New to Claude Skills? Learn how to install them →

davila7 on GitHub

Agent MD Refactor

Free

Streamline your agent documentation with structured clarity.

Get this skill

Free · Opens the source repo

What Agent MD Refactor does

Agent MD Refactor is a specialized tool designed to help developers and designers manage and optimize their agent instruction files, such as AGENTS.md and CLAUDE.md. This skill applies progressive disclosure principles to transform bloated and monolithic documentation into organized, linked files that enhance readability and usability. By breaking down complex instructions into manageable sections, it ensures that essential information is easily accessible while allowing for detailed guidance to be categorized and linked appropriately.

The process begins with an analysis phase where the skill identifies contradictions within the existing documentation. This is crucial for resolving any conflicting instructions that could confuse users. Once contradictions are addressed, the skill extracts only the core instructions that apply universally to all tasks, ensuring that the root file remains concise and focused. The remaining instructions are then grouped into logical categories, creating a clear structure that aids in navigation and comprehension.

Following the categorization, the skill generates a well-organized file hierarchy, linking the root document to the categorized files. This structure not only improves the flow of information but also adheres to best practices in documentation management. Finally, the skill flags redundant or vague instructions for deletion, further streamlining the documentation and ensuring that only actionable content remains.

This skill is particularly beneficial for teams that frequently update their agent configurations or have extensive documentation that needs regular maintenance. By using Agent MD Refactor, users can maintain clarity and coherence in their documentation, ultimately improving the efficiency of their development processes.

When to use it

Use this skill when your agent documentation has become too lengthy or disorganized, and you need to apply structured clarity to your instructions.

When not to use it

This skill may not be suitable for simple projects with minimal documentation needs or for users who prefer to keep all instructions in a single file.

What you can build with it

Refactoring a Large AGENTS.md

When your AGENTS.md has grown too long and unwieldy, use this skill to refactor it into a concise root file with linked details.

Organizing CLAUDE.md for Clarity

If your CLAUDE.md file is cluttered with mixed instructions, this skill can help categorize and structure it for better readability.

Streamlining Documentation for a Team

For teams that frequently update agent configurations, this skill ensures documentation remains clear and easy to navigate.

How to install Agent MD Refactor

View source

1. Install with the skills CLI

npx skills add davila7/claude-code-templates/agent-md-refactor --agent claude-code

2. Or install it manually

Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.

Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs

Inside SKILL.md

Written by davila7

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

Frequently asked questions about Agent MD Refactor

Similar skills