Token导航 LogoToken导航

Agent Skill · 前端设计

writing-claude-md-files(writing Claude MD files 控制)

用于辅助文档、README、Markdown、说明文和内容稿件的整理与改写。它适合让 Agent 提炼结构、补齐章节、统一术语、检查链接或把零散材料整理成可读文档。使用时应保留项目已有事实、命令和路径,不要把未确认的信息写成确定结论;涉及对外文案时,还需要控制语气,避免过度营销或夸大能力。

writing-claude-md-files 是前端设计类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为接触敏感数据;许可证信息还不明确,第三方扫描已通过,按安装量在前端设计类的 10,216 个 Skill 里排第 8,476。

总安装 282周安装 12GitHub Stars 176下载 99核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:writing-claude-md-files(writing Claude MD files 控制)
来源仓库:https://github.com/ed3dai/ed3d-plugins
仓库路径:skills/writing-claude-md-files
安装命令:
npx skills add https://github.com/ed3dai/ed3d-plugins --skill writing-claude-md-files
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/ed3dai/ed3d-plugins --skill writing-claude-md-files

这个 Skill 是做什么的

前端设计类 Skill 关注页面结构、视觉规范和组件写法,输出通常是可运行的界面代码。

用于辅助文档、README、Markdown、说明文和内容稿件的整理与改写。适合让 Agent 提炼结构、补齐章节、统一术语或检查链接。使用时保留项目已有事实和路径,避免写成确定结论。涉及对外文案时需控制语气,防止过度营销或夸大能力。安装方式:通过 GitHub 仓库添加技能。

writing-claude-md-files 属于前端设计类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/writing-claude-md-files

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/ed3dai/ed3d-plugins --skill writing-claude-md-…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

writing-claude-md-files 怎么安装?

在终端执行 npx skills add https://github.com/ed3dai/ed3d-plugins --skill writing-claude-md-files。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

writing-claude-md-files 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

writing-claude-md-files 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

writing-claude-md-files 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

writing-claude-md-files 用的人多吗?

公开数据是累计安装 282 次,近一周安装 12 次,下载 99 次,GitHub 176 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

writing-claude-md-files 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理前端设计类任务、又不想每次都手写提示词的人。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

前端设计类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
frontend-design

前端设计 · Codex、Claude

8,823,360126,072只读MIT通过
vercel-composition-patterns

Vercel 组合模式 · Codex、Claude

3,858,81625,893需要联网MIT通过
vercel-react-native-skills

Vercel React native skills 前端 · Codex、Claude

2,468,66425,878只读MIT通过
adapt

adapt 搜索 · Codex、Claude

2,027,04023,125操作浏览器未明确通过
bolder

bolder 分析 · Codex、Claude

2,004,28823,130只读未明确通过
writing-claude-md-files

writing Claude MD files 控制 · 本页

282176接触敏感数据未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Writing CLAUDE.md Files

REQUIRED BACKGROUND: Read ed3d-extending-claude:writing-claude-directives for foundational guidance on token efficiency, compliance techniques, and directive structure.

Core Principle

CLAUDE.md files bridge Claude's statelessness. They preserve context so humans don't re-explain architectural intent every session.

Key distinction:

  • Top-level: HOW to work in this codebase (commands, conventions)
  • Subdirectory: WHY this piece exists and what it PROMISES (contracts, intent)

File Hierarchy

Claude automatically reads CLAUDE.md files from current directory up to root:

project/
├── CLAUDE.md                    # Project-wide: tech stack, commands, conventions
└── src/
    └── domains/
        ├── auth/
        │   ├── CLAUDE.md        # Auth domain: purpose, contracts, invariants
        │   └── oauth2/
        │       └── CLAUDE.md    # OAuth2 subdomain (rare, only when needed)
        └── billing/
            └── CLAUDE.md        # Billing domain: purpose, contracts, invariants

Depth guideline: Typically one level (domain). Occasionally two (subdomain like auth/oauth2). Rarely more.

Top-Level CLAUDE.md

Focuses on project-wide WHAT and HOW.

What to Include

SectionPurpose
Tech StackFramework, language, key dependencies
CommandsBuild, test, run commands
Project StructureDirectory overview with purposes
ConventionsNaming, patterns used project-wide
BoundariesWhat Claude can/cannot edit

Template

# [Project Name]

Last verified: [DATE - use `date +%Y-%m-%d`]

## Tech Stack
- Language: TypeScript 5.x
- Framework: Next.js 14
- Database: PostgreSQL
- Testing: Vitest

## Commands
- `npm run dev` - Start dev server
- `npm run test` - Run tests
- `npm run build` - Production build

## Project Structure
- `src/domains/` - Domain modules (auth, billing, etc.)
- `src/shared/` - Cross-cutting utilities
- `src/infrastructure/` - External adapters (DB, APIs)

## Conventions
- Functional Core / Imperative Shell pattern
- Domain modules are self-contained
- See domain CLAUDE.md files for domain-specific guidance

## Boundaries
- Safe to edit: `src/`
- Never touch: `migrations/` (immutable), `*.lock` files

What NOT to Include

  • Code style rules (use linters)
  • Exhaustive command lists (reference package.json)
  • Content that belongs in domain-level files
  • Sensitive information (keys, credentials)

Subdirectory CLAUDE.md (Domain-Level)

Focuses on WHY and CONTRACTS. The code shows WHAT; these files explain intent.

