Home / robozephyr / ai-engineering-playbook · CLAUDE.md · GitHub

CLAUDE.md claudeA

Name: CLAUDE.md
Author: robozephyr

CLAUDE.md is agent-read markdown (claude) from robozephyr/ai-engineering-playbook.

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# AI Engineering Playbook — 项目约束

## 站点定位

本项目是一个 **AI Agent 工程实践知识库**（VitePress 文档站），核心目标：

1. **Harness Engineering** — Agent 工作环境设计方法论（CLAUDE.md/AGENTS.md、日志、知识管理、自进化）
2. **Skill 评估** — 对各类 AI 编码 Skill 进行评测、对比、打分
3. **流程搭建** — 按不同开发场景编排 Skill 使用流程（Workflow）
4. **模板沉淀** — 提供可直接复制使用的文档模板

## 内容边界

### 应该做的
- Harness 方法论：项目初始化、Context 设计、日志系统、知识管理、自进化机制
- 评测某个 Skill 的能力、优势、局限
- 对比同类 Skill 的差异和适用场景
- 编排特定场景下的 Skill 使用顺序（Workflow）
- 提供选型建议和使用注意事项
- 收录相关资源链接和调研报告
- 提供可复制的文档模板（CLAUDE.md、ADR、Solution 等）

### 不应该做的
- ❌ 绑定特定前端框架（Vue/Nuxt/React 等）— 保持技术中立
- ❌ 复制 Skill 的完整源码或 SKILL.md 内容 — 链接到原始仓库即可
- ❌ 做可执行的 Skill 运行时结构（.claude/skills 符号链接等）

## 技术栈

- VitePress 文档站
- 中文撰写，专有名词保留英文（Skill、Workflow、Claude Code）

## 写作规范

- 每条信息只在一处详细描述，其他地方链接引用
- Skill 评测使用统一模板（见根目录 CONTRIBUTING.md）
- 三级优先级标记：必装 / 推荐 / 视情况
- 善用表格做对照，流程用有序列表
- 评测必须基于实际使用，不做未验证的推荐

Read the whole file at its exact version.

How to install

Latest version

mdr add robozephyr/ai-engineering-playbook/CLAUDE.md@git:20260519.2b008ba

Exact content

mdr add robozephyr/ai-engineering-playbook/CLAUDE.md@sha256:188a7c2328855c44

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

[![mdr](https://markdownregistry.com/badge/art_4e6hmxg7kkmscwvp.svg)](https://markdownregistry.com/a/art_4e6hmxg7kkmscwvp)

1 badge views in 30 days

Versions

version	committed	commit	size	audit
git:20260519.2b008ba latest	2026-05-19	2b008ba	1,656 B	A	view

Audit of the latest version

A 14 of 14 checks passed. Deterministic, no model, same answer every run.

pass: Size between 200 bytes and 200 KB (1656 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag

Source

GitHub

robozephyr/ai-engineering-playbook · 3 stars · license none · pushed 2026-09-23 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_4e6hmxg7kkmscwvp
GET https://markdownregistry.com/api/v1/resolve?ref=robozephyr/ai-engineering-playbook/CLAUDE.md
GET https://markdownregistry.com/api/v1/blob/188a7c2328855c4483e0bbe660b3935aa52385501ba9576942600cc072fbaf11

Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.