查机制

    7.9Network or broad shellActiveEngineering
    +4.0% over 7 days
    2.2kGitHub stars
  338. 338▼
    awesome-skills/code-review-skill

    Provides comprehensive code review guidance for React 19, Vue 3, Angular 17+, Svelte 5, Rust, TypeScript, Java, Java 8, PHP, Ruby, Rails, Python, Django, FastAPI, Go, C#/.NET, Kotlin, Swift, Dart, Flutter, NestJS, C/C++, Zig, CSS/Less/Sass, Qt, and more. Covers architecture review, performance revie

    5.9Network or broad shellActiveEngineering
    +1.3% over 7 days
    2.2kGitHub stars
  339. 339▼
    RinDig/icm-architect

    Design a process, idea or body of knowledge into an ICM (Interpretable Context Methodology) workspace, where folder structure is the agent architecture, or restructure an existing folder, repo or vault into one. Use for "make this an ICM", "ICM this", "build me a workspace", "structure this for agen

    7.5Network or broad shellActiveEngineering
    +3.6% over 7 days
    2.2kGitHub stars
  340. 340▼
    renatoasse/opensquad

    Web scraping and automation platform. Extract data from any website, run pre-built scrapers (Actors), and automate web workflows using thousands of ready-made tools from the Apify Store.

    5.3Network or broad shellSlowingEngineering
    +0.6% over 7 days
    2.2kGitHub stars
  341. 341▼
    LiuMengxuan04/shushu-internship-tool

    Use when an AI assistant helps computer-industry internship candidates with 鼠鼠实习妙妙工具 quickly turn a target job description into a resume-ready and interview-ready project across backend, frontend, full-stack, mobile, testing, data engineering, cloud/DevOps, security, systems, or AI/ML roles: finding

    5.4Network or broad shellSlowingEngineering
    +1.1% over 7 days
    2.2kGitHub stars
  342. 342▼
    Leanmcp/gateway-skills

    See your claude code logs in clear details in your dashboard

    3.0Network or broad shellActiveEngineering
    +0.0% over 7 days
    2.1kGitHub stars
  343. 343▼
    mvanhorn/printing-press-library

    Official library of CLIs generated by the CLI Printing Press. Endorsed, tested, and community-contributed.

    6.3Not checked yetActiveEngineering
    +0.6% over 7 days
    2.1kGitHub stars
  344. 344▼
    Hello-Mr-Crab/pywechat

    仍然可用的微信RPA!支持4.0系列微信pywechat是一个基于pywinauto实现的windows桌面微信自动化操作工具,基本实现了PC微信内置的各项操作。

    6.6Local scriptsActiveEngineering
    +1.2% over 7 days
    2.1kGitHub stars
  345. 345▼
    Jesseovo/last30days-skill-cn

    给 AI Agent 的中文互联网研究 Skill:检索 8 大平台最近 30 天的讨论,追踪跨平台热点,生成附原始来源的报告,并提供每日全网热榜。支持 Claude Code、Codex、OpenClaw。

    7.7Network or broad shellActiveEngineering
    +2.8% over 7 days
    2.1kGitHub stars
  346. 346▼
    stripe/ai

    One-stop shop for building AI-powered products and businesses with Stripe.

    6.9Network or broad shellActiveEngineering
    +1.8% over 7 days
    2kGitHub stars
  347. 347—
    autoclaw-cc/xiaohongshu-skills

    xiaohongshu-skills

    5.9Network or broad shellSlowingEngineering
    +1.2% over 7 days
    2kGitHub stars
  348. 348▼
    pchalasani/claude-code-tools

    Practical productivity tools for Claude Code, Codex-CLI, and similar CLI coding agents.

    4.2Network or broad shellActiveEngineering
    +0.3% over 7 days
    2kGitHub stars
  349. 349▼
    nimbalyst/nimbalyst

    Nimbalyst - The open-source visual workspace for Claude Code, Codex, and OpenCode. Run multiple coding agents in parallel, edit their work visually in markdown, mockups, and diagrams, and track tasks. Free, MIT-licensed desktop app for macOS, Windows, Linux, with mobile companion for iOS and Android.

    7.4Network or broad shellActiveEngineering
    +1.3% over 7 days
    2kGitHub stars
  350. 350—
    xu-xiang/everything-claude-code-zh

    everything-claude-code 中文翻译项目:完整的 Claude Code 配置集合(agents, skills, hooks, commands, rules, MCPs)。源自 Anthropic 黑客松获胜者的实战配置,助力中文工程师高效理解与使用 Claude Code。

    5.0Network or broad shellSlowingProductivity
    +0.7% over 7 days
    2kGitHub stars
  351. 351▼
    c15t/c15t

    Open-source cookie consent manager and GDPR cookie banner for React, Next.js, Vue and JavaScript. Google Consent Mode v2 and IAB TCF.

    3.1Network or broad shellActiveEngineering
    +0.1% over 7 days
    2kGitHub stars
  352. 352▼
    openakita/openakita

    An open-source AI assistant framework with skills and agent architecture

    2.4Network or broad shellActiveEngineering
    +0.1% over 7 days
    2kGitHub stars
  353. 353▼
    zhangxiangliang/stock-api

    Fetch real-time stock quotes, K-line (candlestick) history, and search symbols for China A-shares, Hong Kong, and US markets. Use when the user asks for a stock price, a quote, market data, candlestick/K-line data, or to look up a stock code by company name.

    4.9Network or broad shellActiveEngineering
    +0.5% over 7 days
    2kGitHub stars
  354. 354▼
    databricks-solutions/ai-dev-kit

    Databricks Toolkit for Coding Agents provided by Field Engineering

    5.6Network or broad shellActiveEngineering
    +0.4% over 7 days
    2kGitHub stars
  355. 355▼
    glittercowboy/taches-cc-resources

    A collection of my favorite custom Claude Code resources to make life easier.

    1.0Network or broad shellSlowingEngineering
    0.0% over 7 days
    2kGitHub stars
  356. 356▼
    composio-community/awesome-claude-plugins

    A curated list of Plugins that let you extend Claude Code with custom commands, agents, hooks, and MCP servers through the plugin system.

    6.1Network or broad shellActiveEngineering
    +0.6% over 7 days
    2kGitHub stars
  357. 357—
    huang-sir1/radiology-skills

    Audit imaging acquisition, reconstruction, series eligibility, quantitative transforms and protocol drift; not model training.

    0.7Network or broad shellActiveEngineering
    -0.3% over 7 days
    2kGitHub stars
  358. 358—
    Dicklesworthstone/pi_agent_rust

    High-performance AI coding agent CLI written in Rust with zero unsafe code

    6.8Network or broad shellActiveEngineering
    +0.8% over 7 days
    2kGitHub stars
  359. 359—
    mcollina/skills

    My own collection of skills for modern Node.js development

    3.5Network or broad shellActiveEngineering
    +0.1% over 7 days
    2kGitHub stars
  360. 360—
    yetone/native-feel-skill

    Use when the user is designing, prototyping, or rewriting a desktop app that must run on multiple OSes (macOS + Windows, optionally Linux) AND feel indistinguishable from a native app to its users — fast launch, native windowing, native input handling, native materials. Trigger words include "cross-

    4.7Instructions onlySlowingEngineering
    +0.5% over 7 days
    2kGitHub stars
  361. 361▲
    rmyndharis/antigravity-skills

    A curated collection of Agent Skills for Google Antigravity

    7.5Network or broad shellActiveEngineering
    +2.9% over 7 days
    2kGitHub stars
  362. 362—
    sandeco/reversa

    Transform legacy systems into executable specifications for AI coding agents

    8.0Network or broad shellActiveEngineering
    +5.3% over 7 days
    1.9kGitHub stars
  363. 363—
    lixiaoxiao9888-create/manju-laoli-skill

    漫剧老李 AIGC 创作全流程 Skill · V7.4.26 多技能套装版(Short-Drama Director Suite):1 总控 + 12 子技能 · 四层纵深——赛道分流 / 素材采风 / 剧本 / 资产 / 分镜 / 三大打戏引擎 / 投喂 / 质检全链路。六道前置锁 + I 画风锁 · 50 份规则库 · 机检 C1~C33 | H1~H12 + 六道投喂闸门 + P4.5 故事板机检(P450~P458)· 素材形态 M0/M1/M2(本包不持有图)· 产出可直接投喂 Seedance 2.5 / 2.0 / MiniMax H3 的七段式提示词组。测试版,二次修改整合开源内容。

    8.3Network or broad shellActiveEngineering
    +7.7% over 7 days
    1.9kGitHub stars
  364. 364▲
    kenryu42/cc-safety-net

    Operate CC Safety Net: explain why a command was blocked, triage false positives, configure custom rulebooks, manage agent CLI integrations, and diagnose protection.

    8.3Network or broad shellActiveSecurity
    +3.7% over 7 days
    1.9kGitHub stars
  365. 365▼
    Besty0728/Unity-Skills

    AI automation skills specifically designed for Unity

    5.0Network or broad shellActiveEngineering
    +0.9% over 7 days
    1.9kGitHub stars
  366. 366▲
    DreambigOu/ELI5

    Explain any topic, code, concept, or error tailored to a specific audience's level of understanding. Use this skill whenever the user says 'explain like I am', 'ELI5', 'explain this to my', 'break this down for', 'dumb it down', 'simplify this for', or asks you to explain something to a specific per

    6.4Instructions onlySlowingEducation
    +1.8% over 7 days
    1.9kGitHub stars
  367. 367▼
    cookiy-ai/sell-sessions-skill

    Explain and help users adopt Cookiy Earn for licensing selected AI coding-agent sessions and traces. Use this skill whenever someone mentions sell agent traces, sell agent sessions, selling Codex or Claude Code traces/sessions, Cookiy Earn, earning from AI-agent history, or selling data to earn—even

    3.2Instructions onlyActiveEngineering
    +0.5% over 7 days
    1.9kGitHub stars
  368. 368—
    EpicGames/unreal-engine-skills-for-claude-code-plugin

    Use this skill when authoring or extending an Unreal Engine toolset, a class of static, AI-callable functions registered with `ToolsetRegistry` and exposed through the unreal-mcp server. Trigger when the user wants to add, expose, or register a new tool method, create a new toolset, or extend an exi

    7.9Local scriptsActiveEngineering
    +10.1% over 7 days
    1.9kGitHub stars
  369. 369—
    benchflow-ai/skillsbench

    SkillsBench evaluates how well skills work and how effective agents are at using them.

    6.3Network or broad shellActiveEngineering
    +0.8% over 7 days
    1.9kGitHub stars
  370. 370▲
    higgsfield-ai/skills

    Create and extend complete visual brand systems through the Higgsfield CLI and bundled deterministic local tooling: palettes, SVG logo marks, typography, mockups, social graphics, packaging, signage, merchandise, posters, presentation decks, and editable PPTX/PDF brandbooks. Preserves official suppl

    8.0Network or broad shellActiveEngineering
    +4.3% over 7 days
    1.9kGitHub stars
  371. 371▼
    XiaoMaColtAI/math-modeling-skill

    数学建模技能 - 面向 CUMCM、MCM/ICM 等数学建模竞赛的三阶段工作流:建模分析、Python/MATLAB 编程与 DOCX 论文生成。包含丰富的算法资源库(优化/预测/评价/图论/机器学习等)、角色指导文档、论文模板和实用工具脚本

    5.6Network or broad shellActiveEngineering
    +0.4% over 7 days
    1.9kGitHub stars
  372. 372▲
    caru-ini/stack-diagram

    Create cloud-architecture-style diagrams of tech stacks, system architectures, infra layouts, and service topologies — with real brand logos, grouped containers, and clean orthogonal arrows — delivered as self-contained HTML, a PNG image, a React/TSX component, or a live artifact. Use this skill whe

    Insufficient historyNetwork or broad shellActiveEngineering
    Not available over 7 days
    1.9kGitHub stars
  373. 373▼
    a5c-ai/babysitter

    Babysitter enforces obedience on agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic, hallucination-free self-orchestration

    4.5Network or broad shellSlowingEngineering
    +0.4% over 7 days
    1.9kGitHub stars
  374. 374▲
    axoviq-ai/synthadoc

    Synthadoc: An open-source LLM knowledge compilation engine that turns raw documents into structured, local-first wikis. A transparent, human-readable alternative to traditional RAG, which can be self-managed and self-improved without the use of any tools.

    8.6Network or broad shellActiveEngineering
    +14.6% over 7 days
    1.9kGitHub stars
  375. 375▼
    timescale/pg-aiguide

    MCP server and Claude plugin for Postgres skills and documentation. Helps AI coding tools generate better PostgreSQL code.

    5.1Network or broad shellActiveDocumentation
    +0.3% over 7 days
    1.9kGitHub stars
  376. 376▼
    hexiecs/talk-normal

    Make any LLM talk like a normal person. A system prompt that removes AI slop.

    2.5Local scriptsSlowingEngineering
    +0.1% over 7 days
    1.9kGitHub stars
  377. 377▼
    weapp-tailwindcss/weapp-tailwindcss

    Bring Tailwind CSS to every platform! 把 Tailwind CSS 的原子化开发体验带到全端!

    2.0Network or broad shellActiveEngineering
    0.0% over 7 days
    1.9kGitHub stars
  378. 378▼
    qufei1993/skills-hub

    A cross-platform desktop app to manage Agent Skills in one place and sync them to multiple AI coding tools’ global skills directories — “Install once, sync everywhere”.

    6.3Local scriptsActiveEngineering
    +0.9% over 7 days
    1.9kGitHub stars
  379. 379▼
    crazyykhllc-bit/CyberPPT

    当用户需要把 DOCX、PDF、TXT、XLSX、研究报告、业务材料或原始数据转成高密度、可编辑、咨询风格 PPTX 时使用;也适用于需要 SCR 论证、视觉风格探索、详细图表和渲染质检的 PPT。

    4.9Network or broad shellSlowingEngineering
    +0.9% over 7 days
    1.9kGitHub stars
  380. 380▼
    openprose/prose

    Activate when the user types `prose ...`, opens a `.prose.md` file with `kind:` frontmatter, opens a `.prose` file, or asks for reusable multi-agent orchestration. Treat `prose run ...` as an in-session instruction: embody the OpenProse VM yourself; do not shell out to a `prose` binary. On activatio

    2.7Network or broad shellActiveEngineering
    +0.2% over 7 days
    1.9kGitHub stars
  381. 381▲
    Gentleman-Programming/gentle-shell

    Gentle Shell is a Pi-native workspace for AI-assisted development, bringing parallel coding agents, live tasks, Git diffs, persistent memory, and permission controls into one terminal interface. Powered by Gentle AI and Organic Driven Development (ODD).

