All skills
brianlovin avatar

/reclaude

@21a5c1f official

Refactor CLAUDE.md files to follow progressive disclosure principles. Use when CLAUDE.md is too long or disorganized.

Use this Skill: https://skilld.dev/gh/brianlovin/claude-config/reclaude

This session only. Nothing lands on disk.

SKILL.md

≈32 tokens always: the name and description. ≈947 when used: this file.

reclaude

Refactor CLAUDE.md files to follow progressive disclosure principles.

Prompt

I want you to refactor my CLAUDE.md file to follow progressive disclosure principles.

Follow these steps:

1. Check length

Report the current line count. Flag issues:

  • Ideal: <50 lines
  • Acceptable: 50-100 lines
  • Needs refactoring: >100 lines (move content to .claude/rules/ files)

2. Integrate workflow orchestration

Read the workflow skill at ~/.claude/skills/workflow/SKILL.md and incorporate its principles into the CLAUDE.md or a .claude/rules/workflow.md file. Adapt the content to fit the project — don't copy verbatim, but ensure the key behaviors are represented:

  • Plan mode for non-trivial tasks
  • Subagent strategy
  • Self-improvement loop with tasks/lessons.md
  • Verification before marking tasks done
  • Elegance checks for non-trivial changes
  • Autonomous bug fixing

For short CLAUDE.md files, add a concise workflow section. For longer ones, create .claude/rules/workflow.md and link to it.

3. Ensure verification section exists

Check for a ## Verification section with commands Claude can run after making changes. If missing:

  • Look in package.json for test/lint/typecheck/build scripts
  • Look for Makefile, justfile, or other task runners
  • Add a ## Verification section with discovered commands

This is critical—Claude performs dramatically better when it can verify its work.

4. Find contradictions

Identify any instructions that conflict with each other. For each contradiction, ask me which version I want to keep.

5. Check for global skill extraction candidates

Look for content that could become a reusable global skill in ~/.claude/skills/:

  • Is about a tool/framework (not project-specific)
  • Same instructions appear (or would apply) in 2+ projects
  • Is substantial (>20 lines)

If found, suggest creating a global skill with name and description.

6. Identify essentials for root CLAUDE.md

Extract only what belongs in the root CLAUDE.md:

  • One-line project description
  • Package manager (if not npm)
  • Non-obvious commands only (skip npm test, npm run build if standard)
  • Links to .claude/rules/ files with brief descriptions
  • Verification section (always required)

7. Group remaining content

Organize remaining instructions into .claude/rules/ files by category (e.g., TypeScript conventions, testing patterns, API design, Git workflow).

8. Flag for deletion

Identify content that should be removed entirely:

  • API documentation — link to external docs instead
  • Code examples — Claude can infer from reading source files
  • Interface/type definitions — these exist in the code
  • Generic advice — "write clean code", "follow best practices"
  • Obvious instructions — "use TypeScript for .ts files"
  • Redundant info — things Claude already knows
  • Too vague — instructions that aren't actionable

Target Template

# Project Name

One-line description.

## Commands
- `command` - what it does (only non-obvious ones)

## Rules
- [Topic](/.claude/rules/topic.md) — brief description

## Verification
After making changes:
- `npm test` - Run tests
- `npm run lint` - Check linting

What to Keep vs Remove

Keep in CLAUDE.md:

  • Commands Claude can't guess from package.json
  • Non-standard patterns specific to this project
  • Project gotchas and footguns
  • Links to detailed rules files

Move to .claude/rules/:

  • Detailed conventions (>10 lines on a topic)
  • Style guides
  • Architecture decisions
  • Workflow documentation

Remove entirely:

  • Anything Claude can infer from reading the codebase
  • Standard practices for the language/framework
  • Documentation that exists elsewhere (link instead)

Source: SKILL.md on GitHub

No alerts16d5 checks · Risk SAFE
  • Gen Agent Trust Hub16d

    The skill refactors project-specific instructions and documentation. It involves reading local files like CLAUDE.md and project configuration files to generate new rule files. The main security consideration is an attack surface for indirect prompt injection, as the skill processes untrusted user-controlled documentation without explicit sanitization or boundary markers.

  • Socket16d

    No alerts

  • Snyk16d

    Risk: LOW · No issues

  • Runlayer7mo

    1/1 file flagged

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at 21a5c1f. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 months ago.

Dormantupdated 7 months ago

README badge

README badge for brianlovin/claude-config/reclaude

Refactors CLAUDE.md files using progressive disclosure principles, checking length, integrating workflow orchestration, ensuring verification sections, and organizing content into `.claude/rules/` subdirectories. Targets overly long or disorganized CLAUDE.md files by extracting reusable global skills and flagging redundant content for removal.

Generated from the current SKILL.md.

What is progressive disclosure in the context of CLAUDE.md?
Progressive disclosure means keeping the root CLAUDE.md concise (ideally under 50 lines) and moving detailed instructions into separate `.claude/rules/` files organized by topic. Claude reads the root file first, then loads specific rule files as needed.
Does this skill reorganize an existing CLAUDE.md or create one from scratch?
This skill refactors an existing CLAUDE.md file. It analyzes the current file's length and content, then guides you through restructuring it by moving content to `.claude/rules/` subdirectories and identifying what should stay in the root.
Will this skill integrate with other skills or workflows?
Yes. The skill reads the workflow skill at `~/.claude/skills/workflow/SKILL.md` and incorporates its principles (plan mode, subagent strategy, verification) into your project's CLAUDE.md or a new `.claude/rules/workflow.md` file.
Does this skill require me to manually answer questions?
Yes. When the skill finds contradictions in your instructions or suggests global skill extraction candidates, it will ask you which version to keep or whether to extract reusable content.
What happens if my CLAUDE.md has no verification section?
The skill will scan your package.json, Makefile, or justfile for test/lint/typecheck/build commands and add a `## Verification` section with discovered commands, since Claude performs better when it can verify its work.

Generated from the current SKILL.md. These answers refresh after source changes.