NickCollect

AI Coding Runbook — AI skill for Claude Code

AI community

Multi-vendor AI coding knowledge base.

How to install AI Coding Runbook

This entry records only its repository, not the path inside it, so there is no exact command to give. Open NickCollect/ai-coding-runbook and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What AI Coding Runbook does

Multi-vendor AI coding knowledge base. Auto-synced docs for Claude Code, Cursor, Codex, OpenAI, Gemini. Long-term context for AI agents — clone, open, ask.

Alternatives in AI

  • Skill Seekers Roadmap — Transform Skill Seekers into the easiest way to create Claude AI skills from any knowledge source - documentat 11.1k ★
  • Hindsight — State-of-the-art long-term memory for AI agents by Vectorize 6.7k ★
  • Nocturne Memory — A lightweight, rollbackable, and visual Long-Term Memory Server for MCP Agents 1.3k ★

README

AI Coding Runbook

[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](./LICENSE) [![Last commit](https://img.shields.io/github/last-commit/NickCollect/ai-coding-runbook)](https://github.com/NickCollect/ai-coding-runbook/commits/main) [![Repo size](https://img.shields.io/github/repo-size/NickCollect/ai-coding-runbook)](https://github.com/NickCollect/ai-coding-runbook) [![GHA: refresh-raw](https://github.com/NickCollect/ai-coding-runbook/actions/workflows/refresh-raw.yml/badge.svg)](https://github.com/NickCollect/ai-coding-runbook/actions/workflows/refresh-raw.yml) [![Stars](https://img.shields.io/github/stars/NickCollect/ai-coding-runbook?style=social)](https://github.com/NickCollect/ai-coding-runbook/stargazers)

[English](./README.en.md) | **中文**

**如果你同时用 Claude Code / Cursor / Codex CLI / Gemini / MCP,且烦透了在多家官方文档之间反复跳**,这个 repo 给你一个**本地、可搜索、给 AI agent 读的多厂商 AI 编程知识库**。每周自动抓 4 家官方文档 + MCP 协议生态 + LLM 加工成可查询 wiki,clone 完直接给 agent 当 long-term context。


这个项目解决什么问题

如果你 ——

  • 重度用 Claude Code / Cursor / Codex CLI,但每周都要追各家 release notes / 新 feature
  • 想跨厂商对比("我该用 Skills 还是 MCP server?Cursor 的 Rules 跟 Claude 的 CLAUDE.md 一样吗?"),但官方站只讲自家
  • 想给你的 AI agent 喂 long-term 多厂商上下文,但市面没现成的开源选项
  • 文档变化快,模型权重过期,agent 答的不一定是最新版

那这个 repo 把这 4 家官方文档(Anthropic / OpenAI / Google / Cursor)+ MCP 协议生态**每周自动抓** + LLM **加工成可查询的 entity / cheatsheet / decision matrix**,clone 完就能直接给 agent 当 long-term context。


适合谁用

✅ **适合**:

  • AI coding tool 重度用户(Claude Code / Cursor / Codex CLI / Aider 等任意一种或多种)
  • 想跟踪 Claude / OpenAI / Gemini / Cursor 各家文档变化的开发者
  • 想给自己的 AI agent 喂多厂商 long-term context 的人
  • 团队想沉淀 "什么场景该用什么工具" 的内部知识,但不想自己抓文档
  • AI 内容创作者 / 顾问,常需要查多家文档对比

❌ **不适合**:

  • 找最新模型 benchmark 数字(去 lmarena / Artificial Analysis 等专业 site)
  • 找代码示例运行(去 official cookbook / quickstart repos)
  • 需要实时(< 1 周)文档变化(当前 cron 周更新)

和同类方案的区别

各家 official docs awesome-* 链接列表 Context7 / 类似商业 service 本仓库
多厂商聚合