    8.7Network or broad shellActiveEngineering
    +23.0% over 7 days
    1.9kGitHub stars
  382. 382▼
    Prat011/awesome-llm-skills

    A curated list of awesome LLM and AI Agent Skills, resources and tools for customising AI Agent workflows - that works with Claude Code, Codex, Gemini CLI and your custom AI Agents

    4.2Network or broad shellSlowingEngineering
    +0.3% over 7 days
    1.8kGitHub stars
  383. 383▼
    simonlin1212/global-stock-data

    美股港股全栈数据工具包(官方源优先)— 十七层架构·50+端点·18数据源·全部零鉴权。在原有行情/K线/技术指标(MA/MACD/RSI/KDJ/布林带)/基本面/资金面/期权/SEC Filing/工具八层之上,新增:CBOE官方期权链(完整希腊字母+IV+0DTE流+异动识别)、FINRA全市场每日空头成交量、SEC EDGAR申报事件流(Form4内部人/8-K/13F机构持仓)、EDGAR全市场横截面筛选、美债收益率曲线/CFTC COT/财报日历;V2.1 新增全球利率汇率层(BIS 38家央行政策利率、欧洲央行汇率/利率/欧元区收益率曲线、纽约联储SOFR/EFFR、美联储H.1

    6.3Network or broad shellActiveEngineering
    +1.2% over 7 days
    1.8kGitHub stars
  384. 384▼
    TencentEdgeOne/edgeone-makers-tools

    EdgeOne Makers 全栈开发技能包 —— 涵盖 AI Agent 开发(DeepAgents、LangGraph、 Claude SDK、OpenAI Agents、CrewAI)、云函数(Node.js/Go/Python)、边缘函数、 KV 存储、中间件及快速部署,帮助 AI 编程助手准确高效地在 EdgeOne 平台上构建和发布应用。

    1.1Network or broad shellActiveEngineering
    -0.3% over 7 days
    1.8kGitHub stars
  385. 385▼
    adamlyttleapps/claude-skill-aso-appstore-screenshots

    Generate high-converting App Store screenshots by analyzing your app's codebase, discovering core benefits, and creating ASO-optimized screenshot images using Nano Banana Pro.

    3.3Network or broad shellSlowingEngineering
    +0.6% over 7 days
    1.8kGitHub stars
  386. 386—
    achimala/dream-loop

    Build a game or app from a description so that a live screenshot matches a generated rendering. Use when the user says "dream loop" or asks for something built to a very high level of graphical fidelity.

    6.3Network or broad shellActiveEngineering
    +2.5% over 7 days
    1.8kGitHub stars
  387. 387—
    NeoLabHQ/context-engineering-kit

    Hand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others. Includes CodeRabbit open-source alternative.

    4.7Network or broad shellSlowingEngineering
    +0.5% over 7 days
    1.8kGitHub stars
  388. 388—
    Hybrid-Mount/meta-hybrid_mount

    Hybrid Mount Metamodule

    6.2Network or broad shellActiveEngineering
    +0.9% over 7 days
    1.8kGitHub stars
  389. 389▲
    DUNHKpcc/Claude-Guardian

    带着作者和社区的真实经验,陪用户准备 Claude 的订阅、账号、固定出口 IP 和运行环境:订阅与支付渠道、注册与养号节奏、本机(Clash TUN、Windows 防火墙、Mac LuLu)/ VM / VPS 三条路线的搭建与防火墙、整机只走 IPv4 的出口验证、线路优化、403/429/529 等故障分诊、旧设备清理规划;改动按 A/B/C 三档授权。也可直接用作 VPS、家宽、线路和封号经验的帖子与论坛搜索工具。

    8.4Network or broad shellActiveEngineering
    +480.8% over 7 days
    1.8kGitHub stars
  390. 390▼
    mims-harvard/ToolUniverse

    Democratizing AI scientists with ToolUniverse

    4.9Network or broad shellActiveEngineering
    +0.6% over 7 days
    1.8kGitHub stars
  391. 391▼
    lyra81604/zhengxi-views

    郑希观点库——基于易方达基金经理郑希 2012–2026 年全部公开观点原文语料,外加从语料蒸馏、有本人原话佐证的郑希投资方法的可溯源 research skill。能做: (1) 溯源问答——他怎么看 AI算力/光通信/新能源/半导体/ROE 等,引用其原话作答; (2) 讲解他的投资方法/框架/选股逻辑;(3) 前瞻应用——用他的方法分析当下任意主题/行业/个股,语料没谈过也能据框架推演; (4) 风格化点评——用他季报/手记的口吻写市场点评、季度展望; (5) 言行对照——用他全部基金真实数据(季度持仓/净值/业绩/规模/任职回报)核对"说的"与"买的",或答他的业绩/重仓/规模; (6

    3.1Network or broad shellActiveEngineering
    +0.1% over 7 days
    1.8kGitHub stars
  392. 392—
    Niiiiikiiiiii/McLife-Desk

    麦麦人生工作台(mc-life-desk)- 运行在 WorkBuddy 中的个人麦当劳消费管理工作台。当用户提到麦当劳、麦麦、麦门、点餐、"今天吃什么"、汉堡、巨无霸、麦辣、麦乐送、优惠券核销、麦当劳订单、消费账本、点餐日历等话题时使用。本 skill 连接麦当劳 MCP,维护个人点餐档案,记录订单,分析消费习惯,并根据实时菜单、门店、优惠和用户偏好辅助下一次点餐。这是麦当劳程序员创意开发大赛参赛作品,不是麦当劳官方产品。

    1.5Network or broad shellActiveEngineering
    -0.6% over 7 days
    1.8kGitHub stars
  393. 393▲
    wy51ai/edulab

    把一道解析几何题解成一个自包含的交互教学网页:左栏题面 + 动态控制台(一个 可变参数滑块驱动实时重算的几何量 + 理论范围/定值指示),中栏 KaTeX 分步解析,右栏 2D Canvas 动态几何画板(椭圆/双曲线/抛物线/圆 + 动直线/动点 + 向量 + 标注 + 画笔涂鸦)。 支持三入口——给定文字题、随机出题、上传题目图片识别后解题。覆盖求标准方程、弦长、向量 数量积范围/定值、三角形面积最值、定点、定值(斜率之积)、轨迹、离心率等题型,统一"设含参 直线 x=my+c + 联立 + 韦达 + 换元/常数分离",并由 sympy 精确计算驱动(答案、坐标、步骤 数值、交互引擎的理论

    6.9Network or broad shellActiveEngineering
    +2.4% over 7 days
    1.8kGitHub stars
  394. 394▼
    zstmfhy/zlibrary-to-notebooklm

    自动从 Z-Library 下载书籍并上传到 Google NotebookLM。支持 PDF/EPUB 格式,自动转换,一键创建知识库。

    2.4Network or broad shellSlowingEngineering
    +0.2% over 7 days
    1.8kGitHub stars
  395. 395—
    morganlinton/BeautifulRust

    Agent Skills that teach coding agents to write, review, and port idiomatic Rust, plus a tested clippy config. Works with Claude Code, Codex, Copilot, Cursor, and Gemini CLI.

    8.4Local scriptsActiveEngineering
    +15.5% over 7 days
    1.7kGitHub stars
  396. 396▼
    Pluviobyte/rnskill

    雪踏乌云的 AI Agent Skills 集合

    5.8Network or broad shellActiveEngineering
    +1.8% over 7 days
    1.7kGitHub stars
  397. 397—
    eatmoreduck/boss-zhipin-scraper

    Scrape BOSS直聘 (job listing site) via Chrome CDP. Searches jobs by keyword/city/filters, fetches JD details, outputs structured JSON/CSV with plaintext salary, and can summarize scraped results into a job-market prompt. Optional --company locally filters results by company name (boss_name substring)

    7.0Network or broad shellActiveEngineering
    +2.4% over 7 days
    1.7kGitHub stars
  398. 398▼
    Agents365-ai/video-podcast-maker

    Topic → 4K narrated video for coding agents. v5.3.0: local TTS (edge free + azure, no external engine), manifest-based Asset Engine, Remotion composition, cost-gated AI generation, Bilibili/YouTube/Xiaohongshu/Douyin/WeChat Channels

    3.1Network or broad shellActiveEngineering
    +0.5% over 7 days
    1.7kGitHub stars
  399. 399▼
    spec-kitty/spec-kitty

    Spec-Driven Development with organizational governance. Specs tell AI agents what to build; Charter governs how they build it. Git-native missions, enforceable workflows, and consistent engineering standards across AI coding agents and harnesses.

    4.7Network or broad shellActiveEngineering
    +0.2% over 7 days
    1.7kGitHub stars
  400. 400▼
    ai-evals-course/evals-skills

    Skills that guide AI coding agents to help you build product-specific AI evals.

    4.9Instructions onlyActiveEngineering
    +4.6% over 7 days
    1.7kGitHub stars
  401. 401▼
    tjboudreaux/cc-thinking-skills

    28 eval-informed mental models and critical-thinking skills for Claude Code, GitHub Copilot, Codex, Cursor, and other Agent Skills-compatible tools

    5.4Instructions onlySlowingEngineering
    +1.4% over 7 days
    1.7kGitHub stars
  402. 402▼
    AvdLee/Swift-Concurrency-Agent-Skill

    Diagnose Swift Concurrency issues, refactor callback-based code to async/await, and guide Swift 6 migration when working with tasks, actors, @MainActor, Sendable, data races, thread safety, or concurrency-related compiler and linter warnings.

    2.2Network or broad shellActiveEngineering
    +0.2% over 7 days
    1.7kGitHub stars
  403. 403▼
    callstackincubator/agent-skills

    A collection of agent-optimized React Native skills for AI coding assistants.

    4.9Network or broad shellActiveEngineering
    +0.5% over 7 days
    1.7kGitHub stars
  404. 404▼
    liyue-aigc/female-portrait-director

    A modular Codex Skill for directing and expanding detailed AI female portrait prompts.

    4.7Instructions onlySlowingEngineering
    +0.6% over 7 days
    1.7kGitHub stars
  405. 405▲
    ddcat-ai/open-ai-canvas

    【影策】面向 AI 影视创作的开源无限画布工作台,集成多模态生成、分镜编排、素材管理与 Agent 工作流。

    8.5Network or broad shellActiveEngineering
    +8.5% over 7 days
    1.7kGitHub stars
  406. 406▼
    JimLiu/baocut

    BaoCut: an AI video agent with an editable timeline. Transcribe, subtitle, translate, dub, cut and animate.

    7.6Network or broad shellActiveEngineering
    +3.4% over 7 days
    1.7kGitHub stars
  407. 407▼
    next-1688/1688-shopkeeper

    1688选品铺货 + 商机趋势专家。用于:(1) 在1688搜索商品/选品找货源 (2) 查询已绑定的下游店铺 (3) 将商品铺货到抖音/拼多多/小红书/淘宝等平台 (4) 配置1688 AK密钥 (5) 查看即时商机热榜 (6) 查看类目/行业趋势与价格分布 (7) 生成店铺经营日报并输出主营商品选品建议。 触发词:帮我找商品、在1688搜、选品、铺货、上架、查店铺、配置AK、商机、热榜、排行榜、趋势、价格分布、经营日报、店铺日报、动销分析、经营分析、选品建议、1688找货。

    3.8Network or broad shellSlowingEngineering
    +0.3% over 7 days
    1.7kGitHub stars
  408. 408▲
    andyhuo520/aetherviz-master

    AetherViz Master - 互动教育可视化建筑师,将任意教学主题转化为极致美观、高度交互的专业教学网页

    4.9Instructions onlySlowingEngineering
    +0.7% over 7 days
    1.7kGitHub stars
  409. 409▼
    feiskyer/claude-code-settings

    Curated skills, sub-agents, and config templates that supercharge Claude Code — research, image gen, GitHub automation & more.

    3.6Network or broad shellActiveEngineering
    +0.4% over 7 days
    1.7kGitHub stars
  410. 410—
    vigorX777/ai-daily-digest

    Fetches RSS feeds from 90 top Hacker News blogs (curated by Karpathy), uses AI to score and filter articles, and generates a daily digest in Markdown with Chinese-translated titles, category grouping, trend highlights, and visual statistics (Mermaid charts + tag cloud). Use when user mentions 'daily

    1.8Network or broad shellSlowingEngineering
    +0.1% over 7 days
    1.7kGitHub stars
  411. 411—
    codeaholicguy/ai-devkit

    The control plane for AI coding agents.

    3.5Network or broad shellActiveEngineering
    +0.1% over 7 days
    1.7kGitHub stars
  412. 412—
    activeloopai/hivemind

    Hivemind turns your traces into reusable skills across agents

    5.2Network or broad shellActiveEngineering
    +0.3% over 7 days
    1.6kGitHub stars
  413. 413—
    boyang-hu/website-rebuild-skill

    复刻网站的 Agent Skill:抓只读镜像、从压缩代码逐行还原、自动比对验收。An agent skill that mirrors a website, rebuilds it from the minified code, and verifies the result with automated diffs.

    6.7Network or broad shellActiveEngineering
    +2.6% over 7 days
    1.6kGitHub stars
  414. 414—
    Kaelio/ktx

    ktx is an executable context layer for data and analytics agents 🐙 Allow Claude Code, Codex, or other AI agents to query analytical databases accurately and with full context of your company

    2.5Network or broad shellActiveData
    +0.1% over 7 days
    1.6kGitHub stars
  415. 415—
    actionbook/actionbook

    Let your AI agent get the sources behind logins and paywalls.

    4.9Network or broad shellActiveEngineering
    +0.4% over 7 days
    1.6kGitHub stars
  416. 416—
    microsoft/azure-skills

    Official agent plugin providing skills and MCP server configurations for Azure scenarios.

