Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.
npx skills add https://github.com/softaworks/agent-toolkit --skill 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.
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:
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
Execute git commit with conventional commit message analysis, intelligent staging, and message generation. Use when user asks to commit changes, create a git commit, or mentions "/commit". Supports: (1) Auto-detecting type and scope from changes, (2) Generating conventional commit messages from diff, (3) Interactive commit with optional type/scope/description overrides, (4) Intelligent file staging for logical grouping
Comprehensive GitHub code review with AI-powered swarm coordination
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
Use this skill to review code. It supports both local changes (staged or working tree) and remote Pull Requests (by ID or URL). It focuses on correctness, maintainability, and adherence to project standards.
> Ultra-compressed code review comments. Cuts noise from PR feedback while preserving says "review this PR", "code review", "review the diff", "/review", or invokes /caveman-review. Auto-triggers when reviewing pull requests.
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.
Take softaworks/agent-md-refactor from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.