SkillAtlasSkill 详情

agent-md-refactor

Opinionated skills shared by @leonardocouy for improving daily work efficiency with Claude Code.

审核状态:已审核Quality 80Security 92

复制安装命令

用 Codex 或 Claude 安装复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它先审查 Skill 页面再帮你安装。

复制前请先查看来源、License 和安全提示。

项目 README

来源文件:README.md

抓取于 2026年8月15日

Softaworks Agent Skills

Opinionated skills shared by @leonardocouy for improving daily work efficiency with Claude Code. Skills are packaged instructions and scripts that extend agent capabilities across development, documentation, planning, and professional workflows.

Skills follow the Agent Skills format.


🧭 Quick Navigation

🚀 Installation • 📚 Available Skills • 🤖 Agents & Commands • 📖 Skill Structure • 🤝 Contributing • 📄 License • 🔗 Links


🚀 Installation

Quick Install (Recommended)

npx skills add softaworks/agent-toolkit

This method works with multiple AI coding agents (Claude Code, Codex, Cursor, AdaL, etc.)

Register as Plugin Marketplace

Run the following commands in Claude Code:

/plugin marketplace add softaworks/agent-toolkit
/plugin

Install Plugins

Option 1: Via Browse UI

  1. Switch to Marketplaces tab (use arrow keys or Tab)
  2. Select agent-toolkit, press Enter
  3. Browse and select the plugin(s) you want to install
  4. Select Install now

Option 2: Direct Install

# Install specific skill
/plugin install codex@agent-toolkit
/plugin install humanizer@agent-toolkit

# Install specific agent
/plugin install agent-codebase-pattern-finder@agent-toolkit

# Install specific command
/plugin install command-codex-plan@agent-toolkit

Option 3: Ask the Agent

Simply tell Claude Code:

Please install Skills from github.com/softaworks/agent-toolkit

Available Plugins

Each skill, agent, and command is an individual plugin that can be installed separately:

  • Skills → See Available Skills for the full list
  • Agents → See Agents (install as agent-<name>@agent-toolkit)
  • Commands → See Slash Commands (install as command-<name>@agent-toolkit)

Update Plugins

To update plugins to the latest version:

  1. Run /plugin in Claude Code
  2. Switch to Marketplaces tab
  3. Select agent-toolkit
  4. Choose Update marketplace

You can also Enable auto-update to get the latest versions automatically.

Manual Installation

For Claude Code (Manual) — Skills only

cp -r skills/<skill-name> ~/.claude/skills/

For claude.ai — Skills only

Add skills to project knowledge or paste SKILL.md contents into the conversation.


📚 Available Skills

CategorySkillDescription
🤖 AI ToolscodexAdvanced code analysis with GPT-5.2
🤖 AI ToolsgeminiLarge-scale review (200k+ context)
🤖 AI ToolsperplexityWeb search & research
🔮 Metaagent-md-refactorRefactor bloated agent instruction files
🔮 Metacommand-creatorCreate Claude Code slash commands
🔮 Metaplugin-forgeBuild Claude Code plugins & manifests
🔮 Metaskill-judgeEvaluate skill design quality
📝 Documentationbackend-to-frontend-handoff-docsAPI handoff docs for frontend
📝 Documentationc4-architectureC4 architecture diagrams with Mermaid
📝 Documentationcrafting-effective-readmesWrite effective README files
📝 Documentationdraw-ioCreate & edit draw.io diagrams
📝 DocumentationexcalidrawWork with Excalidraw diagrams
📝 Documentationfrontend-to-backend-requirementsDocument API requirements
📝 Documentationmarp-slideProfessional presentation slides
📝 Documentationmermaid-diagramsSoftware diagrams with Mermaid
📝 Documentationwriting-clearly-and-conciselyClear, professional writing
🎨 Design & Frontenddesign-system-starterCreate design systems
🎨 Design & FrontendmuiMaterial-UI v7 patterns
🎨 Design & Frontendopenapi-to-typescriptConvert OpenAPI to TypeScript
🎨 Design & Frontendreact-devType-safe React 18-19 with TypeScript
🎨 Design & Frontendreact-useeffectReact useEffect best practices
🛠️ Developmentdatabase-schema-designerDesign robust database schemas
🛠️ Developmentdependency-updaterSmart dependency management
🛠️ Developmentnaming-analyzerSuggest better variable/function names
🛠️ Developmentlesson-learnedExtract SE lessons from recent code changes
🛠️ Developmentreducing-entropyMinimize codebase size
🛠️ Developmentsession-handoffSeamless AI session transfers
🎯 Planninggame-changing-featuresFind 10x product opportunities
🎯 PlanninggepettoDetailed implementation planning
🎯 Planningrequirements-clarityClarify requirements before coding
🎯 Planningship-learn-nextTurn learning into actionable reps
👔 Professionaldaily-meeting-updateInteractive daily standup generator
👔 Professionaldifficult-workplace-conversationsNavigate difficult conversations
👔 Professionalfeedback-masteryDeliver constructive feedback
👔 Professionalprofessional-communicationTechnical communication guide
🧪 Testingqa-test-plannerComprehensive QA test planning
📦 Gitcommit-workHigh-quality git commits
🔧 Utilitiesdatadog-cliDebug with Datadog logs & metrics
🔧 Utilitiesdomain-name-brainstormerGenerate & check domain names
🔧 UtilitieshumanizerRemove AI writing patterns
🔧 Utilitiesmeme-factoryGenerate memes with API
🔧 UtilitiesjiraNatural language Jira interaction
🔧 Utilitiesweb-to-markdownConvert webpages to Markdown