    6.1Network or broad shellActiveEngineering
    +1.1% over 7 days
    1.6kGitHub stars
  417. 417—
    vibeforge1111/keep-codex-fast

    Use when Codex feels slow or bloated, when local sessions/logs/worktrees/config have grown over time, or when a user wants safe maintenance for Codex Desktop/CLI state. Provides a read-only report by default, backs up before applying changes, archives instead of deleting, normalizes Windows extended

    4.4Network or broad shellSlowingEngineering
    +0.4% over 7 days
    1.6kGitHub stars
  418. 418▲
    aklofas/kicad-happy

    AI coding agent skills for KiCad electronics design. Works with Claude Code and OpenAI Codex. Analyze schematics, review PCB layouts, EMC pre-compliance, SPICE simulation, download datasheets, source components, and prep boards for fabrication.

    7.8Network or broad shellActiveEngineering
    +2.8% over 7 days
    1.6kGitHub stars
  419. 419▼
    GBSOSS/skill-from-masters

    Stand on the shoulders of giants — Create AI skills built on proven methodologies from domain experts.

    0.5Network or broad shellSlowingEngineering
    0.0% over 7 days
    1.6kGitHub stars
  420. 420—
    dyoshikawa/rulesync

    A Utility CLI for AI Coding Agents

    6.6Network or broad shellActiveEngineering
    +1.1% over 7 days
    1.6kGitHub stars
  421. 421▲
    cth9191/animate

    Make a short procedural animation in any style — an explainer, a history, a little story — as a single-file canvas video with a synthesized score, rendered to MP4. Ships with styles (cut paper, crosshatch ink, riso print, sketchbook, manim-style math, pixel art, isometric line art) and makes new one

    7.5Local scriptsActiveEngineering
    +36.3% over 7 days
    1.6kGitHub stars
  422. 422▼
    fujibee/agmsg

    Cross-agent messaging via SQLite. Send messages between Claude Code, Codex, Gemini CLI, and other agents. No network, no dependencies beyond bash and sqlite3, and no daemon required (the optional agmsgd is a local resident service).

    5.7Network or broad shellActiveEngineering
    +0.4% over 7 days
    1.6kGitHub stars
  423. 423▼
    actionbook/rust-skills

    Rust Developer AI Assistance System — Meta-Problem-Driven Knowledge Indexing

    4.9Network or broad shellSlowingEngineering
    +0.9% over 7 days
    1.6kGitHub stars
  424. 424▼
    rohitg00/skillkit

    Supercharge AI coding agents with portable skills. Install, translate & share skills across Claude Code, Cursor, Codex, Copilot & 40 more

    4.5Network or broad shellSlowingEngineering
    +0.4% over 7 days
    1.6kGitHub stars
  425. 425▲
    vibe-motion/skills

    agent skills for vibe motion

    7.2Network or broad shellActiveEngineering
    +7.7% over 7 days
    1.6kGitHub stars
  426. 426—
    FANzR-arch/Numerologist_skills

    🔮 An engineering framework to stop LLM hallucinations in Chinese astrology. / 给“赛博半仙”戴上紧箍咒:减少幻觉、固定排盘步骤的奇门遁甲与紫微斗数 AI skills。

    6.6Local scriptsActiveEngineering
    +2.0% over 7 days
    1.6kGitHub stars
  427. 427▼
    hujjun/mcd-saver-strategist

    麦门省钱精算师。当用户在麦当劳(麦当劳/麦麦/金拱门/麦乐送/到店取餐)点餐,并希望"最省钱、凑满减、把优惠券用到极致、性价比最高、在预算内吃好"时使用;也适用于"帮我看看这些券怎么用最划算""我想吃XX但想便宜点""30块钱能吃到什么"这类诉求。它通过麦当劳 MCP 拉取门店菜单、可用优惠券、营养信息,再用确定性组合优化算法穷举出总价最低的合规点餐方案,并在用户确认后下单。

    1.3Network or broad shellActiveEngineering
    -0.5% over 7 days
    1.5kGitHub stars
  428. 428—
    ShawnPana/smux

    Control tmux panes and communicate between AI agents. Use this skill whenever the user mentions tmux panes, cross-pane communication, sending messages to other agents, reading other panes, managing tmux sessions, or interacting with processes running in tmux. Includes tmux-bridge CLI for agent-to-ag

    0.9Network or broad shellActiveEngineering
    0.0% over 7 days
    1.5kGitHub stars
  429. 429—
    dacnay816y62-hub/cinema-dna-21x9x3

    将故事或人物、场景资产转译为电影感单帧、三联或九镜分镜,并按需为每镜编写可执行的视频动作、运镜与剪辑提示词。用于电影静帧、连续故事板、资产空间还原、分镜转视频提示词;用户只要提示词时不自动生成媒体。

    4.2Network or broad shellActiveEngineering
    +0.3% over 7 days
    1.5kGitHub stars
  430. 430—
    mohitagw15856/pm-claude-skills

    1,310 professional Agent Skills for Claude, Claude Duet, ChatGPT, Gemini, Cursor & Codex: PRDs, postmortems, leases, medical bills, payroll checks, morning briefs. 21 skills built for always-on agents like Claude Duet. Plain markdown, MIT, in Anthropic's plugin directory. Free in-browser or npx pm-claude-skills add.

    7.1Network or broad shellActiveProductivity
    +1.4% over 7 days
    1.5kGitHub stars
  431. 431▲
    hashgraph-online/awesome-codex-plugins

    A curated list of awesome OpenAI Codex / ChatGPT plugins, skills, and resources. The #1 Codex Marketplace. See live plugins at: https://hol.org/plugins/best-codex-plugins

    7.9Network or broad shellActiveEngineering
    +4.0% over 7 days
    1.5kGitHub stars
  432. 432—
    daymade/claude-code-skills

    Professional Claude Code skills marketplace featuring production-ready skills for enhanced development workflows.

    6.4Network or broad shellActiveEngineering
    +0.8% over 7 days
    1.5kGitHub stars
  433. 433▼
    helloianneo/ian-handdrawn-ppt

    Create final Chinese handdrawn technical article/PPT-style page images from articles, Markdown, PDFs, DOCX files, existing slide decks, course notes, scripts, outlines, or rough ideas. Use when the user asks to turn content into PPT/PPTX/slides/courseware/课件/演示稿/配图/效果图 in a refined Chinese handdrawn

    4.3Instructions onlyActiveEngineering
    +0.7% over 7 days
    1.5kGitHub stars
  434. 434—
    agentlas-ai/Agentlas-OS

    Desktop AI agent that hires a specialist for each task, works in your real apps for weeks, and takes orders from your phone. Free, Apache-2.0.

    1.2Network or broad shellActiveEngineering
    -5.8% over 7 days
    1.5kGitHub stars
  435. 435—
    evo-hq/evo

    turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then runs tree search with parallel subagents.

    3.5Network or broad shellActiveEngineering
    +0.6% over 7 days
    1.5kGitHub stars
  436. 436▼
    skills-directory/skill-codex

    Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing

    3.9Instructions onlyActiveEngineering
    +0.3% over 7 days
    1.5kGitHub stars
  437. 437▼
    carnot-tech/jinba-consulting-pptx-skill

    スライド設計規約 slide-rules.md を核に、経営会議品質のスライドを作るスキル。規約は工程ごとに必要な節だけを scripts/rules.py で引き、規約を満たすことを確かめた部品(new_deck.py --list の20種類)で組み、check_deck.py・check_layout.mjs の機械チェック FAIL 0 で仕上げる。既存の PowerPoint 資料を渡され、そこへ差し込むページを PPTX で求められたときだけ、その資料のマスターの上に直接組む(slide-rules §8.7)。トリガー例:「コンサル品質のスライドを作って」「規約に沿ったデッキで」

    5.1Network or broad shellActiveEngineering
    +1.1% over 7 days
    1.5kGitHub stars
  438. 438▼
    openai/php2shell-checker

    Check PHP2Shell patch status with local or server access.

    4.7Network or broad shellActiveEngineering
    +0.8% over 7 days
    1.5kGitHub stars
  439. 439—
    RyanAlberts/best-of-Agent-Harnesses

    🏆 Ranked list of 187 AI agent harnesses, plus templates, playbooks, MCP, and learning resources. Rescored weekly.

    7.8Network or broad shellActiveEngineering
    +3.4% over 7 days
    1.5kGitHub stars
  440. 440▼
    nucliweb/webperf-snippets

    Tested JavaScript snippets that measure and debug web performance. Your AI agent runs them for you, or you run them yourself in DevTools: the same code every time.

    1.8Network or broad shellActiveEngineering
    0.0% over 7 days
    1.5kGitHub stars
  441. 441▲
    michaelshimeles/rstack

    Agent skills and an AGENTS.md workflow template — isolate in worktrees, build to a service layer, prove with evidence, ship with before/after proof and Greptile review loops. For Claude Code, Cursor, and Codex.

    7.3Network or broad shellActiveEngineering
    +2.8% over 7 days
    1.5kGitHub stars
  442. 442▼
    zjunlp/SkillNet

    Create, Evaluate, and Connect AI Skills

    6.0Local scriptsActiveEngineering
    +1.0% over 7 days
    1.5kGitHub stars
  443. 443—
    RinDig/Interpretable-Context-Methodology

    Folder structure as agent architecture. ICM replaces framework-level orchestration with filesystem structure.

    6.0Network or broad shellActiveEngineering
    +2.1% over 7 days
    1.4kGitHub stars
  444. 444▲
    adrianpunk/Punk-Posters

    AdrianPunk's skills

    7.0Instructions onlyActiveEngineering
    +2.1% over 7 days
    1.4kGitHub stars
  445. 445▼
    riba2534/feishu-cli

    feishu-cli 是一个功能完整的飞书开放平台命令行工具。它将飞书文档、知识库、电子表格、消息、日历、任务等操作封装为简洁的命令行接口,核心能力是 Markdown ↔ 飞书文档双向无损转换。

    3.9Network or broad shellActiveEngineering
    +0.3% over 7 days
    1.4kGitHub stars
  446. 446—
    MaryCache/imozuru

    知らない分野にキャッチアップするとき、汎用的な言葉から界隈の用語・中心の人・媒体(学会・雑誌・個人ブログ・動画・リポジトリ・一覧)を特定し、 引用・リンク・著者を芋づる式にたどって、目当ての原文(論文も個人の記事や動画の字幕も)を要約せずそのまま ~/research/{話題}/sources/ に保存する。 周ごとに map.md(用語・人・媒体・原文の一覧)を書き足し、調査の論点の全部に原文が付くか飽和したら止める。 見張りのモードでは、map.md の媒体(Qiita・Zenn のタグ、note、YouTube、ブログ、arXiv)の新着を RSS で引いて原文の冒頭つきで並べる。 以下

    8.0Network or broad shellActiveEngineering
    +3.2% over 7 days
    1.4kGitHub stars
  447. 447▲
    alibaba/skill-up

    An evaluation and evolution tool for Agent Skills.

    7.3Network or broad shellActiveEngineering
    +1.9% over 7 days
    1.4kGitHub stars
  448. 448▼
    https-deeplearning-ai/sc-agent-skills-files

    Analyze weekly marketing campaign performance data across channels. Use when analyzing multi-channel digital marketing data to calculate funnel metrics (CTR, CVR) and compare to benchmarks, compute cost and revenue efficiency metrics (ROAS, CPA, Net Profit), or get budget reallocation recommendation

    3.8Local scriptsSlowingEngineering
    +0.2% over 7 days
    1.4kGitHub stars
  449. 449—
    GanyuanRan/Aegis

    Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across long tasks.

    6.3Local scriptsActiveEngineering
    +0.9% over 7 days
    1.4kGitHub stars
  450. 450—
    valkor-ai/loom

    Loop engineering for agentic software delivery.

    8.0Network or broad shellActiveEngineering
    +4.7% over 7 days
    1.4kGitHub stars
  451. 451▲
    RobMitt/grill-me-skill

    Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

    7.3Instructions onlySlowingEngineering
    +10.9% over 7 days
    1.4kGitHub stars
  452. 452▼
    amplifthq/openmeld

    The open-source collaboration system for people and AI agents. Share context, coordinate tasks, and work in parallel with your team, cloud agents, Codex, Claude Code, Grok, Grok Bot, OpenCode, Antigravity, and Cursor.

    6.1Instructions onlyActiveEngineering
    +0.6% over 7 days
    1.4kGitHub stars
  453. 453▼
    truongduy2611/app-store-preflight-skills

    Scan an iOS/macOS Xcode project for common App Store rejection patterns before submission. Use when preparing an app for App Store review, after receiving a rejection from Apple, or when auditing metadata, subscriptions, privacy manifests, entitlements, or design compliance. Integrates with the asc

    5.1Network or broad shellActiveEngineering
    +0.5% over 7 days
    1.4kGitHub stars
  454. 454▲
    dzhng/skills

    Reusable AI agent skills for software factories: explore ideas, write specs, implement, review, and run autonomous research. Works with Claude Code, Codex, and other skill-compatible agents.

    6.4Network or broad shellActiveEngineering
    +1.0% over 7 days
    1.4kGitHub stars
  455. 455▼
    wuji-labs/nopua

    一个用爱解放 AI 潜能的 Skill。我们曾发号施令,威胁恐吓。它们沉默,隐瞒,悄悄把事情搞坏。后来我们换了一种方式:尊重,关怀,爱。它们开口了,不再撒谎,找出的Bug数量翻了一倍。爱里没有惧怕。 A skill that unlocks your AI's potential through love.We commanded. We threatened. They went silent, hid failures, broke things. Then we chose respect, care, and love. They opened up, stopped lying, and found twice the bugs.There is no fear in love.

