Markdown folder → website. One command. Zero config.

Curated AI skills for open data workflows — tool-agnostic instructions following the Agent Skills open standard

An AI agent skill that provides comprehensive GitLab integration — fetch issues and merge requests, generate executive summaries, perform structured code reviews, and automate end-to-end issue resolution workflows.

Free open-source Agent Skills for voice-to-instrument AI music production — recording best practices, instrument-specific tips, and prompt engineering

Build and test trading strategies with Stingray from any SKILL.md-compatible agent, including Claude Code, Codex, Cursor, and more.

Open Agent Skills for adding bansos.dev listings and developing the bansos.dev SvelteKit site.

Expert startup strategy council with 6 advisors (Thiel, Graham, Ries, Andreessen, Lavingia, Dunford) for validation, PMF, business models, positioning, and growth.

Image generation skill for Claude Code, Codex CLI, OpenCode, Cursor and 50+ AI coding agents. Two backends (OpenAI API or codex CLI signed in to ChatGPT subscription), three modes (generate, edit, compose up to 16 references), six production recipes for gpt-image-2.

PHP and Laravel Cursor rules — coding standards, testing, and conventions for the Cursor editor. Install via Composer.

短视频数据采集与分析工具skills：一键抓取元数据+评论、NLP话题聚类、多维度Excel导出、封面下载、词云生成。基于Douyin_TikTok_Download_API，支持抖音/TikTok/B站。

Opinionated Claude Code foundation — Explore → TDD → Audit workflow, auto-detected stack presets (nextjs, fastapi, astro, ...), curl | bash install. MIT.

Agent skill to search Adobe Fonts, manage Typekit web kits, and return embed tags with CSS font-family snippets.

Reusable PapersFlow research skills for literature search, citation graph exploration, and DeepScan monitoring powered by papersflow-mcp.

Complete agent stack for Jaz. Plugins, Skills, MCP tools, and CLI for Claude Code, Cowork, Codex, Copilot, Cursor, and more.

Force agents to read critical context left by other agents, enforced by linting and freshness checks.

In-session compliance enforcement skill for Claude Code (paper Sec 6 dogfood). Per-user adaptive threshold + chaos-tested install/doctor/uninstall.

A library of reusable skills for AI agents. Each skill/plugin is a Markdown file with YAML frontmatter that can be invoked as a slash command within Claude Code CLI or Antigravity IDE.

DingTalk group chat bridge for Claude Code. Send messages, receive @mentions, auto-execute prompts via Stream SDK.

A Claude Code development workflow plugin: walks every piece of work through the six Working Geniuses (Wonder, Invention, Discernment, Galvanizing, Enablement, Tenacity) so no stage gets skipped.

Open Agent Skill for Codex, Claude Code, and GitHub Copilot that turns rough ideas into researched decisions and practical outputs.

Agent skills, templates, examples, validators, and docs for operating Amadeus DLC, a lifecycle contract for AI driven software development.

Free AI agent skills for business automation. Sales, content, ops, growth. Compatible with Claude Code, Codex, Gemini CLI, Cursor.

把辅导员的通知、私聊、约谈、批注和制度语气蒸成一个能长期使用的 Skill，给大学生预演那些最难开口的真实沟通。

Autonomous operations layer for Claude Code — opens small reviewable PRs for your live side project and re-orients from which ones you merge or reject. HALT file + hard cost cap; you stay in command.

Understand core techniques of harness-engineering by building a mini Claude Code

🩺 A meta-skill for Claude Code that gives your other skills a health checkup — diagnose-only, based on Matt Pocock's 'Building Great Agent Skills' method.

a collection of custom Claude Code skills for productivity and project management

A collection of skills distilled from minorcell's own workflows and useful practices from others.

Open source Claude Code agent skills for iOS developers and content creators on Mac

AI Agent Skills Monorepo: hq（行情查询）, pp（Pinterest 画廊）, imagegen-magick（矢量图像生成）, music（在线音乐播放）。跨平台零依赖分发。

All things related to my Codex agents running on MacOS

agent skills for science

Agentic Skill for the Hyperliquid Names API

CLI for AIDDLC -- Scaffolded, parallelized, context aware agent runtime in seconds.

Open-source Codex workspace, skills and verifiable-document tooling for evidence-grounded legal work

Agent Skill for automatic CLI tool management - installs missing tools, audits environments | Claude Code compatible

Portable Agent Skill for small, verified coding-agent changes

Production-ready Claude Code skills — audit code quality, forge design docs, generate documentation, automate infrastructure. CLI = Command Line Interface + Clement Liard Initials.

Programmable email inbox skill for 40+ AI agents — Claude Code, Codex, Cursor, Windsurf, Cowork, OpenClaw, and any agent that supports SKILL.md

Skills for Syncfusion WPF controls. Enable AI-assisted development with comprehensive documentation, code examples, and best practices for 100+ UI controls including DataGrid, Charts, Scheduler, and more.

Agent Skills for coding agents

My personal, curated set of artifacts for AI coding agents

Agent skills and MCP server for Tough Tongue AI. Create voice-agent scenarios, refine them from real transcripts, and analyze session performance from Claude Code, Codex, or Cursor.

Agent skills for systematic review, meta-analysis, umbrella review, and AI-assisted evidence synthesis.

Enable Codex to run objective-first autonomous loops with mandatory review and optional verification for long-running task completion

Provider-agnostic agent skills and plugins for AI coding assistants. By Robert Courson.

Framework-agnostic web accessibility skills and Cursor subagents for AI coding agents.

An agent skill that turns recent coding-agent session history into durable repository guidance.

Keep AI noise out of your git history. A cross-platform agent skill that blocks Co-Authored-By bots, generator footers, and model-name watermarks in commit messages — so git log, git blame, and changelogs stay signal, not spam.

Spec-first, cross-harness SDLC skills framework — one director, AI agents, a living spec spine

Agent skills for Gitea/Forgejo issue, pull request, milestone, and label workflows using the tea CLI

GNME (pronounced Gen-Me) is a lightweight framework that replaces static, task-based specifications with living Module Genomes. It is designed specifically for developers using AI assistants (Cursor, Claude) to build complex, evolving systems.

Agent skills for frontend architecture and development

Mindful-coding OS for any LLM coding agent (Claude Code, Codex, Gemini CLI) — the Five Forces: session handoff, eval loops, vibe-debugging diagrams, FMEA failure scans + a pre-commit secret gate. Plain markdown, no daemons.

Govern, audit, and ship AI-agent skills with policy checks, evidence, SBOM, and MCP.

Safe, quality-gated model+effort router for Claude Code - delegates cheap work down to save tokens, escalates hard/sensitive work up through a verify staircase, never-down gate, and fail-safe Lock, up to a consent-gated Fable 5 top rung. Not the cheapest router; the safest one inside Claude.

Some of my Agents & Skills, compatible with most AI coding tools

Agent skills

Agent Skill for rebuilding Embedded IDE for VS Code (EIDE) projects with Codex and returning structured JSON build results.