🤖 Agents & Commands

Requires Claude Code CLI — These agents and commands are exclusive to Claude Code users.

For full access, add the marketplace and install plugins:

/plugin marketplace add softaworks/agent-toolkit
/plugin install codex@agent-toolkit

Agents

Specialized sub-agents that Claude Code can delegate tasks to:

AgentDescription
ascii-ui-mockup-generatorVisualize UI concepts through ASCII mockups
codebase-pattern-finderFind similar implementations and patterns
communication-excellence-coachEmail refinement, tone calibration, roleplay
general-purposeDefault agent for complex multi-step tasks
mermaid-diagram-specialistCreate flowcharts, sequence diagrams, ERDs
ui-ux-designerResearch-backed UI/UX design feedback

Slash Commands

Reusable workflows invoked with /command-name:

CommandDescription
/codex-planCreate implementation plans using Codex 5.2
/compose-emailDraft professional emails
/explain-changes-mental-modelBuild mental model of code changes
/explain-pr-changesGenerate PR summaries
/sync-branchSync feature branch with main
/sync-skills-readmeUpdate README skills table
/viral-tweetOptimize tweet ideas for X engagement

📖 Skill Structure

Each skill contains:

  • SKILL.md - Detailed instructions for the agent (with YAML frontmatter)
  • README.md - User-friendly documentation with examples
  • scripts/ - Helper scripts for automation (optional)
  • references/ - Supporting documentation (optional)

🤝 Contributing

Contributions are welcome! When adding new skills:

  1. Follow the Agent Skills format
  2. Include both SKILL.md (for agents) and README.md (for users)
  3. Add YAML frontmatter to SKILL.md with name: and description: fields
  4. Update this README.md with a link to your skill

📄 License

MIT


🔗 Links

Agent / MCP / Skill 创作

低风险

  • 来源需自行核对维护者身份。
  • 包含脚本或命令调用,安装前请复核。
  • 未检测到明显外部权限要求。
  • 未检测到高风险命令。
  • 扫描发现:0 条。

Codex — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/softaworks/agent-toolkit.git
  3. 将 "skills/agent-md-refactor" 文件夹复制到 Codex 的 skills 目录中。
  4. 重启 Codex 让新的 skill 生效。

Codex — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Codex 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Codex 让新的 skill 生效。

Claude Code — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/softaworks/agent-toolkit.git
  3. 将 "skills/agent-md-refactor" 文件夹复制到 Claude Code 的 skills 目录中。
  4. 重启 Claude Code 让新的 skill 生效。

Claude Code — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Claude Code 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Claude Code 让新的 skill 生效。

Cursor — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/softaworks/agent-toolkit.git
  3. 将 "skills/agent-md-refactor" 文件夹复制到 Cursor 的 skills 目录中。
  4. 重启 Cursor 让新的 skill 生效。