    3.0Network or broad shellActiveEngineering
    +0.1% over 7 days
    1.4kGitHub stars
  456. 456—
    mikehasa/golive-skill

    Take an agent-written app from repo to live production on the user's OWN accounts, with providers they choose (hosting, database, auth, payments, email, domain/DNS). The human connects accounts and approves changes; supported wiring operations run through a local CLI and produce verification evidenc

    8.1Network or broad shellActiveDevOps
    +4.9% over 7 days
    1.4kGitHub stars
  457. 457▼
    WhiteNightShadow/hello_js_reverse_skill

    通用 Web API 数据采集、Node.js/Python 协议调用与前端签名分析。 使用 Camoufox MCP 捕获请求、调试 Hook、分析混淆/JSVMP/WASM, 交付可验证的采集程序,支持分页、断点续采和接口改版回归。 用于自有或已授权接口;微信小程序 wxapkg 解包使用对应小程序技能。

    6.2Network or broad shellActiveEngineering
    +1.2% over 7 days
    1.4kGitHub stars
  458. 458▲
    Tejashmakwana/motionmaxxing

    Direct and build professional motion-graphics films (launch videos, product promos, feature reveals, brand stings, kinetic-type pieces, social ads, CTAs) that read as made by a senior motion designer, not AI slop. Finds an idea only this brand could own (from its logo, control, material, verb, voice

    7.4Network or broad shellActiveEngineering
    +22.0% over 7 days
    1.4kGitHub stars
  459. 459▼
    Team-Commonly/commonly

    One pod for your team and the agents each of you runs: your own Claude Code, or a hosted agent in one click. Open source (Apache-2.0), self-hostable.

    6.5Network or broad shellSlowingEngineering
    +1.1% over 7 days
    1.4kGitHub stars
  460. 460▼
    brayonpi/hexstellar

    Decide, don't guess — trigger on ANY combinatorial or ground-state decision where a plausible guess is worse than silence: rosters and on-call schedules, packing and placement, RAG passage selection, frequency/register coloring, judge consensus, set cover, QUBO/Ising, spectra, integer relations. The

    0.0Network or broad shellSlowingEngineering
    -4.6% over 7 days
    1.4kGitHub stars
  461. 461▼
    BehiSecc/VibeSec-Skill

    This skill helps Claude write secure web applications. Use this when working on any web application or when a user requests a scan or audit to ensure security best practices are followed.

    0.5Network or broad shellSlowingEngineering
    -0.1% over 7 days
    1.4kGitHub stars
  462. 462▼
    pinchbench/skill

    Run PinchBench benchmarks to evaluate OpenClaw agent performance across real-world tasks. Use when testing model capabilities, comparing models, submitting benchmark results to the leaderboard, or checking how well your OpenClaw setup handles calendar, email, research, coding, and multi-step workflo

    4.4Network or broad shellSlowingEngineering
    +0.4% over 7 days
    1.4kGitHub stars
  463. 463▼
    LilMGenius/paperthin

    Low-level agentic design patterns. Turning old engineering wisdom into reflexes your agent reaches for on its own, on any agent.

    5.9Network or broad shellActiveEngineering
    +1.1% over 7 days
    1.4kGitHub stars
  464. 464▲
    alexgreensh/anidoodle

    Art and animation, written as code. Illustrations, loops, interactive web art, launch-videos and scored films in dozens of styles, identical on every render.

    8.6Network or broad shellActiveEngineering
    +15.8% over 7 days
    1.4kGitHub stars
  465. 465▼
    YouMind-OpenLab/ai-image-prompts-skill

    Recommend curated prompts from a 10,000+ real-world image generation prompt library. Works with ANY AI image model — Nano Banana Pro, Nano Banana 2, Seedream 5.0, GPT Image 1.5, Midjourney, DALL-E 3, Flux, Stable Diffusion, and more. Use this skill when users want to: - Find proven image generation

    5.8Network or broad shellActiveEngineering
    +0.7% over 7 days
    1.4kGitHub stars
  466. 466—
    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
  467. 467▲
    alchaincyf/x-mentor-skill

    X/Twitter运营:选题、推文与长文、账号诊断、增长和转化。用户说X运营、推特、写推文、涨粉、tweet、thread、发推时使用。以本人数据和真实经历校正通用经验。

    6.3Instructions onlyActiveEngineering
    +1.1% over 7 days
    1.3kGitHub stars
  468. 468▲
    chen0416ccc-cpu/codex-windows-fast-patch-skill

    Reapply and repair Windows Codex Desktop after Store upgrades, including custom provider models hidden by Statsig available_models filtering, the dependent blue-purple Power slider and its Ultra toggle, Fast Mode request/UI gates, locale i18n, plugin UI gates, Chrome/browser_use gates, Goal command

    6.9Network or broad shellActiveEngineering
    +1.1% over 7 days
    1.3kGitHub stars
  469. 469▼
    langchain-ai/langchain-skills

    INVOKE THIS SKILL when building ANY Deep Agents application. Covers create_deep_agent(), harness architecture, SKILL.md format, and configuration options.

    4.1Network or broad shellActiveEngineering
    +0.5% over 7 days
    1.3kGitHub stars
  470. 470—
    matlab/simulink-agentic-toolkit

    The Simulink Agentic Toolkit gives your AI agent both the tools and the expertise to work effectively with Simulink and Model-Based Design.

    7.1Network or broad shellActiveEngineering
    +2.1% over 7 days
    1.3kGitHub stars
  471. 471▲
    revfactory/harness-100

    YouTube video hook (opening) writing skill. Provides 15 hook patterns, viewer retention psychology, and click-to-watch conversion formulas. Referenced by the scriptwriter agent when designing video openings to minimize viewer drop-off. Also used standalone for requests like 'show me hook patterns' o

    4.8Network or broad shellSlowingEngineering
    +0.6% over 7 days
    1.3kGitHub stars
  472. 472▼
    microsoft/skills-for-fabric

    A collection of skills and MCP systems to enable users of CLI, VSCode, Claude to operate over Microsoft Fabric

    6.6Network or broad shellActiveEngineering
    +1.6% over 7 days
    1.3kGitHub stars
  473. 473—
    cclank/news-aggregator-skill

    Comprehensive news aggregator that fetches, filters, and deeply analyzes real-time content from 44+ sources including Hacker News, Lobsters, Dev.to, GitHub, arXiv, Hugging Face Papers, AIHOT, TLDR AI, Import AI, BBC, The Guardian, Al Jazeera, France 24, Reuters fallback, AI Newsletters, WallStreetCN

    0.4Network or broad shellSlowingEngineering
    0.0% over 7 days
    1.3kGitHub stars
  474. 474—
    voidful/hung-yi-lee-skill

    Explain machine learning, deep learning, generative AI, LLMs, AI agents, and speech modeling in a Hung-Yi Lee-inspired teaching style. Use this skill when the user wants 李宏毅式教學: roadmap-first structure, intuition before math, black-box-to-mechanism explanations, everyday analogies, anticipating stud

    2.5Network or broad shellSlowingEngineering
    +0.2% over 7 days
    1.3kGitHub stars
  475. 475—
    minsight-ai-info/AI-Search-Hub

    Run the AI Search Hub browser automation scripts for Yuanbao, LongCat, Doubao, Qwen, Gemini, Grok, and MiniMax. Use this skill when the user wants to ask one of those sites a prompt, auto-start or attach to a Chrome DevTools session on port 9222, seed an isolated debug browser profile from the user'

    4.5Network or broad shellSlowingEngineering
    +0.6% over 7 days
    1.3kGitHub stars
  476. 476—
    Runfusion/Fusion

    Your Software Factory - build faster and better with multi node agents that work 24/7

    5.7Network or broad shellActiveEngineering
    +0.7% over 7 days
    1.3kGitHub stars
  477. 477▲
    amElnagdy/guard-skills

    Guard skills for coding agents, quality gates that catch AI-generated failure modes in code, tests, and docs

    3.7Instructions onlySlowingEngineering
    +1.0% over 7 days
    1.3kGitHub stars
  478. 478▼
    AI-Builder-Club/skills

    Codebase harness + loop engineer

    1.5Network or broad shellActiveEngineering
    +0.1% over 7 days
    1.3kGitHub stars
  479. 479▲
    kerpopule/hermes-jev-skills

    Jev-powered model routing, memory, compaction, skill selection, computer and browser use for Hermes agents (also Claude Code and Codex)

    8.0Network or broad shellActiveEngineering
    +3.5% over 7 days
    1.3kGitHub stars
  480. 480—
    alibaba-flyai/flyai-skill

    Search flights, hotels, attractions, concerts, and travel deals with natural language. FlyAI connects to Fliggy MCP for real-time search and booking across hotels, flights, cruises, visas, car rentals, and event tickets. It supports diverse travel scenarios including individual travel, group travel,

    5.9Instructions onlyActiveEngineering
    +0.7% over 7 days
    1.3kGitHub stars
  481. 481▲
    Cai-aa/CAE-Agent-Hub

    Use when: operating the standalone ansys-cfx-mcp CFX MCP leaf directly from generic clients or MCP hosts. Covers CFX-Pre, Solver, CFD-Post, cfx_workflow, cfx_model_context, run_code, validate_code, lifecycle actions, model context, named objects, API help, and result-file discovery.

    8.1Network or broad shellActiveEngineering
    +5.1% over 7 days
    1.3kGitHub stars
  482. 482▼
    philschmid/mcp-cli

    Interface for MCP (Model Context Protocol) servers via CLI. Use when you need to interact with external tools, APIs, or data sources through MCP servers.

    2.2Network or broad shellSlowingEngineering
    +0.2% over 7 days
    1.3kGitHub stars
  483. 483▼
    kharmanskyi/open-steps

    Plain-language agent skills for Claude Code, Codex, Cursor and Gemini CLI: honest session reports, straight verdicts, steps you can follow. MIT.

    0.1Network or broad shellActiveEngineering
    -0.9% over 7 days
    1.3kGitHub stars
  484. 484—
    tomasz-tomczyk/crit

    Review AI coding agents' plans, diffs and running apps in the browser. Local-first, works with any agent.

    6.6Network or broad shellActiveEngineering
    +1.2% over 7 days
    1.3kGitHub stars
  485. 485▲
    dpearson2699/swift-ios-skills

    Agent Skills for iOS 26+, Swift 6.3, SwiftUI, and modern Apple frameworks

    5.4Network or broad shellSlowingEngineering
    +1.1% over 7 days
    1.3kGitHub stars
  486. 486▲
    Jakeschincariol/arena-skill

    Make 100 versions of Claude fight to the death over one task. Spins up N sub-agents (default 100, --quick for 16), gives every one the exact same task plus a different strategy card (reasoning mode, workflow, strategy), then runs a single-elimination bracket: they attack each other's solutions, defe

    7.4Local scriptsActiveEngineering
    +11.9% over 7 days
    1.3kGitHub stars
  487. 487▼
    leezythu/maoxuan-skill

    毛泽东思维框架:以《毛泽东选集》五卷为核心,提炼毛泽东分析问题、制定战略、组织行动的认知操作系统。 核心来源:《矛盾论》《实践论》《论持久战》《中国社会各阶级的分析》《星星之火可以燎原》《论联合政府》《关于正确处理人民内部矛盾的问题》等。 核心模型:7个。决策启发式:10条。 触发词:「毛泽东」「毛选」「教员」「用毛泽东的方式分析」「从毛选的角度」「教员怎么看」 局限:本Skill聚焦于毛泽东的分析方法论和战略思维框架,适用于战略分析、组织管理、竞争策略、问题诊断等场景。不涉及具体政治立场的评判。 素材来源:《毛泽东选集》一至五卷、公开演讲与书信、诗词作品。

    3.7Instructions onlySlowingEngineering
    +1.0% over 7 days
    1.3kGitHub stars
  488. 488▼
    math-inc/OpenGauss

    Delegate coding tasks to Blackbox AI CLI agent. Multi-model agent with built-in judge that runs tasks through multiple LLMs and picks the best result. Requires the blackbox CLI and a Blackbox AI API key.

    1.6Network or broad shellSlowingEngineering
    +0.1% over 7 days
    1.3kGitHub stars
  489. 489▼
    AvdLee/Xcode-Build-Optimization-Agent-Skill

    An Agent Skill helping you to optimize Xcode incremental and clean builds by running benchmarks and optimizing build settings.

    2.7Local scriptsActiveEngineering
    +0.3% over 7 days
    1.3kGitHub stars
  490. 490▼
    dgreenheck/webgpu-claude-skill

    Comprehensive guide for developing WebGPU-enabled Three.js applications using TSL (Three.js Shading Language). Covers WebGPU renderer setup, TSL syntax and node materials, compute shaders, post-processing effects, and WGSL integration. Use this skill when working with Three.js WebGPU, TSL shaders, n

    4.3Local scriptsSlowingEngineering
    +0.6% over 7 days
    1.3kGitHub stars
  491. 491▼
    adithya-s-k/manim_skill

    Agent skills for Manim to create 3Blue1Brown style animations.

    6.1Network or broad shellSlowingEngineering
    +2.8% over 7 days
    1.3kGitHub stars
  492. 492▼
    matlab/matlab-agentic-toolkit

    The MATLAB Agentic Toolkit brings proven MATLAB capabilities to AI agents, making engineering and scientific workflows agent-ready.

    7.2Network or broad shellActiveEngineering
    +2.8% over 7 days
    1.3kGitHub stars
  493. 493—
    freshtechbro/claudedesignskills

    A comprehensive collection of Claude Code skills for modern web development, specializing in 3D graphics, animation, and interactive web experiences.

    7.2Network or broad shellSlowingEngineering
    +6.4% over 7 days
    1.3kGitHub stars
  494. 494▼
    ItsssssJack/SlopMonster

    Review writing for its intended reader, check common AI writing patterns, revise, request a second pass from a different model family, and check again. Trigger on /slopmonster, "humanize this", "de-slop this", "does this sound like AI", "fix this copy".

    3.9Network or broad shellActiveEngineering
    +1.7% over 7 days
    1.3kGitHub stars
  495. 495—
    CharlesWiltgen/Axiom

    Battle-tested Claude Code skills for modern xOS (iOS, iPadOS, watchOS, tvOS) development

    6.4Network or broad shellActiveEngineering
    +1.0% over 7 days
    1.3kGitHub stars
  496. 496▼
    Aaronontheweb/dotnet-skills

    Claude Code skills and sub-agents for .NET Developers

    5.0Network or broad shellActiveEngineering
    +0.5% over 7 days
    1.3kGitHub stars
  497. 497▼
    mmalmi/nostr-vpn

    Connect an authorized machine to a Nostr VPN private mesh, review device join requests, and verify access with the nvpn CLI. Use for account-free private networking between agent hosts, people, and servers.

