agentleFS
PatriotAgenticLLCPatriotAgenticLLC/better_claude_skillz/skills/init-project/SKILL.md

init-project

Skill3 starsChanged 5 months agoMITView on GitHub

Initialize new project with standard structure

  • Reads credentials

49 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use addskill, apply-firmware and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • ryanportfolioSkill

    addskill

    Create, import, update, or install repo or personal skills: runtime ownership, resources, discovery checks.

    Also in 6 projects that use this

  • ryanportfolioSkill

    apply-firmware

    Bring current folder (plain folder, existing repo, old or partial firmware copy) up to full Harness Firmware in place. Mirror external repo → adopt-repo.

    Also in 6 projects that use this

  • +10 more from ryanportfolio

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 42 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create all standard directories

    line 198
  2. Distinctive:

    Create CLAUDE.md with templates

    line 202
  3. Distinctive:

    Create README.md with project info

    line 203
  4. Distinctive:

    Don't overwrite existing files without asking

    line 262

“Common” is measured: kept by at least 6 in 10 of the 42 edited versions of this file we could read. “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

Init Project: Initialize Project Structure

Overview

Set up a new project with the standard directory structure and configuration files for an AI development workflow.

Usage

/init-project [project-path]

Example:

/init-project ~/projects/my-new-project

What This Command Does

Creates the following structure in the target directory:

project-name/
├── .claude/
│   ├── plans/              # Implementation plans
│   ├── code-reviews/       # Code review outputs
│   ├── system-reviews/     # System evolution reviews
│   └── PRD.md              # Product requirements (if applicable)
│
├── CLAUDE.md               # Project-specific configuration
├── README.md               # Project overview
├── .gitignore              # Standard gitignore
└── [project files]

Generated Files

1. CLAUDE.md Template

# [Project Name] - Project Configuration

## Project Overview
[Brief description of what this project does]

## Tech Stack
- [Primary language and version]
- [Frameworks and major libraries]
- [Database/storage solution]

## Current Focus
[What we're working on right now]

## Key Files
- `[path]` - [Description]
- `[path]` - [Description]

## Development Commands

\`\`\`bash
# Start development server
[command]

# Run tests
[command]

# Build for production
[command]
\`\`\`

## Reference Documentation

**Read when working on:**
- [Topic]: `[path to relevant reference doc, if any]`

## Validation Commands

### Syntax & Style
\`\`\`bash
[linting command]
\`\`\`

### Unit Tests
\`\`\`bash
[test command]
\`\`\`

### Integration Tests
\`\`\`bash
[integration test command]
\`\`\`

## Code Conventions
- [Convention 1]
- [Convention 2]
- [Convention 3]

2. README.md Template

# [Project Name]

[Brief project description]

## Status

**Status:** Active | Paused | Archived
**Type:** Application | Internal Tool | Experiment
**Started:** YYYY-MM-DD

## Quick Start

\`\`\`bash
# Installation
[install commands]

# Development
[dev commands]

# Testing
[test commands]
\`\`\`

## Documentation

- [Architecture Documentation](docs/architecture.md)
- [API Documentation](docs/api.md)
- [Deployment Guide](docs/deployment.md)

## Development

See [CLAUDE.md](CLAUDE.md) for AI development workflow context.

## License

[License information]

3. .gitignore Template

Based on detected tech stack or user input:

Python:

__pycache__/
*.py[cod]
*$py.class
.venv/
venv/
*.egg-info/
dist/
build/
.pytest_cache/
.coverage
htmlcov/

Node.js:

node_modules/
npm-debug.log*
yarn-error.log*
dist/
build/
.env
.env.local
coverage/

General:

.DS_Store
Thumbs.db
*.swp
*.swo
.idea/
.vscode/
.claude/settings.local.json

Process

  1. Gather Information
    • Project name
    • Project type (application, internal tool, experiment)
    • Tech stack
    • Brief description
  2. Create Directory Structure
    • Create all standard directories
    • Create .claude/ subdirectories
  3. Generate Configuration Files
    • Create CLAUDE.md with templates
    • Create README.md with project info
    • Create appropriate .gitignore
  4. Initialize Git (if not already a repo)
    git init
    git add .
    git commit -m "chore: initialize project structure"
  5. Confirmation
    • List created files
    • Provide next steps

Interactive Questions

Ask the user:

  1. Project name? (infer from path if possible)
  2. Project type?
    • Application
    • Internal Tool
    • Experiment
  3. Tech stack?
    • Python (FastAPI, Flask, Django)
    • Node.js (Express, NestJS, Next.js)
    • PHP (WordPress, Laravel)
    • Other
  4. Brief description? (one sentence)
  5. Initialize git repository? (yes/no)

Output

After initialization, provide:

Project initialized successfully

Location: [full path]
Type: [project type]
Tech Stack: [stack]

Created:
- .claude/ (plans, code-reviews, system-reviews)
- CLAUDE.md (project configuration)
- README.md (project overview)
- .gitignore (tech stack specific)

Next steps:
1. Review and customize CLAUDE.md
2. Create PRD if needed: /create-prd .claude/PRD.md
3. Start development!

To prime the AI agent on this project:
/prime

Notes

  • Don't overwrite existing files without asking
  • Adapt templates based on tech stack
  • Include relevant reference doc paths in CLAUDE.md
  • Suggest appropriate reference docs based on tech stack

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.