Cursor — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Cursor 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Cursor 让新的 skill 生效。

GitHub Copilot — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/softaworks/agent-toolkit.git
  3. 将 "skills/agent-md-refactor" 文件夹复制到 GitHub Copilot 的 skills 目录中。
  4. 重启 GitHub Copilot 让新的 skill 生效。

GitHub Copilot — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 GitHub Copilot 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 GitHub Copilot 让新的 skill 生效。

Windsurf — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/softaworks/agent-toolkit.git
  3. 将 "skills/agent-md-refactor" 文件夹复制到 Windsurf 的 skills 目录中。
  4. 重启 Windsurf 让新的 skill 生效。

Windsurf — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Windsurf 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Windsurf 让新的 skill 生效。
查看 SKILL.md 原文
name: agent-md-refactor
description: Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.
license: MIT

Agent MD Refactor

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.


Triggers

Use this skill when:

  • "refactor my AGENTS.md" / "refactor my CLAUDE.md"
  • "split my agent instructions"
  • "organize my CLAUDE.md file"
  • "my AGENTS.md is too long"
  • "progressive disclosure for my instructions"
  • "clean up my agent config"

Quick Reference

PhaseActionOutput
1. AnalyzeFind contradictionsList of conflicts to resolve
2. ExtractIdentify essentialsCore instructions for root file
3. CategorizeGroup remaining instructionsLogical categories
4. StructureCreate file hierarchyRoot + linked files
5. PruneFlag for deletionRedundant/vague instructions

Process

Phase 1: Find Contradictions

Identify any instructions that conflict with each other.

Look for:

  • Contradictory style guidelines (e.g., "use semicolons" vs "no semicolons")
  • Conflicting workflow instructions
  • Incompatible tool preferences
  • Mutually exclusive patterns

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.


Phase 2: Identify the Essentials

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):

CategoryExample
Project descriptionOne sentence: "A React dashboard for analytics"
Package managerOnly if not npm (e.g., "Uses pnpm")
Non-standard commandsCustom build/test/typecheck commands
Critical overridesThings that MUST override defaults
Universal rulesApplies to 100% of tasks

NOT essential (move to linked files):

  • Language-specific conventions
  • Testing guidelines
  • Code style details
  • Framework patterns
  • Documentation standards
  • Git workflow details

Phase 3: Group the Rest

Organize remaining instructions into logical categories.

Common categories:

CategoryContents
typescript.mdTS conventions, type patterns, strict mode rules
testing.mdTest frameworks, coverage, mocking patterns
code-style.mdFormatting, naming, comments, structure
git-workflow.mdCommits, branches, PRs, reviews
architecture.mdPatterns, folder structure, dependencies
api-design.mdREST/GraphQL conventions, error handling
security.mdAuth patterns, input validation, secrets
performance.mdOptimization rules, caching, lazy loading

Grouping rules:

  1. Each file should be self-contained for its topic
  2. Aim for 3-8 files (not too granular, not too broad)
  3. Name files clearly: {topic}.md
  4. Include only actionable instructions

Phase 4: Create the File Structure

Output 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
\`\`\`

Phase 5: Flag for Deletion

Identify instructions that should be removed entirely.

Delete if:

CriterionExampleWhy 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
OutdatedReferences deprecated APIsNo 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 |

Execution Checklist

[ ] 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

Anti-Patterns

AvoidWhyInstead
Keeping everything in rootBloated, hard to maintainSplit into linked files
Too many categoriesFragmentationConsolidate related topics
Vague instructionsWastes tokens, no valueBe specific or delete
Duplicating defaultsAgent already knowsOnly override when needed
Deep nestingHard to navigateFlat structure with links

Examples

Before (Bloated Root)

# 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)

After (Progressive Disclosure)

# 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)

Verification

After refactoring, verify:

  1. Root file is minimal - Under 50 lines, only universal info
  2. Links work - All referenced files exist
  3. No contradictions - Instructions are consistent
  4. Actionable content - Every instruction is specific
  5. Complete coverage - No instructions were lost (unless flagged for deletion)
  6. Self-contained files - Each linked file stands alone

发现问题?提交给管理员复核

评分:

评论 (0)

暂无评论,成为第一个评论者吧!