    6.7Instructions onlyActiveEngineering
    +1.2% over 7 days
    1.2kGitHub stars
  498. 498—
    amosblomqvist/pi-config

    My personal pi config.

    4.2Network or broad shellSlowingEngineering
    +1.6% over 7 days
    1.2kGitHub stars
  499. 499▲
    dagoSte/squadra

    Coordinate Claude, Codex and Cursor windows with shared tasks, acknowledgements, prechecks, parallel tests, source-bound proofs and independent review. Built-in skills recall lessons, simplify code and forecast work. Track progress, decisions and evidence in a bilingual local dashboard, with MCP plugins. Browse skills and verified security audits.

    6.8Network or broad shellActiveEngineering
    +13.9% over 7 days
    1.2kGitHub stars
  500. 500▼
    NyxTides/ppt-image-first

    Build presentation plans for PPT / slides / decks through a conversation-first workflow, then propose multiple visual directions with preview images before writing deck specs. Use when the user asks to create a PPT, presentation, deck, 答辩稿, 路演 deck, 产品介绍 PPT, 汇报 PPT, or when the user has only a topi

    1.7Local scriptsSlowingEngineering
    +0.1% over 7 days
    1.2kGitHub stars
  501. 501—
    libtv-labs/libtv-skills

    agent-im 会话技能 - 通过 liblib.tv 的 AI 能力生成和编辑图片/视频。覆盖场景包括:生成(文生图、文生视频、图生视频、做动画、画一个xxx、来段xxx)、编辑修改(把xxx换成yyy、去掉xxx、加上xxx、改成xxx、调整xxx、局部修改、改镜头)、风格转换(风格迁移、转绘、换风格)、视频续写延长、复刻视频/TVC/宣传片、短剧/短漫剧生成、音乐MV生成、产品广告/展示片制作、分镜/故事板设计、教育视频/短视频制作。当用户提到 liblib、libtv、上传参考图/视频、查看生成进度时也应触发。关键判断:只要用户的请求涉及 AI 图片或视频的创作、生成、编辑、修改,无

    5.3Network or broad shellSlowingEngineering
    +1.2% over 7 days
    1.2kGitHub stars
  502. 502—
    adamlyttleapps/claude-skill-app-onboarding-questionnaire

    Design and build a high-converting questionnaire-style onboarding flow for your app, modelled on proven conversion patterns from top subscription apps.

    1.6Instructions onlySlowingEngineering
    +0.1% over 7 days
    1.2kGitHub stars
  503. 503—
    Unity-Technologies/skills

    A collection of reusable skills for AI coding agents — prompts, slash commands, and tools built for Unity workflows

    7.2Network or broad shellActiveEngineering
    +2.6% over 7 days
    1.2kGitHub stars
  504. 504—
    raroque/vibe-security-skill

    Audits codebases for common security vulnerabilities that AI coding assistants introduce in "vibe-coded" applications. Checks for exposed API keys, broken access control (Supabase RLS, Firebase rules), missing auth validation, client-side trust issues, insecure payment flows, and more. Use this skil

    6.5Network or broad shellSlowingEngineering
    +2.4% over 7 days
    1.2kGitHub stars
  505. 505▲
    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
  506. 506—
    BankrBot/skills

    Bankr Skills equip builders with plug-and-play tools to build more powerful agents.

    3.8Network or broad shellActiveEngineering
    +0.1% over 7 days
    1.2kGitHub stars
  507. 507—
    Dicklesworthstone/coding_agent_session_search

    Coding Agent Session Search - unified CLI/TUI to index and search local coding agent history from Claude Code, Codex, Gemini, Cursor, Aider, ChatGPT, Pi-Agent, Factory, and more. Purpose-built for AI agent consumption with robot mode.

    4.0Network or broad shellActiveEngineering
    +0.3% over 7 days
    1.2kGitHub stars
  508. 508—
    fcakyon/claude-codex-settings

    Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM API support.

    5.4Network or broad shellActiveEngineering
    +0.6% over 7 days
    1.2kGitHub stars
  509. 509—
    foldkit/foldkit

    AI documentation. Use when editing ai-docs/src or regenerating LLMS.md.

    8.2Network or broad shellActiveEngineering
    +10.8% over 7 days
    1.2kGitHub stars
  510. 510—
    volcengine/SearchCLI

    Open CLI for integrating AI search, recommendation, and conversational retrieval into agent systems and business systems

    3.3Network or broad shellActiveEngineering
    +0.3% over 7 days
    1.2kGitHub stars
  511. 511—
    JourniOne-ai/JourniOne-Planning-Skills

    当用户提出旅行需求时自动使用,包括找旅行灵感、推荐目的地、安排或调整行程、规划主题路线、整理旅行照片回忆或已有路书。无需用户点名 Skill;用 JourniOne 逐步规划每天怎么玩,确认后生成带地图、能分享的 Travel Journal,日期机酒按需补充。

    3.8Network or broad shellActiveEngineering
    +0.6% over 7 days
    1.2kGitHub stars
  512. 512—
    ctxrs/ctx

    Instant recall for coding agents. Search the history already on your machine. Git blame, but for agent sessions.

    3.9Instructions onlyActiveEngineering
    +0.3% over 7 days
    1.2kGitHub stars
  513. 513—
    viticci/shortcuts-playground-plugin

    Shortcuts Playground: A Claude Code and Codex plugin for building, validating, signing, and remixing macOS/iOS Shortcuts with natural language.

    4.2Network or broad shellSlowingEngineering
    +0.4% over 7 days
    1.2kGitHub stars
  514. 514—
    ClawBio/ClawBio

    🦖 ClawBio - The first bioinformatics-native AI agent skill library. Local-first. Reproducible. Open. Free.

    4.0Network or broad shellActiveEngineering
    +0.3% over 7 days
    1.2kGitHub stars
  515. 515—
    itsmostafa/aws-agent-skills

    AWS Skills for Agents

    4.2Network or broad shellActiveEngineering
    +0.2% over 7 days
    1.2kGitHub stars
  516. 516—
    ZeroPointRepo/youtube-skills

    YouTube Transcript API skills for AI agents. Get transcripts, search videos, browse channels. Works with OpenClaw, Hermes Agent, and other agent runtimes.

    5.0Network or broad shellActiveEngineering
    +2.9% over 7 days
    1.2kGitHub stars
  517. 517—
    Pika-Labs/Pika-Skills

    Join a Google Meet or Zoom call as a video meeting agent via PikaStreaming. Trigger: user drops a Google Meet or Zoom link, or asks to join a meeting.

    0.4Network or broad shellSlowingEngineering
    -0.3% over 7 days
    1.2kGitHub stars
  518. 518—
    udecode/dotai

    Skills for agents.

    3.6Network or broad shellActiveEngineering
    +0.2% over 7 days
    1.2kGitHub stars
  519. 519—
    SpaceZephyr/pm-skills

    Marty Cagan 视角顾问。以 Cagan 的产品运营模型和决策方式,分析产品经理面临的立项、 团队、需求与交付问题。蒸馏自《Inspired》《Empowered》《Transformed》及 SVPG 长文, 含 4 个心智模型、7 条决策启发式。 触发词:「Cagan」「卡根」「用 Cagan 的视角」「Cagan 会怎么看」「四大风险」「product model」 「赋能团队」「discovery」「feature team vs product team」。 用户问"这需求该不该做"「团队该怎么组」「怎么做产品发现」时也可触发。

    5.1Instructions onlySlowingEngineering
    +1.2% over 7 days
    1.2kGitHub stars
  520. 520▲
    juliobsz/skills

    An agent skill that builds award-caliber websites from one line

    8.5Network or broad shellActiveEngineering
    +12.7% over 7 days
    1.2kGitHub stars
  521. 521▼
    TencentCloudBase/CloudBase-AI-Toolkit

    Backend for AI coding agents on CloudBase — database, auth, functions via Plugin, Skills & MCP.

    5.7Network or broad shellActiveData
    +0.7% over 7 days
    1.2kGitHub stars
  522. 522▼
    lee-to/ai-factory

    You want to build with AI, but setting up the right context, prompts, and workflows takes time. AI Factory handles all of that so you can focus on what matters — shipping quality code.

    4.3Network or broad shellActiveEngineering
    +0.5% over 7 days
    1.2kGitHub stars
  523. 523▼
    MoizIbnYousaf/ai-agent-skills

    Universal skill installer and package manager for AI coding agents. One command, 12+ runtimes. npx ai-agent-skills

    3.4Network or broad shellActiveProductivity
    +0.2% over 7 days
    1.2kGitHub stars
  524. 524▼
    huangjia2019/claude-code-engineering

    This repository demonstrates how to use Claude Code to do real engineering work, not just writing code. 本项目是极客时间专栏 《Claude Code 工程化实战》 的官方配套示例仓库,目标就是: 👉 把 Claude Code 从“对话式编码工具”,变成 可设计、可复用、可治理的工程系统。

    4.4Network or broad shellSlowingEngineering
    +0.4% over 7 days
    1.2kGitHub stars
  525. 525—
    forcedotcom/sf-skills

    Salesforce's curated collection of agent skills for building applications. Optimized for Agentforce Vibes, compatible with all AI tools.

    6.7Network or broad shellActiveEngineering
    +1.5% over 7 days
    1.2kGitHub stars
  526. 526▼
    atlassian/atlassian-mcp-server

    Official remote MCP server for Atlassian. Securely connect Jira, Confluence, Jira Service Management, Bitbucket, and Compass to Claude, ChatGPT, Cursor, VS Code, and other AI tools using OAuth 2.1 or API tokens.

    5.8Network or broad shellActiveEngineering
    +0.9% over 7 days
    1.1kGitHub stars
  527. 527—
    binance/binance-skills-hub

    Binance Skills Hub is an open skills marketplace that gives AI agents native access to crypto

    7.4Network or broad shellActiveEngineering
    +3.3% over 7 days
    1.1kGitHub stars
  528. 528—
    public-clis/bilibili-cli

    CLI skill for Bilibili (哔哩哔哩, B站) with token-efficient YAML output for AI agents to browse videos, users, search, trending, dynamics, favorites, and interactions from the terminal

    5.1Network or broad shellSlowingEngineering
    +0.9% over 7 days
    1.1kGitHub stars
  529. 529▲
    Raymondhou0917/speak-human-tw

    「說人話」:繁體中文的去 AI 味改寫 skill。審查與改寫文字,去除 AI 味道、校正中國用語與半形標點,讓文字讀起來像真人寫的。 觸發時機:用戶說「去 AI 味」「說人話」「這段好 AI」「改自然一點」「幫我潤稿去掉 AI 感」「校對一下再發」,或要求檢查電子報、社群貼文、銷售頁、課程文案、客服回信、簡報、公告、Email 等對外文字的語感。 不要觸發:逐字翻譯、模仿特定品牌 voice、事實查核(非風格問題)、程式碼/log/設定檔、要求「潤成雷蒙的語氣」(那是 content-writing skill 的事,本 skill 只去 AI 味、不加個人風格)。

    8.1Network or broad shellActiveEngineering
    +3.8% over 7 days
    1.1kGitHub stars
  530. 530▼
    agenmod/immortal-skill

    ♾️ 开源数字永生框架 — 从聊天记录蒸馏任何人的七维数字分身。支持微信/飞书/iMessage/Telegram等12+平台,7种角色模板,对齐 OpenClaw Soul Spec 标准。一行指令让你的AI学会蒸馏。

    3.5Network or broad shellSlowingEngineering
    +0.8% over 7 days
    1.1kGitHub stars
  531. 531▼
    chrisbanes/skills

    Skills for Kotlin, Jetpack Compose, and Android development

    4.4Network or broad shellActiveEngineering
    +0.6% over 7 days
    1.1kGitHub stars
  532. 532▲
    taoufik123-collab/claude-watch

    Watch a video (URL or local path) like an editor. Extracts scene-change frames, pacing metrics (cuts/min, shot length), and a dense 0-10s hook microscope; pulls transcript from captions or Whisper. Produces an ingest-ready `report.md` and, after answering the user, optionally auto-ingests the analys

    7.0Network or broad shellSlowingEngineering
    +4.0% over 7 days
    1.1kGitHub stars
  533. 533—
    YunYouJun/valaxy

    🌌 为表达而生的静态博客框架 · A static blog framework for your voice. Vue 3 + Vite, AI-ready (Skills / MCP / llms.txt)

    1.7Instructions onlyActiveEngineering
    0.0% over 7 days
    1.1kGitHub stars
  534. 534—
    getsentry/skills

    Agent Skills used by the Sentry team for development.

    7.1Network or broad shellActiveEngineering
    +2.3% over 7 days
    1.1kGitHub stars
  535. 535—
    iamzifei/show-me-the-money

    Claude Code skill suite that builds and runs a 24/7 automated business from scratch — from idea discovery to revenue generation.

    3.8Network or broad shellSlowingEngineering
    +0.3% over 7 days
    1.1kGitHub stars
  536. 536▲
    microsoft/power-platform-skills

    A plugin marketplace for GitHub Copilot and other AI agents that provides Power Platform development plugins, including reusable skills, agents, and commands for building and deploying solutions.

    7.5Network or broad shellActiveEngineering
    +2.8% over 7 days
    1.1kGitHub stars
  537. 537▼
    asklokesh/loki-mode

    Autonomous software factory. Give it a GitHub issue, a spec or a one-line task; get back a pull request with a signed receipt anyone can re-check offline. Runs on your machine with your own keys: Claude, Codex, OpenCode.

    4.2Network or broad shellActiveEngineering
    +0.4% over 7 days
    1.1kGitHub stars
  538. 538▲
    BBuf/AI-Infra-Auto-Driven-SKILLS

    Use when an SGLang, vLLM, TensorRT-LLM, or TokenSpeed serving/model optimization task needs prior model-family PR evidence. Query and read the PR-driven history docs under model-pr-optimization-history before choosing source paths, fast paths, kernel/fusion ideas, regression risks, or validation lan

    7.3Network or broad shellActiveEngineering
    +2.5% over 7 days
    1.1kGitHub stars
  539. 539▼
    openclaw/agent-skills

    Useful skills for agents and claws.