What to Include

SectionPurpose
PurposeWHY this domain exists (not what it does)
ContractsWhat this domain PROMISES to others
DependenciesWhat it uses, what uses it, boundaries
Key DecisionsADR-lite: decisions and rationale
InvariantsThings that must ALWAYS be true
GotchasNon-obvious traps

Template

# [Domain Name]

Last verified: [DATE - use `date +%Y-%m-%d`]

## Purpose
[1-2 sentences: WHY this domain exists, what problem it solves]

## Contracts
- **Exposes**: [public interfaces - what callers can use]
- **Guarantees**: [promises this domain keeps]
- **Expects**: [what callers must provide]

## Dependencies
- **Uses**: [domains/services this depends on]
- **Used by**: [what depends on this domain]
- **Boundary**: [what should NOT be imported here]

## Key Decisions
- [Decision]: [Rationale]

## Invariants
- [Thing that must always be true]

## Key Files
- `index.ts` - Public exports
- `types.ts` - Domain types
- `service.ts` - Main service implementation

## Gotchas
- [Non-obvious thing that will bite you]

Example: Auth Domain

# Auth Domain

Last verified: 2025-12-17

## Purpose
Ensures user identity is verified exactly once at the system edge.
All downstream services trust the auth token without re-validating.

## Contracts
- **Exposes**: `validateToken(token) → User | null`, `createSession(credentials) → Token`
- **Guarantees**: Tokens expire after 24h. User objects always include roles.
- **Expects**: Valid JWT format. Database connection available.

## Dependencies
- **Uses**: Database (users table), Redis (session cache)
- **Used by**: All API routes, billing domain (user identity only)
- **Boundary**: Do NOT import from billing, notifications, or other domains

## Key Decisions
- JWT over session cookies: Stateless auth for horizontal scaling
- bcrypt cost 12: Legacy decision, migration to argon2 tracked in ADR-007

## Invariants
- Every user has exactly one primary email
- Deleted users are soft-deleted (is_deleted), never hard deleted
- User IDs are UUIDs, never sequential

## Key Files
- `service.ts` - AuthService implementation
- `tokens.ts` - JWT creation/validation
- `types.ts` - User, Token, Session types

## Gotchas
- Token validation returns null on invalid (doesn't throw)
- Never return raw password hashes in User objects

Freshness Dates: MANDATORY

Every CLAUDE.md MUST include a "Last verified" date.

CRITICAL: Use Bash to get the actual date. Do NOT hallucinate dates.

date +%Y-%m-%d

Include in file:

Last verified: 2025-12-17

Why mandatory: Stale CLAUDE.md files are worse than none. The date signals when contracts were last confirmed accurate.

Referencing Files

You can reference key files in CLAUDE.md:

## Key Files
- `index.ts` - Public exports
- `service.ts` - Main implementation

Do NOT use @ syntax (e.g., @./service.ts). This force-loads files into context, burning tokens. Just name the files; Claude can read them when needed.

Heuristics: Top-Level vs Subdirectory

QuestionTop-levelSubdirectory
Applies project-wide?✓
New engineer needs on day 1?✓
About commands/conventions?✓
About WHY a component exists?✓
About contracts between parts?✓
Changes when the domain changes?✓

Rule of thumb:

  • Top-level = "How to work here"
  • Subdirectory = "Why this exists and what it promises"

When to Create Subdirectory CLAUDE.md

Create when:

  • Domain has non-obvious contracts with other parts
  • Architectural decisions affect how code should evolve
  • Invariants exist that aren't obvious from code
  • New sessions consistently need the same context re-explained

Don't create for:

  • Trivial utility folders
  • Implementation details that change frequently
  • Content better captured in code comments

Updating CLAUDE.md Files

When updating any CLAUDE.md:

  1. Update the freshness date using Bash date +%Y-%m-%d
  2. Verify contracts still hold - read the code, check invariants
  3. Remove stale content - better short and accurate than long and wrong
  4. Keep token-efficient - <300 lines top-level, <100 lines subdirectory

Common Mistakes

MistakeFix
Describing WHAT code doesFocus on WHY it exists, contracts it keeps
Missing freshness dateAlways include, always use Bash for real date
Using @ to reference filesJust name files, let Claude read on demand
Too much detailSubdirectory files should be <100 lines
Duplicating parent contentSubdirectory inherits parent; don't repeat
Stale contractsUpdate when domain changes; verify dates

Checklist

Top-level:

  • Tech stack listed
  • Key commands documented
  • Project structure overview
  • Freshness date (from date +%Y-%m-%d)

Subdirectory:

  • Purpose explains WHY (not what)
  • Contracts: exposes, guarantees, expects
  • Dependencies and boundaries clear
  • Key decisions with rationale
  • Invariants documented
  • Freshness date (from date +%Y-%m-%d)
  • Under 100 lines

平台分布

Codex

34.22%
按下载量换算34

Claude

33.55%
按下载量换算33

Cursor

20.56%
按下载量换算20

Gemini CLI

9.46%
按下载量换算9

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills