agentleFS
nisarthnisarth/claude-skills-store/skills/devtools/claude-md-management/SKILL.md

CLAUDE.md Management

Skill1 starsChanged 7 months agoMITView on GitHub

Create and maintain CLAUDE.md project configuration files. Define project context, coding standards, tool preferences, and persistent memory for Claude Code sessions. Trigger phrases: "create CLAUDE.md", "update CLAUDE.md", "project config", "set up claude config", "configure claude for this project", "project context file"

The file

Show its rules and text

We split this skill into the rules it gives an agent

14 rules. About 0 are common, 11 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈11

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create and maintain CLAUDE.md files that give Claude Code persistent context about your project, coding standards, and preferences.

    line 15
  2. Very specific:

    Read package.json, pyproject.toml, Cargo.toml, or equivalent for tech stack

    line 29
  3. Very specific:

    Check for existing linter configs (.eslintrc, .prettierrc, ruff.toml)

    line 30
  4. Distinctive:

    Look for existing documentation (README.md, CONTRIBUTING.md)

    line 31
  5. Distinctive:

    Check for CI/CD configuration files

    line 33
  6. Distinctive:

    Ask the user about preferences not discoverable from the codebase:

    line 38
  7. Distinctive:

    Use clear, imperative language ("Use camelCase for variables")

    line 93
  8. Distinctive:

    Keep each section concise and scannable

    line 94
  9. Distinctive:

    Add warnings for common pitfalls

    line 97
  10. Distinctive:

    Verify the CLAUDE.md is effective:

    line 101
  11. Distinctive:

    Update the CLAUDE.md when:

    line 112
  12. Very specific:

    Action: Read pyproject.toml, check for ruff/mypy configs, identify the pipeline framework, and generate a CLAUDE.md with data engineering …

    line 145
  13. Distinctive:

    Version control it: - commit CLAUDE.md so the whole team benefits

    line 161
  14. Distinctive:

    Avoid duplication: - do not repeat what linter configs already enforce

    line 162

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

CLAUDE.md Management

Create and maintain CLAUDE.md files that give Claude Code persistent context about your project, coding standards, and preferences.

Prerequisites

  • A project directory to configure
  • Understanding of the project's tech stack and conventions
  • Knowledge of team coding standards and preferences

Workflow

Step 1: Assess the Project

Scan the project to understand its structure:

  1. Read package.json, pyproject.toml, Cargo.toml, or equivalent for tech stack
  2. Check for existing linter configs (.eslintrc, .prettierrc, ruff.toml)
  3. Look for existing documentation (README.md, CONTRIBUTING.md)
  4. Identify the test framework and test directory structure
  5. Check for CI/CD configuration files
  6. Note the directory layout and naming conventions

Step 2: Gather Preferences

Ask the user about preferences not discoverable from the codebase:

  1. Code style - beyond what linters enforce (naming conventions, file organization)
  2. Architecture patterns - MVC, hexagonal, functional, etc.
  3. Commit conventions - conventional commits, ticket references, etc.
  4. Testing philosophy - TDD, coverage targets, test naming
  5. Tool preferences - preferred commands for build, test, deploy
  6. Forbidden patterns - things Claude should never do in this project

Step 3: Structure the CLAUDE.md

Organize the file with these sections:

# Project Overview
Brief description of what the project does and its key technologies.

# Tech Stack
- Language, framework, and major dependencies
- Database and infrastructure details

# Project Structure
Key directories and their purposes.

# Coding Standards
- Naming conventions
- File organization rules
- Import ordering
- Error handling patterns

# Commands
- Build: `<command>`
- Test: `<command>`
- Lint: `<command>`
- Deploy: `<command>`

# Testing
- Framework and test file conventions
- How to run specific tests
- Coverage expectations

# Git Workflow
- Branch naming conventions
- Commit message format
- PR requirements

# Important Notes
- Critical warnings or gotchas
- Things Claude should always or never do

Step 4: Write the CLAUDE.md

Generate the file using the Write tool. Place it at the project root:

  1. Use clear, imperative language ("Use camelCase for variables")
  2. Keep each section concise and scannable
  3. Include actual commands, not placeholders
  4. List concrete examples for ambiguous rules
  5. Add warnings for common pitfalls

Step 5: Validate the Configuration

Verify the CLAUDE.md is effective:

  • Commands listed actually work when run
  • Referenced directories and files exist
  • Coding standards match existing code patterns
  • No contradictory instructions
  • File is under 200 lines for optimal context usage
  • Critical rules are near the top of the file

Step 6: Maintain Over Time

Update the CLAUDE.md when:

  • New dependencies or tools are added
  • Coding standards evolve
  • Project structure changes
  • New team conventions are adopted
  • Common mistakes are identified

Output Format

A single CLAUDE.md file at the project root containing:

  • Project overview in 2-3 sentences
  • Tech stack list
  • Project structure summary
  • Coding standards as bullet points
  • Runnable commands for common tasks
  • Testing conventions
  • Git workflow rules
  • Important warnings and notes

Examples

Example 1: Node.js Web Application

User: "Set up CLAUDE.md for our Express API"

Action: Scan package.json for dependencies, check for ESLint/Prettier configs, identify test framework, and generate a CLAUDE.md with API-specific conventions (route naming, middleware patterns, error response format).

Example 2: Python Data Pipeline

User: "Create CLAUDE.md for our data pipeline project"

Action: Read pyproject.toml, check for ruff/mypy configs, identify the pipeline framework, and generate a CLAUDE.md with data engineering conventions (typing requirements, logging standards, idempotency rules).

Example 3: Monorepo Setup

User: "Configure CLAUDE.md for our monorepo"

Action: Scan the workspace root and each package, identify shared tooling, and generate a root CLAUDE.md with cross-package rules plus guidance on per-package conventions.

Best Practices

  1. Be specific over general - "Use zod for validation" beats "validate inputs"
  2. Keep it short - Claude reads this every session; respect the context window
  3. Put critical rules first - most important instructions at the top
  4. Use imperative mood - "Run tests before committing" not "Tests should be run"
  5. Include real commands - paste actual CLI commands, not descriptions
  6. Update regularly - stale CLAUDE.md causes incorrect behavior
  7. Version control it - commit CLAUDE.md so the whole team benefits
  8. Avoid duplication - do not repeat what linter configs already enforce

Error Handling

ErrorCauseRecovery
Conflicting rulesTwo sections contradict each otherAudit and resolve conflicts, keep one source of truth
Stale commandsBuild/test commands changedRe-scan project config files and update
Overly long fileToo much detailTrim to essentials, move details to docs
Missing contextKey conventions not documentedInterview the team, add missing sections
Wrong tech stackProject evolved since CLAUDE.md was writtenRe-run assessment step

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.