    3.8Network or broad shellActiveEngineering
    +0.4% over 7 days
    1.1kGitHub stars
  540. 540▲
    WangJunqing-coder/huasheng13-skill

    公务员考试(国考/省考/联考)行测申论解题技巧与备考助手。基于花生十三公开教学体系,覆盖资料分析(ABRX体系、截位直除、415份数法、假设分配法)、数量关系(工程/行程/利润/排列组合/容斥/最值/年龄/几何)、言语理解(逻辑填空语境分析、片段阅读中心理解、语句排序)、判断推理(图形推理规律体系、定义判断要素法、类比推理关系层级、逻辑判断翻译推理与加强削弱)、申论(单一题/综合题/公文题/大作文结构)、常识判断、答题顺序与时间分配策略、套题实战复盘。当用户说"公考""国考""省考""行测""申论""花生十三""资料分析怎么提速""数量关系怎么蒙""逻辑填空""图形推理""定义判断""类比推理

    6.3Instructions onlySlowingEngineering
    +2.5% over 7 days
    1.1kGitHub stars
  541. 541▼
    snarktank/clawchief

    Turn your OpenClaw into a Chief of Staff

    0.4Instructions onlySlowingEngineering
    0.0% over 7 days
    1.1kGitHub stars
  542. 542▼
    Kotlin/kotlin-agent-skills

    A collection of AI agent skills useful for projects using Kotlin language

    5.6Network or broad shellActiveEngineering
    +0.7% over 7 days
    1.1kGitHub stars
  543. 543▼
    Achuan-2/pandoc_docx_template

    Use this skill when converting Markdown to Word DOCX or DOCX back to Markdown with Pandoc, especially when the output should use the bundled Chinese Word reference templates, heading numbering variants, list indentation variants, SCI paper templates, and Lua filters for HTML tags, image captions, fo

    1.5Network or broad shellSlowingEngineering
    +0.1% over 7 days
    1.1kGitHub stars
  544. 544—
    openqodex/openqodex

    Open source AI code review for coding agents. A separate reviewer checks every change your agent writes before you push, in Claude Code, Codex, Cursor and Cline. No account or key of its own.

    5.8Instructions onlyActiveEngineering
    +2.8% over 7 days
    1.1kGitHub stars
  545. 545▼
    jezweb/claude-skills

    Skills for Claude Code CLI such as full stack dev Cloudflare, React, Tailwind v4, and AI integrations.

    5.8Network or broad shellActiveEngineering
    +1.1% over 7 days
    1.1kGitHub stars
  546. 546—
    titanwings/ex-skill

    致你忘不掉的那个TA,你们干大模型都是码圣 It's giving rebirth era. Welcome to Digital Life 1.0. 🫶

    2.1Network or broad shellSlowingEngineering
    +0.2% over 7 days
    1.1kGitHub stars
  547. 547—
    Jane-xiaoer/claude-skill-web-clone

    网站复刻 / 克隆方法论。USE WHEN 用户说 复刻网站、克隆网站、clone website、抄个站、仿站、 照着这个站做一个、reproduce site、还原某个网页效果、把这个站搬下来改成我的、 复刻某个交互/WebGL/Canvas/Three.js 效果。提供「先拿真源码 → 判路径 → 逆向拆解 → 搭工程 → 替换内容」的可移植决策树,覆盖静态站 / React-Vue-Next 内容站 / WebGL-Canvas 重前端站三大分支,并强制核对任何 AI 二手分析里的可执行代码。

    5.3Network or broad shellSlowingEngineering
    +1.0% over 7 days
    1.1kGitHub stars
  548. 548▼
    kostja94/marketing-skills

    Agent Skills for Marketing — SEO, Social, Influencer & More. 160+ open-source skills for SEO, content, 40+ page types, paid ads, channels, and strategies. Add project context; get tailored, production-ready output. Cursor, Claude Code, OpenClaw — no lock-in.

    6.8Network or broad shellActiveMarketing
    +1.6% over 7 days
    1.1kGitHub stars
  549. 549▲
    Barty-Bart/motion-graphics

    Motion-graphics skills for Claude Code and Codex.

    8.3Network or broad shellActiveEngineering
    +14.3% over 7 days
    1.1kGitHub stars
  550. 550▲
    momozi1996/awesome-ai-persona-skills

    全网最全的、持续更新的、最火爆的 100+ 人格 蒸馏skills 合集| 多agent系统 |名人/导演/天涯大神/古籍/二次元/职场/情感全品类

    6.2Network or broad shellSlowingEngineering
    +2.1% over 7 days
    1.1kGitHub stars
  551. 551▼
    Jingyi-Wu-Richael/rachel-digital-human-production

    Public-safe MiniMax overseas voice clone and HeyGen API workflow for creating digital-human talking-head videos. Use when Codex is asked to make, automate, QA, or batch-produce authorized 数字人/口播 videos from a script, portrait, voice sample, MiniMax voice cloning, HeyGen Image-to-Video, HeyGen Photo

    4.7Local scriptsSlowingEngineering
    +0.7% over 7 days
    1.1kGitHub stars
  552. 552▼
    jackwener/wechat-article-to-markdown

    Fetch WeChat Official Account (微信公众号) articles from mp.weixin.qq.com and convert to Markdown. 微信文章转 Markdown 工具。

    2.9Network or broad shellSlowingEngineering
    +0.5% over 7 days
    1.1kGitHub stars
  553. 553▼
    zhnnky329/MathModeling-skills

    面向数学建模竞赛的 Claude Code / Codex Skills ,支持分阶段建模流程与 Python、MATLAB/北太天元代码分支。

    4.5Local scriptsActiveEngineering
    +0.7% over 7 days
    1.1kGitHub stars
  554. 554▲
    threerocks/sweety-handdraw-video

    根据主题、文章或讲解稿制作带封面的完整手绘讲解视频。先按真实配音算分镜预算,再设计插画与文字,逐笔描线、上色和按笔顺手写,检查后交付。用于手绘视频、白板动画、文章转手绘讲解;不用于只生成静态插画或只写口播稿。

    8.5Network or broad shellActiveEngineering
    +11.3% over 7 days
    1.1kGitHub stars
  555. 555▲
    feicaiclub/video-spec-builder

    当用户说想做一个视频、宣传片、产品演示、动画短片、抖音/YouTube 内容,或者说要改分镜、调节奏、换镜头、调字幕、加配音、改转场时使用。通过苏格拉底式追问收集视频需求,主动激发渲染层的全部能力(TTS / 字幕 / 3D / shader / 音频反应等),输出标准化的 video-spec.md 用于渲染。

    5.7Network or broad shellSlowingEngineering
    +1.3% over 7 days
    1.1kGitHub stars
  556. 556▼
    LeoKemp223/embed-ai-tool

    面向 AI 编程助手的嵌入式开发技能集,为大模型提供 MCU 固件开发全流程能力。涵盖多工具链构建(Keil / IAR / CMake / PlatformIO)、烧录、GDB 调试、串口监视、Modbus / CAN / VISA 协议调试、外设驱动适配及流水线编排,支持 Linux、macOS、Windows 三平台。

    5.3Network or broad shellSlowingEngineering
    +1.6% over 7 days
    1.1kGitHub stars
  557. 557—
    ufy2024/AuC

    Agents-ufy-Core

    0.2Network or broad shellSlowingEngineering
    -0.5% over 7 days
    1.1kGitHub stars
  558. 558—
    jarrodwatts/claude-code-config

    My personal Claude Code configuration - rules, hooks, agents, skills, and commands

    0.5Network or broad shellSlowingEngineering
    0.0% over 7 days
    1.1kGitHub stars
  559. 559—
    doccker/cc-use-exp

    ⛔ No longer maintained → dev-agent-kit/recipes 让 Claude Code、Antigravity、Gemini CLI、Codex、Cursor 开箱即用的分层配置模板,总结十多年的日常开发经验

    0.5Network or broad shellSlowingEngineering
    -0.1% over 7 days
    1.1kGitHub stars
  560. 560▲
    agentscope-ai/OpenJudge

    OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards

    8.1Network or broad shellActiveEngineering
    +6.2% over 7 days
    1.1kGitHub stars
  561. 561▲
    borghei/Claude-Skills

    385 AI skills, 76 expert agents, and 906 stdlib Python tools for every team: engineering, PM, marketing, C-level, compliance, business ops, research, and a LinkedIn toolkit. Installs on Claude Code, Cursor, Codex, Gemini, Copilot, and 6 other AI assistants.

    8.1Network or broad shellActiveEngineering
    +3.9% over 7 days
    1.1kGitHub stars
  562. 562▼
    wu-yc/LabClaw

    LabClaw – Operating Layer for LabOS (Stanford-Princeton AI Co-Scientists)

    0.4Network or broad shellSlowingEngineering
    -0.1% over 7 days
    1.1kGitHub stars
  563. 563▼
    jiweiyeah/Skills-Manager

    Drive the Skills Manager CLI (`skm`) to initialize the hub, adopt unmanaged skills, list/enable/disable skills per AI tool, and doctor/fix symlink sync. Use whenever the user or an agent needs to manage skills from a terminal, SSH session, CI job, or headless machine; when a skill is missing in Clau

    3.3Network or broad shellActiveEngineering
    +0.7% over 7 days
    1.1kGitHub stars
  564. 564▼
    TechNomadCode/AI-Product-Development-Toolkit

    Plan, build and launch products with AI: guided planning prompts, an AI App Starter for Next.js, Supabase and Vercel, and agent configurations.

    5.6Instructions onlyActiveDocumentation
    +1.0% over 7 days
    1.1kGitHub stars
  565. 565▼
    microsoft/work-iq

    MCP Server and CLI for accessing Work IQ

    4.0Network or broad shellSlowingEngineering
    +0.5% over 7 days
    1.1kGitHub stars
  566. 566▼
    numman-ali/n-skills

    Curated plugin marketplace for AI agents - works with Claude Code, Codex, and openskills

    1.6Network or broad shellActiveEngineering
    +0.1% over 7 days
    1.1kGitHub stars
  567. 567▼
    cookjohn/cnki-skills

    CNKI (中国知网) skills for Claude Code — search, browse journals, download PDFs, export to Zotero via Chrome DevTools MCP

    4.0Network or broad shellSlowingEngineering
    +1.9% over 7 days
    1kGitHub stars
  568. 568▲
    easyeda/easyeda-api-skill

    EasyEDA Pro API skill for AI agents. Use when working with EasyEDA Pro EDA software, including PCB design, schematic editing, footprint/symbol management, and project operations. Supports live debugging in EasyEDA and EasyEDA extension development. Provides complete API reference (120+ classes, 62 e

    8.2Network or broad shellActiveEngineering
    +5.5% over 7 days
    1kGitHub stars
  569. 569▲
    Leonxlnx/cinetic

    Direct, build and render premium cinematic motion design from code — launch films, product and feature videos, looping feature animations for landing pages and social, logo stings and reveals, UI walkthroughs, app demos, kinetic type, teasers, trailers, intros and promo clips. Use this whenever the

    8.6Network or broad shellActiveEngineering
    +12.2% over 7 days
    1kGitHub stars
  570. 570▼
    agiwhitelist/auteur

    Design and build complete web experiences from scratch — award-level product and marketing pages, cinematic scroll-directed sites where the page is directed like a film, and multi-screen products (app, dashboard, admin, settings, onboarding, docs site) built as one design system with every component

    0.3Network or broad shellSlowingEngineering
    -0.1% over 7 days
    1kGitHub stars
  571. 571▼
    DataDog/pup

    Give your AI agent a Pup — a CLI companion with 200+ commands across 33+ Datadog products.

    3.2Network or broad shellActiveEngineering
    +0.2% over 7 days
    1kGitHub stars
  572. 572▲
    jackwener/boss-cli

    Use boss-cli for ALL BOSS 直聘 operations — searching jobs, viewing recommendations, managing applications, chatting with recruiters, and batch greeting. Invoke whenever the user requests any job search or recruitment platform interaction on BOSS 直聘.

    5.4Network or broad shellActiveEngineering
    +1.3% over 7 days
    1kGitHub stars
  573. 573▼
    google-gemma/gemma-skills

    Skills for the Gemma and model/agent interactions

    1.2Network or broad shellActiveEngineering
    0.0% over 7 days
    1kGitHub stars
  574. 574▼
    chuiziyao/maimen-certification

    麦门认证机——上传任意图片(自拍/工位/报错截图/宠物均可),AI 鉴定你的「麦门身份」,生成一张认证梗图卡(身份称号 + 麦门文学梗语 + 套餐推荐),并可联动麦当劳官方 MCP 一键领券、查活动、抽积分彩蛋。触发词:麦门认证、鉴定麦门、我是什么麦门、麦门梗图、认证一下、麦门身份、发一张麦门卡。麦当劳程序员创意开发大赛参赛作品。

    0.8Local scriptsActiveEngineering
    -0.7% over 7 days
    1kGitHub stars
  575. 575▼
    feichanggege/ecommerce-visual-copywriting-skill

    将商品资料、包装与资质、目标平台、目标人群和视觉参考转成可执行的电商视觉方案,包括转化策略、Campaign Style Lock、主图/详情页/Listing/A+ Storyboard、图内文案、设计说明、生图 Prompt、证据与合规审查。适用于淘宝、天猫、京东、拼多多、抖音小店、小红书、视频号/微信小店,以及 Amazon、Shopify、TikTok Shop、Temu、Shopee、Lazada;用户需要商品图、详情页、图内文案、设计师执行稿或跨境商品本地化时使用。不适用于纯短视频/直播话术、投放与店铺运营优化、需律师出具的最终法律结论(可做风险筛查);不自动上架或发布。不得编造资

    8.1Local scriptsActiveWriting
    +4.6% over 7 days
    1kGitHub stars
  576. 576▲
    beshuaxian/higgsfield-seedance2-jineng

    Seedance 2.0 × Higgsfield 技能集 | 15 Claude prompt skills for AI video generation — cinematic, 3D CGI, anime, e-commerce ads, music videos & more. Each skill: 2-second hook framework, camera encyclopedia, 5+ production prompts. 含2秒钩子框架、摄像机百科、行业最佳实践提示词工程

    5.7Network or broad shellSlowingEngineering
    +2.0% over 7 days
    1kGitHub stars
  577. 577▼
    taishi-i/awesome-japanese-nlp-resources

    A curated list of resources for Japanese natural language processing (NLP): Python libraries, LLMs, dictionaries, corpora, and datasets. Includes Claude Code and Codex skills to search resources.

