Coding & Development

A local context graph for AI coding agents.

Benchmark Claude Code plugins/skills/agents/MCPs by A/B comparing versions with LLM-judged evaluation prompts

Architecture diagrams that actually run, generated by AI agents

My AI agent skills — managed with skillshare

A Codex skill that dynamically discovers installed skills and MCP servers, then recommends the best one for a task.

语雀 AI Skill 纯 Skills 版 — 零 MCP 开销，curl 直调语雀 API，40+ API 端点 + 18 业务 Skills

免登陆一键保存小红书笔记到本地的 Skill，适用于 Claude Code/Codex/OpenClaw 等 agent

AGENTS.md files converted and distributed by TomeVault

面向 WebMCP 标准的非侵入式前端集成套件：写一个普通 TS 函数加一段 JSDoc，即可被任意 MCP 客户端调用 —— 含 SDK、Vite/Webpack 插件与 AI 编码 Skill。

Local control plane for Claude Code / Codex skills — deterministic rules + quality gate + usage feedback loop. Push auto-trigger rate from ~50% toward 100%.

PIERRE — Un agent IA open source et plurilingue au service du mouvement HLM

Claude Code + Codex 协作的自主交付工作流 skill 模板：独立 worktree 隔离、Heavy/Light 分流、Codex 假死 watchdog、并行自审，推进到干净 PR + CI。

AI Code Agent Taming 2026: Master 15K+ Line Repos Without Context Overflow Errors

AI agent skill repository: llg524062-stack/baizhi-skill-mcp

Orchestrate a crew of specialist AI agents in one local-first workspace. Each role on its best model, with memory and skills that compound. Free, MIT.

A desktop AI agent that sees your screen and acts on your behalf.

A Codex skill for keeping long AI work on track with summaries, structured memory, and timely clarification.

AI agent skill repository: WawaGuess/codex-pets-skill

Exercise: Integrate Model Context Protocol with GitHub Copilot

A community-maintained collection of agent skills for WordPress plugin and theme development.

The only AI stack nestled on a biodiverse agentic kernel framework

Codex skill for Seoul Outdoor Library Hipdok Club automation

Community registry of MCPs, skills, hooks, rules, and agents for AgentDock. Add this repo in Settings → Registry Sync to load capabilities into your Library.

Modular execution substrate for governed agentic workloads.