做什么
重构出膨胀的AGENTS.md,CLAUDE.md,或类似的代理指令文件,以遵循渐进披露原则. 将单文文件分为有组织,有链接的文档.
技能库 智客分类:文档办公 agent-md-refactor
重构出膨胀的AGENTS.md,CLAUDE.md,或类似的代理指令文件,以遵循渐进披露原则. 将单文文件分为有组织,有链接的文档.
官方网址:skills.sh
先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。
重构出膨胀的AGENTS.md,CLAUDE.md,或类似的代理指令文件,以遵循渐进披露原则. 将单文文件分为有组织,有链接的文档.
官方 description 未单独写出 Use when。按规范,代理会在用户任务与这段 description 的关键词匹配时激活本技能。
按 Agent Skills 渐进披露:启动时只加载 name 与 description(约 100 token);任务匹配后才读入整份 SKILL.md 正文;scripts/、references/、assets/ 仅在需要时再读。 本文件正文结构:Agent MD Refactor、Triggers、Quick Reference、Process、Phase 1: Find Contradictions、Contradiction Found。
文件分析:这是一份仅含 SKILL.md 的指令型技能,代理激活后整份正文进入上下文。
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.
Agent MD RefactorTriggersQuick ReferenceProcessPhase 1: Find ContradictionsContradiction FoundPhase 2: Identify the EssentialsPhase 3: Group the RestPhase 4: Create the File StructureProject NameQuick ReferenceDetailed Instructions
· 许可:MIT
来源分类:skills.sh agent-skill
nameagent-md-refactordescription具体调用语法与可用工具以目标 Agent 客户端为准。 查看调用机制说明 ↗
先选择目标 Agent 和安装范围,保留技能包的附属文件,安装后检查客户端能否发现该技能。
复制安装指令给支持 Agent Skills 的代理,确认其中的目标目录与客户端匹配。
把 Agent Skill「agent-md-refactor」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-5bfa5972193e3e4c-%E4%BB%A3%E7%90%86-Md-%E9%87%8D%E6%9E%84.html 请存为 .cursor/skills/agent-md-refactor/SKILL.md 或 .claude/skills/agent-md-refactor/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。
需要 Node.js 与 npx。先查看仓库技能列表,确认实际名称。
npx skills add 'https://github.com/softaworks/agent-toolkit' --list
npx skills add 'https://github.com/softaworks/agent-toolkit' --skill 'agent-md-refactor'
CLI 会交互选择目标 Agent,默认安装到项目;用户级安装使用 -g。先通过查看命令核对仓库内容,再用 npx skills list 检查已安装技能。
Refactor bloated agent instruction files (AGENTS.md, CLAUDE.md, COPILOT.md, etc.) to follow progressive disclosure principles - keeping essentials at root and organizing the rest into linked, categorized files.
Use this skill when:
| Phase | Action | Output | |-------|--------|--------| | 1. Analyze | Find contradictions | List of conflicts to resolve | | 2. Extract | Identify essentials | Core instructions for root file | | 3. Categorize | Group remaining instructions | Logical categories | | 4. Structure | Create file hierarchy | Root + linked files | | 5. Prune | Flag for deletion | Redundant/vague instructions |
Identify any instructions that conflict with each other.
Look for:
For each contradiction found:
## Contradiction Found
**Instruction A:** [quote]
**Instruction B:** [quote]
**Question:** Which should take precedence, or should both be conditional?
Ask the user to resolve before proceeding.
Extract ONLY what belongs in the root agent file. The root should be minimal - information that applies to every single task.
Essential content (keep in root): | Category | Example | |----------|---------| | Project description | One sentence: "A React dashboard for analytics" | | Package manager | Only if not npm (e.g., "Uses pnpm") | | Non-standard commands | Custom build/test/typecheck commands | | Critical overrides | Things that MUST override defaults | | Universal rules | Applies to 100% of tasks |
NOT essential (move to linked files):
Organize remaining instructions into logical categories.
Common categories:
| Category | Contents |
|----------|----------|
| typescript.md | TS conventions, type patterns, strict mode rules |
| testing.md | Test frameworks, coverage, mocking patterns |
| code-style.md | Formatting, naming, comments, structure |
| git-workflow.md | Commits, branches, PRs, reviews |
| architecture.md | Patterns, folder structure, dependencies |
| api-design.md | REST/GraphQL conventions, error handling |
| security.md | Auth patterns, input validation, secrets |
| performance.md | Optimization rules, caching, lazy loading |
Grouping rules:
{topic}.mdOutput structure:
project-root/
├── CLAUDE.md (or AGENTS.md) # Minimal root with links
└── .claude/ # Or docs/agent-instructions/
├── typescript.md
├── testing.md
├── code-style.md
├── git-workflow.md
└── architecture.md
Root file template:
# Project Name
One-sentence description of the project.