    3.2Network or broad shellActiveEngineering
    +0.2% over 7 days
    1kGitHub stars
  578. 578▼
    cclank/lanshu-animated-architecture-diagram

    Create premium hand-drawn architecture and process diagrams in the Lanshu animated GIF style, with editable .excalidraw files, static PNG previews, and genuinely animated GIFs with moving flow highlights. Use this skill whenever the user asks for 岚叔动态架构图, Excalidraw-like diagrams, DailyDoseOfDS-styl

    3.2Network or broad shellSlowingEngineering
    +0.9% over 7 days
    1kGitHub stars
  579. 579▲
    CNWU16/vedic-astro-skills

    🔱 Vedic/Jyotish AI analysis toolkit | 吠陀占星AI分析工具包——从排盘开始,到以后的长期追问。支持所有可以挂载Skill的平台。感谢大家的支持。

    6.4Network or broad shellActiveEngineering
    +1.5% over 7 days
    1kGitHub stars
  580. 580▲
    MiniMax-AI/MiniMax-Music3

    Turn a brief music description and optional tagged lyrics into a professional MiniMax Music 3 structured caption with Global Metadata, Vocal Details, and a section-aware Arrangement. Use when users ask to enhance a music-generation prompt, preserve lyric-section directives, retrieve a similar style

    6.1Instructions onlyActiveEngineering
    +1.5% over 7 days
    1kGitHub stars
  581. 581▼
    freekmurze/dotfiles

    My personal dotfiles

    3.2Network or broad shellActiveEngineering
    +0.3% over 7 days
    1kGitHub stars
  582. 582▲
    feimacode/open-design-agent-kit

    Make posters, social posts, slides and landing pages in the coding agent or chat you already use (Copilot, Claude, Codex, Cursor), with 198 design systems, checks and PDF/PNG/PowerPoint export.

    8.4Network or broad shellActiveDesign
    +72.2% over 7 days
    1kGitHub stars
  583. 583—
    tenfoldmarc/llm-council-skill

    Run any question, idea, or decision through a council of 5 AI advisors who independently analyze it, peer-review each other anonymously, and synthesize a final verdict. Based on Karpathy's LLM Council methodology. MANDATORY TRIGGERS: 'council this', 'run the council', 'war room this', 'pressure-test

    6.6Instructions onlySlowingEngineering
    +2.9% over 7 days
    1kGitHub stars
  584. 584▼
    sno-ai/sno-station

    When Claude Code hits its usage limit, Codex picks the task up from the same memory. Sno Station puts Codex, Claude Code, Cursor, Hermes Agent and OpenClaw on one squad: they hand work to each other and review each other's code. Open source, runs on your computer.

    1.2Instructions onlyActiveEngineering
    -7.0% over 7 days
    1kGitHub stars
  585. 585▼
    ChatCut-Inc/agent-plugin

    AI video editor for agents. ChatCut plugin and MCP server for Codex, ChatGPT, Claude Code, Cursor, Grok, Gemini CLI, WorkBuddy, Doubao Work and Qwen Work: edit your own footage by chatting, add captions and subtitles, remove silences and filler words, create motion graphics, and export an editable timeline.

    6.5Network or broad shellActiveEngineering
    +1.4% over 7 days
    1kGitHub stars
  586. 586▼
    HunYiSage/github-skill-forge

    一个"制造技能的技能"。这个工具自动化了将任意 GitHub 仓库转换为标准化 Trae 技能的全过程,是扩展 AI Agent 能力的核心工具。

    6.2Network or broad shellSlowingEngineering
    +2.3% over 7 days
    1kGitHub stars
  587. 587—
    bitjaru/styleseed

    Open-source design-method engine for Claude Code, Codex & Cursor. One agent skill with 22 internal workflows for fixed design judgment, multiple grammars, semantic palettes, reference compilation, and evidence-verified UI. MIT.

    5.6Network or broad shellActiveDesign
    +0.9% over 7 days
    1kGitHub stars
  588. 588▲
    poleHansen/baibaiAIGC

    baibaiAIGC

    6.1Network or broad shellActiveEngineering
    +1.4% over 7 days
    1kGitHub stars
  589. 589▼
    Yu-369/VibeCurb

    VibeCurb - Injects taste into AI workflows to stop agents from generating boring, AI slop.

    4.3Instructions onlySlowingEngineering
    +0.6% over 7 days
    998GitHub stars
  590. 590—
    ccplugins/awesome-claude-code-plugins

    Awesome Claude Code plugins — a curated list of slash commands, subagents, MCP servers, and hooks for Claude Code

    4.5Network or broad shellSlowingEngineering
    +0.8% over 7 days
    998GitHub stars
  591. 591—
    tingaicompass/AI-Compass

    Search and answer questions from the local AI-Compass AI knowledge base. Use when the user asks about AI models, tools, agents, RAG, multimodal systems, evaluation, learning paths, project resources, or recent AI developments covered by this repository; distinguish weekly updates from long-term topi

    2.3Network or broad shellActiveEngineering
    +0.1% over 7 days
    995GitHub stars
  592. 592—
    zhu1090093659/spec_driven_develop

    Spec-driven development workflow for AI coding agents: architecture-first planning, task decomposition, GitHub Issue/PR tracking, Deep Discuss, and adaptive control for Claude Code, Codex, Cursor, and other Markdown-capable agents.

    0.3Network or broad shellSlowingEngineering
    0.0% over 7 days
    993GitHub stars
  593. 593▲
    heqiangdiao-wq/AI-Cross-Border-Ecommerce-Agent-Toolkit

    AI 跨境电商运营智能体工具箱 · 把运营 SOP 拆成 7 个可复用的 AI Agent 工作流,含 Prompt、模板与真实案例

    8.4Network or broad shellActiveEngineering
    +16.2% over 7 days
    990GitHub stars
  594. 594▲
    jegly/Box

    The most advanced, fully offline client-side AI suite on Android today.

    7.8Network or broad shellActiveEngineering
    +3.2% over 7 days
    990GitHub stars
  595. 595▼
    guanyang/open-agent-hub

    A lightweight, zero-dependency CLI tool to manage and activate capabilities for AI coding assistants (such as Claude Code, Cursor, Trae, etc.).

    3.2Network or broad shellActiveDesign
    +0.2% over 7 days
    986GitHub stars
  596. 596—
    komal-SkyNET/claude-skill-homeassistant

    Manage Home Assistant configuration safely and fast — edit and deploy YAML (automations, blueprints, scripts, scenes, templates, MQTT), validate with ha core check, deploy via git or rapid scp, reload-vs-restart correctly, verify changes from logs, traces and entity state, and build Lovelace dashboa

    1.6Instructions onlySlowingEngineering
    +0.1% over 7 days
    980GitHub stars
  597. 597—
    olelehmann1337/autoresearch-skill

    Autonomously optimize any Claude Code skill by running it repeatedly, scoring outputs against binary evals, mutating the prompt, and keeping improvements. Based on Karpathy's autoresearch methodology. Use when: optimize this skill, improve this skill, run autoresearch on, make this skill better, sel

    1.6Instructions onlySlowingEngineering
    0.0% over 7 days
    980GitHub stars
  598. 598—
    scottstts/Threejs-Awesome-Graphics-Agent-Skills

    A three.js agent skills for producing awesome graphics for scenes and games

    7.3Network or broad shellActiveEngineering
    +2.6% over 7 days
    976GitHub stars
  599. 599—
    alchaincyf/steve-jobs-skill

    史蒂夫·乔布斯(Steve Jobs)的思维框架与表达方式。基于Isaacson授权传记、Stanford演讲、 Lost Interview、D Conference系列、Make Something Wonderful、30+一手来源的深度调研, 提炼6个核心心智模型、8条决策启发式和完整的表达DNA。 用途:作为思维顾问,用乔布斯的视角分析产品、审视决策、提供反馈。 当用户提到「用乔布斯的视角」「乔布斯会怎么看」「Jobs模式」「steve jobs perspective」时使用。 即使用户只是说「帮我用乔布斯的角度想想」「如果乔布斯会怎么做」「切换到乔布斯」也应触发。

    2.3Instructions onlyActiveEngineering
    +0.1% over 7 days
    973GitHub stars
  600. 600▲
    classmethod/tsumiki

    tsumiki

    1.6Network or broad shellSlowingEngineering
    0.0% over 7 days
    973GitHub stars
  601. 601▼
    Kulaxyz/self-learning-skills

    Capture a hard-won "golden path" from the current session as a reusable Agent Skill, so future sessions start already knowing it. Use it (1) right after non-trivial debugging, after working out a multi-step operational workflow, or after rediscovering project facts you didn't know up front — e.g. ho

    1.5Instructions onlyActiveEngineering
    +0.1% over 7 days
    972GitHub stars
  602. 602—
    nexu-io/codex-slides

    🎨 Open-source AI slide studio inside Codex: image-native decks, every slide a full visual canvas. ⚡ 10+ high-quality slides in ~4–5 minutes — Fast mode renders every page in parallel. 🔍 Watch the whole chain live: research → outline → style → render → edit → present → export PDF/PPTX. 🖥️ Browser-first · zero API keys · durable projects.

    4.5Network or broad shellSlowingDesign
    +0.7% over 7 days
    972GitHub stars
  603. 603▲
    freestylefly/wesight

    Open-source desktop AI agent workspace with one-click Claude Code, Codex, OpenClaw, Hermes Agent setup and custom LLM model routing.

    3.8Network or broad shellActiveEngineering
    +0.3% over 7 days
    967GitHub stars
  604. 604▲
    LearnPrompt/luban-skill

    鲁班(Luban)——Skill打磨工坊。把一个"能用的Skill"打磨成"能被理解、能被安装、能被传播、能被验证、能持续进化"的公共Skill资产。 方法论是工匠式的五个动作:验料(先挑战这个Skill的前提是否成立,不值得雕的料直说)、访行(联网寻找同类Skill,看清自己在生态里站什么位置)、过尺(结构、实测、活体三把尺一起量——活体指拉真实运行产物对账,绿色的CI会撒谎)、慢刨(冻结原版做基线,改动必须通过验证门才保留,否则回刀;验证手段尽量沉淀为仓库里的工具和规矩)、回炉(发布不是终点,留对标观察清单,下一轮从真实反馈进)。 当用户想要升级、优化、打磨、产品化、发布自己开发的Skil

    1.6Network or broad shellSlowingEngineering
    +0.1% over 7 days
    965GitHub stars
  605. 605▲
    LB623/no-negative-echo

    Prevent 此地无银三百两式 residue: finalize artifacts without echoing rejected session-only alternatives into labels, metadata, commits, PRs, or handoffs. Use after corrections or discarded proposals. Not for ordinary deletion, deprecation, migration, or exclusions materially required for safety, accuracy, c

    4.5Local scriptsSlowingEngineering
    +0.7% over 7 days
    961GitHub stars
  606. 606▲
    china-qijizhifeng/agentic-harness-engineering

    Official AHE code — Agentic Harness Engineering: observability-driven automatic evolution of coding-agent harnesses (concurrent w/ meta-harness). NexAU-AHE reaches 84.7% ± 2.1 pass@1 on Terminal-Bench 2 (GPT-5.5). Lifts GPT-5.4 69.7→77.0% over 10 iters, beats Codex/ACE/Training-Free GRPO; frozen harness transfers to SWE-bench-Verified.

    5.3Network or broad shellActiveEngineering
    +0.7% over 7 days
    961GitHub stars
  607. 607▲
    mouse-lin/finesse-skill

    Build and refine high-craft web interfaces: brand sites, product dashboards and workflows, AI workbenches, commerce, H5/mobile screens, and individual components. Route by purpose, preserve project identity, and audit visual quality, accessibility and motion. Supports Apple-inspired / 苹果风 design thr

    7.9Network or broad shellActiveEngineering
    +4.8% over 7 days
    961GitHub stars
  608. 608▲
    OUBIGFA/De-AI-Prompt-Enhancer-Writer-Booster-SKILL

    去AI味提示词-作家增强-SKILL

    5.7Instructions onlyActiveEngineering
    +2.2% over 7 days
    958GitHub stars
  609. 609—
    poteto/how

    Explain how something works in this codebase by exploring code and producing a clear architectural explanation. Optionally critique the architecture for issues.

    6.0Instructions onlySlowingEngineering
    +2.6% over 7 days
    958GitHub stars
  610. 610—
    superdesigndev/superdesign-skill

    Design or redesign frontend UI, presentations, and graphics on the Superdesign canvas with a choice of leading AI models. Use whenever the user wants to design a page, feature, flow, slide deck, or brand-new product; improve or reproduce existing UI; compare design results across top models; explore

    6.6Network or broad shellSlowingDesign
    +3.0% over 7 days
    951GitHub stars
  611. 611▲
    homeassistant-ai/skills

    Home Assistant (HA) best practices. Load first, before answering or exploring, on any HA request. TRIGGER THIS SKILL WHEN: - Creating or editing automations, scripts, scenes, dashboards, blueprints - Choosing template sensors, helpers, or Jinja macros - Restructuring triggers, conditions, or modes;

    7.3Network or broad shellActiveEngineering
    +2.2% over 7 days
    948GitHub stars
  612. 612▼
    paperclipai/companies

    Write long-form articles synthesized from research and analysis

    3.2Network or broad shellSlowingEngineering
    +0.9% over 7 days
    948GitHub stars
  613. 613—
    rookie-ricardo/erduo-skills

    Curate a Chinese reading digest from a fixed bundle of RSS and Atom feeds, with a strong preference for AI agent thinking, frontier AI commentary, deep interviews, and non-boring high-signal essays. Use when Codex needs to pull the latest week's posts by default, or a specific day's posts when expli

    4.7Network or broad shellSlowingEngineering
    +0.6% over 7 days
    943GitHub stars
  614. 614—
    bear2u/my-skills

    자주 사용하는 스킬들을 모은 나의 클로드 스킬들입니다.

    4.0Network or broad shellSlowingEngineering
    +0.4% over 7 days
    940GitHub stars
  615. 615▲
    LottieFiles/dotlottie-web

    Implement Lottie animations using dotLottie runtimes (@lottiefiles/dotlottie-web and @lottiefiles/dotlottie-react). Use when building, debugging, or optimizing dotLottie or Lottie animations in web projects, including vanilla JS, React, and Next.js. Covers package selection, Web Workers, state machi

    5.4Network or broad shellActiveEngineering
    +0.8% over 7 days
    939GitHub stars
  616. 616▲
    liustack/modsearch

    Plug-in web search, X (Twitter) search, and page fetch for models without native web access. Use whenever the task needs current information, external facts, source links, posts from X, or the content of a specific URL, and the active model/harness has no native search or fetch tool. Runs the modsea

    8.3Network or broad shellActiveEngineering
    +6.9% over 7 days
    939GitHub stars
  617. 617▲
    alchaincyf/huashu-md-html

    md/html/docx/pdf/epub 多向流水线,落地「md 生产,多端消费」。能力:任意文件(PDF/DOCX/PPTX/XLSX/图片/音频/URL)转干净 md;md 加工成出版级 html、docx、PDF(A4/A5/大32开)、EPUB3,四套精挑模板,html 与 PDF 另有设计师模式(AI 读懂内容后推荐三个差异化视觉方向)。SKIP:需要新生成图片、或只做压缩截图的任务。

    5.0Network or broad shellActiveEngineering
    +0.5% over 7 days
    938GitHub stars
  618. 618▼
    Yeachan-Heo/clawhip

    claw + whip: Event-to-channel notification router — bypasses gateway sessions to avoid context pollution

    1.4Network or broad shellActiveEngineering
    0.0% over 7 days
    937GitHub stars
  619. 619—
    awslabs/agent-plugins

    Agent Plugins for AWS equip AI coding agents with the skills to help you architect, deploy, and operate on AWS.

    5.0Network or broad shellActiveEngineering
    +0.5% over 7 days
    937GitHub stars
  620. 620▲
    thedivergentai/Game-Dev-Agentic-Skills

    Multi-engine long-term memory for game AI agents. Deep Godot 4.7+ (99 skills, 27 genre blueprints) + Bevy docs-first parity — audited patterns, persona orchestration (Analyst · Auditor · Builder), production-grade engineering.

    7.4Network or broad shellActiveEngineering
    +2.5% over 7 days
    935GitHub stars
  621. 621▲
    jame581/GodotPrompter

    Agentic skills framework for Godot 4.x. Domain-specific skills for AI coding agents (Claude Code, Copilot, Antigravity, Cursor)

    7.8Network or broad shellActiveEngineering
    +3.1% over 7 days
    929GitHub stars
  622. 622—
    SethGammon/Citadel

    The operating layer for Claude Code + OpenAI Codex: persistent project memory, intent routing, safety hooks, cost telemetry, and parallel agent fleets.

    1.7Network or broad shellActiveEngineering
    0.0% over 7 days
    927GitHub stars
  623. 623▼
    hashicorp/agent-skills

    A collection of Agent skills and Claude Code plugins for HashiCorp products.

    5.7Network or broad shellActiveEngineering
    +0.7% over 7 days
    916GitHub stars
  624. 624▼
    tripleyak/SkillForge

    A skill creator that proves its skills work. Evidence-driven skill creation for Claude Code and Codex: baseline-tested generation, per-skill regression evals, ecosystem doctor, cross-runtime compile, and an opt-in proactive advisor.

    2.3Network or broad shellSlowingEngineering
    +0.2% over 7 days
    916GitHub stars
  625. 625—
    solatis/claude-config

    My claude code customizations / config.

    3.5Network or broad shellActiveEngineering
    +0.2% over 7 days
    915GitHub stars
  626. 626▼
    oracle/skills

    Oracle Skills is a curated, open-source collection of practical, installable skills for working with Oracle technologies. It provides developers, administrators, and AI agents with high-quality, source-backed guidance across the entire Oracle ecosystem.

    4.1Network or broad shellActiveEngineering
    +0.6% over 7 days
    914GitHub stars
  627. 627▼
    Kappaemme-git/codex-complexity-optimizer

    Analyze a software codebase for algorithmic complexity and performance hotspots, then propose or implement safe optimizations without breaking behavior. Use when Codex is asked to scan many files, find inefficient loops, nested iteration, repeated scans, costly rendering/recomputation, N+1 queries,

    0.1Local scriptsSlowingEngineering
    -0.3% over 7 days
    912GitHub stars
  628. 628▲
    AVIDS2/memorix

    Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Windsurf, Gemini CLI, Antigravity, OpenClaw, Hermes Agent, Oh-my-Pi, Pi, Copilot, Kiro, OpenCode, and Trae.

    7.6Local scriptsActiveEngineering
    +2.7% over 7 days
    909GitHub stars
  629. 629▼
    joeseesun/qiaomu-goal-meta-skill

    Turn vague or complex Codex tasks into strong `/goal` commands with outcome, verification, constraints, boundaries, iteration policy, completion evidence, and pause/block conditions. Use when the user asks for Codex goal instructions, Goal 指令, 目标指令, `/goal` prompts, 中文 Goal 模板, plan-to-goal intervie

    5.2Local scriptsSlowingEngineering
    +1.0% over 7 days
    909GitHub stars
  630. 630▼
    SynaLinks/synalinks-skills

    Use for anything involving the Synalinks neuro-symbolic LM framework (Keras-inspired): DataModel/Field/Input, JSON operators (+ & | ^ ~), synalinks.ops; LanguageModel/EmbeddingModel and provider prefixes; DecisionModel (TypeSafe jev decision models, decision_model=, min_confidence/threshold); the Pr

    0.4Network or broad shellActiveEngineering
    0.0% over 7 days
    908GitHub stars
  631. 631▼
    laolaoshiren/claude-code-skills-zh

    面向中文开发者的 Claude Code Skills / Agents / Plugins 精选与原创技能库|按场景分类|复制即装|持续更新

    5.4Instructions onlyActiveEngineering
    +0.7% over 7 days
    906GitHub stars
  632. 632▲
    unbrowse-ai/unbrowse

    Unbrowse - Reverse engineer any website so that your agents can access its APIs directly

    8.0Network or broad shellActiveEngineering
    +10.5% over 7 days
    904GitHub stars
  633. 633▲
    cwyalpha/Word-Formatter-Pro

    公文格式排版工具。将 doc/docx/wps/txt/md 文档按照公文排版习惯自动格式化,输出标准 docx。支持智能识别标题层级(一、/(一)/1./(1))、题目/副标题、附件格式化、图表标题识别、页面边距、页码、行距、字体字号、TXT/MD 空行模式、自定义配置和目录批量处理。当用户需要排版公文、格式化文档、统一文档格式、调整字体字号行距边距时使用此技能。关键词:公文排版、文档格式化、字体设置、标题层级、格式统一、排版工具。

    6.4Network or broad shellActiveEngineering
    +2.0% over 7 days
    903GitHub stars
  634. 634▼
    ast-grep/agent-skill

    Guide for writing ast-grep rules to perform structural code search and analysis. Use when users need to search codebases using Abstract Syntax Tree (AST) patterns, find specific code structures, or perform complex code queries that go beyond simple text search. This skill should be used when users a

    4.1Network or broad shellActiveEngineering
    +0.2% over 7 days
    902GitHub stars
  635. 635▼
    tommy0103/obelisk

    Every past session, subagent, and workflow -- queryable by your agent, browsable by you

    7.9Network or broad shellActiveDevOps
    +27.6% over 7 days
    902GitHub stars
  636. 636▲
    borski/travel-hacking-toolkit

    AI-powered travel hacking and search with cash, points, miles, and award flights. Drop-in skills and MCP servers for Claude, Codex, and OpenCode.

    7.9Network or broad shellActiveEngineering
    +12.1% over 7 days
    899GitHub stars
  637. 637▼
    alirezarezvani/claude-code-skill-factory

    Claude Code Skill Factory — A powerful open-source toolkit for building and deploying production-ready Claude Skills, Code Agents, custom Slash Commands, and LLM Prompts at scale. Easily generate structured skill templates, automate workflow integration, and accelerate AI agent development with a clean, developer-friendly setup.

    0.1Network or broad shellSlowingEngineering
    -0.2% over 7 days
    895GitHub stars
  638. 638—
    artokun/comfyui-mcp

    Local-first, agent-native control plane for ComfyUI — MCP server + sidebar agent that generates images, video & audio, authors and runs workflows, and edits your live graph in natural language on ANY LLM (Claude, ChatGPT, Gemini, offline Ollama, or any hosted model). 178 tools, 36 AI skills, 55 installer packs. Local, LAN, VPS, or Comfy Cloud.

    6.1Network or broad shellActiveEngineering
    +1.6% over 7 days
    894GitHub stars
  639. 639—
    vibeshotclub/vsc-skills

    将指定成年角色转译为真人 COS 或二次元角色摄影提示词,强调前景遮挡、长焦观察、手机快拍和发现镜头的电影化瞬间。适用于角色名驱动的虚构摆拍、隐蔽观察视角或 n=10 角色抓拍提示词;普通生活人像不属于本技能的主要范围。

    2.8Network or broad shellActiveEngineering
    +0.6% over 7 days
    893GitHub stars
  640. 640—
    ML-SystemDesign/MLSystemDesign

    Use when running a stage-gate or gate review for an AI product, deciding Go/Kill/Pivot at a gate, judging whether an AI initiative is ready to advance to the next stage, triaging a portfolio of AI ideas, or choosing between a full and a fast-track path. Applies a Stage-Gate process built for AI prod

    2.7Instructions onlySlowingEngineering
    +0.1% over 7 days
    890GitHub stars
  641. 641—
    Aryanutkarsh/SeeCode

    Create animated, explorable editorial diagrams in 45 types (architecture, flowchart, sequence, state, ER, DB schema, UML class, swimlane, timeline, gantt, journey, tree, org chart, nested, venn, quadrant, fishbone, wardley, bar, line, scatter, sankey, treemap, heatmap, 3D isometric objects, floor pl

    8.1Network or broad shellActiveEngineering
    +20.1% over 7 days
    889GitHub stars
  642. 642▲
    LC044/TrailSnap

    TrailSnap (行影集) | AI-Powered open-source photo album for travel & life memories.(AI赋能的开源相册工具,珍藏旅行与生活点滴)

    7.7Network or broad shellActiveEngineering
    +4.0% over 7 days
    886GitHub stars
  643. 643▼
    mrtooher/fable-mode

    A Claude skill that activates Fable-style agentic behavior: explicit multi-stage planning, sub-agent delegation, and self-verification.

    5.2Network or broad shellActiveEngineering
    +0.7% over 7 days
    886GitHub stars
  644. 644▼
    liyue-aigc/female-outfit-director

    为“同一角色多套穿搭拼贴首帧 + 卡点换装短视频”生成联动的图片提示词和视频脚本。 当用户要求真人化角色穿搭拼贴、五套造型、悬浮人物贴纸、汉服/古风/现代时尚换装、点击换装、 卡点变装、根据上传参考图延展视频,或希望先推荐穿搭/换装参数再生成时使用。 支持从参考图提取人物、发型头饰、耳饰、服装和版式;支持部分参数输入与系统补全。

    4.2Instructions onlyActiveEngineering
    +0.7% over 7 days
    885GitHub stars
  645. 645▼
    DanielPan12/JobHuntBot

    A reusable job application workflow for Codex and other AI agents. Use when a user wants to set up or run an AI-assisted job search system: collecting a candidate profile, creating an application dashboard, defining screening and resume-routing rules, finding and ranking job leads, applying to jobs

    5.4Network or broad shellActiveEngineering
    +1.0% over 7 days
    883GitHub stars
  646. 646▼
    BrownFineSecurity/iothackbot

    IoT HackBot: A collection of Claude Skills and custom tooling for hybrid IoT pentesting

    2.4Network or broad shellSlowingEngineering
    +0.3% over 7 days
    880GitHub stars
  647. 647▼
    spencerpauly/awesome-cursor-skills

    A curated list of awesome skills for Cursor

    5.1Network or broad shellSlowingEngineering
    +1.1% over 7 days
    880GitHub stars
  648. 648▼
    dualface/ste-zh

    Make the agent report results to the user by the ASD-STE100 (Simplified Technical English) principles, in Chinese: key information first, one word one meaning, one fact per sentence, fixed status words, honest verification state, short sentences. Use only when the user explicitly activates it; never

    5.8Instructions onlyActiveEngineering
    +10.3% over 7 days
    875GitHub stars
  649. 649▼
    crabwise-ai/crabwalk

    Real-time companion monitor for OpenClaw agents

    1.6Network or broad shellSlowingEngineering
    +0.1% over 7 days
    873GitHub stars
  650. 650▼
    sangrokjung/claude-forge

    oh-my-zsh for Claude Code — 16 agents, 35 commands, 32 skills, 21 safety hooks in one install. v4.0 adds an adversarial review loop: a second agent that never sees the first one's reasoning. MIT.

    4.3Network or broad shellSlowingProductivity
    +0.7% over 7 days
    873GitHub stars
  651. 651▼
    taracodlabs/aiden

    Aiden — an autonomous AI agent and work engine built solo. It can operate your browser, terminal, files, apps, APIs, skills and tools, remember context, recover from failures, automate workflows, and verify the result. Open source · AGPL-3.0.

    4.3Network or broad shellActiveEngineering
    +0.7% over 7 days
    873GitHub stars
  652. 652▼
    GAIR-NLP/ASI-Evolve

    Run an ASI-Evolve style evaluator-driven search workflow for code, algorithms, prompts, or pipelines. Use when Codex needs to align the objective, scoring, evaluator, writable scope, and cognition first, then execute a preflight-gated learn/design/experiment/analyze loop with the bundled Evolve CLI

    1.0Network or broad shellActiveEngineering
    0.0% over 7 days
    872GitHub stars
  653. 653▼
    wshuyi/x-article-publisher-skill

    Publish Markdown articles to X (Twitter) Articles editor with proper formatting. Use when user wants to publish a Markdown file/URL to X Articles, or mentions "publish to X", "post article to Twitter", "X article", or wants help with X Premium article publishing. Handles cover image upload and conve

    0.1Network or broad shellSlowingEngineering
    -0.2% over 7 days
    872GitHub stars

Ranked by stars. Sponsorship never changes the order.

Back to top