## Quick Reference
- **Package Manager:** pnpm
- **Build:** `pnpm build`
- **Test:** `pnpm test`
- **Typecheck:** `pnpm typecheck`
## Detailed Instructions
For specific guidelines, see:
- [TypeScript Conventions](.claude/typescript.md)
- [Testing Guidelines](.claude/testing.md)
- [Code Style](.claude/code-style.md)
- [Git Workflow](.claude/git-workflow.md)
- [Architecture Patterns](.claude/architecture.md)
Each linked file template:
# {Topic} Guidelines
## Overview
Brief context for when these guidelines apply.
## Rules
### Rule Category 1
- Specific, actionable instruction
- Another specific instruction
### Rule Category 2
- Specific, actionable instruction
## Examples
### Good
\`\`\`typescript
// Example of correct pattern
\`\`\`
### Avoid
\`\`\`typescript
// Example of what not to do
\`\`\`
Identify instructions that should be removed entirely.
Delete if: | Criterion | Example | Why Delete | |-----------|---------|------------| | Redundant | "Use TypeScript" (in a .ts project) | Agent already knows | | Too vague | "Write clean code" | Not actionable | | Overly obvious | "Don't introduce bugs" | Wastes context | | Default behavior | "Use descriptive variable names" | Standard practice | | Outdated | References deprecated APIs | No longer applies |
Output format:
## Flagged for Deletion
| Instruction | Reason |
|-------------|--------|
| "Write clean, maintainable code" | Too vague to be actionable |
| "Use TypeScript" | Redundant - project is already TS |
| "Don't commit secrets" | Agent already knows this |
| "Follow best practices" | Meaningless without specifics |
[ ] Phase 1: All contradictions identified and resolved
[ ] Phase 2: Root file contains ONLY essentials
[ ] Phase 3: All remaining instructions categorized
[ ] Phase 4: File structure created with proper links
[ ] Phase 5: Redundant/vague instructions removed
[ ] Verify: Each linked file is self-contained
[ ] Verify: Root file is under 50 lines
[ ] Verify: All links work correctly
| Avoid | Why | Instead | |-------|-----|---------| | Keeping everything in root | Bloated, hard to maintain | Split into linked files | | Too many categories | Fragmentation | Consolidate related topics | | Vague instructions | Wastes tokens, no value | Be specific or delete | | Duplicating defaults | Agent already knows | Only override when needed | | Deep nesting | Hard to navigate | Flat structure with links |
# CLAUDE.md
This is a React project.
## Code Style
- Use 2 spaces
- Use semicolons
- Prefer const over let
- Use arrow functions
... (200 more lines)
## Testing
- Use Jest
- Coverage > 80%
... (100 more lines)
## TypeScript
- Enable strict mode
... (150 more lines)
# CLAUDE.md
React dashboard for real-time analytics visualization.
## Commands
- `pnpm dev` - Start development server
- `pnpm test` - Run tests with coverage
- `pnpm build` - Production build
## Guidelines
- [Code Style](.claude/code-style.md)
- [Testing](.claude/testing.md)
- [TypeScript](.claude/typescript.md)
After refactoring, verify:
文档办公
为结构化的代理内存和可堆肥技能所打入的知识图. 在创建/征服实体(Person, project, Task, Evention, Document)时使用,链接相关对象,强制约束,规划多步动作作为图变,或技能需要共享状态时使用. 触发到"记住","我知道什么","链接X到Y",…
文档办公
使用纳米-pdf CLI编辑带有自然语言指令的PDF.
文档办公
创建,检查,并编辑有可靠样式的Microsoft Word文档和DOCX文件,编号,跟踪更改,表格,章节,并进行相容性检查. 当 (1) 任务涉及 Word 或 ".docx " 时使用; (2) 文件包括跟踪的更改,评论,字段,表格,模板,或页面布局限制; (3) 文档必须在不…
文档办公
通过 Maton 网关调用第三方 API, 它为用户已经连接的应用程序注入证书 。 当用户命名一个连接的应用程序和其中的具体行动时使用此技能——读取一个邮箱,查询一个CMM,归档一个问题,更新一个电子表格,通过一个连接的搜索或刮取提供者运行一个查询. 每一次通话都到用户连接的应用…