agentleFS
shaunandrewsshaunandrews/agent-skills/skills/project-setup/SKILL.md

project-setup

Skill8 starsChanged 2 months agoMITView on GitHub

Set up a new project with standard structure, git, README, CLAUDE.md, and dev server config. Use when starting a new project or bootstrapping a workspace for a new initiative.

  • Reads credentials

48 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use creative-writing-craft, creative-writing-muse 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.
  • Abdullokh-NSkill

    creative-writing-craft

    Справочник ремесла: проза, сцена, стиль, голос. Загружать, когда нужно знание "как писать", а не режим производства.

    Also in 3 projects that use this

  • Abdullokh-NSkill

    creative-writing-muse

    Точка входа в набор скилов для длинной прозы. Включается, когда автор просит спланировать, написать, продолжить, переписать или разобрать художественный текст — роман, повесть, цикл рассказов. Ведёт маршрут от замысла к готовому куску и держит базу знаний проекта.

    Also in 3 projects that use this

  • badgidsSkill

    character-sim

    Pressure-test a character by speaking or reasoning strictly from that character's current voice, goals, relationships, emotional pressure, and knowledge boundary without creating canon by accident.

    Also in 3 projects that use this

  • jpsweeney97Skill

    writing-principles

    Enforces writing principles for instruction documents (SKILL.md, skill supporting files, subagents, CLAUDE.md). Use when writing, reviewing, or editing any file in **/skills/**/*.md, **/agents/*.md, or **/CLAUDE.md. Triggers on skill creation, skill file updates, CLAUDE.md changes, subagent authoring, or instruction document review.

    Also in 3 projects that use this

  • ItsSidharthaSkill

    story-planning

    Collaborative planning skill for a GitHub issue. Takes issue content and codebase context as input. Runs an iterative clarification loop until the user explicitly agrees to a plan, then saves it to docs/<story_number>/plan.md. Used by the user-story-implementation skill — load this skill at the start of Phase 1 and follow it completely before returning to the orchestrator.

    Also in 3 projects that use this

  • badgidsSkill

    story-review

    Diagnose existing prose at a chosen editorial level, from whole-story and developmental problems through scene, line, copy, and proof passes, without rewriting until the diagnosis is accepted.

    Also in 3 projects that use this

  • +4 more from Abdullokh-N

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 7 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 40 edited versions we read keep these.

  • 7

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when creating a new project.

    line 8
  2. Very specific:

    All projects live in: ~/Developer/Projects/{project-name}/

    line 18
  3. Very specific:

    Use kebab-case for project names (e.g., site-editor-navigation, wp-cowork-plugin).

    line 20
  4. Distinctive:

    Always create this file. It's the canonical project overview document — the first thing someone reads to understand the project.

    line 111
  5. Distinctive:

    Ask the user if they want any of these, or infer from context.

    line 223
  6. Distinctive:

    Use portkeeper to avoid conflicts:

    line 231
  7. Distinctive:

    Always expose dev servers on the local network so they're accessible from phones/tablets.

    line 238
  8. Distinctive:

    Add the project to any project registry the user has configured

    line 318
  9. Distinctive:

    Add to memory if significant

    line 319

“Common” is measured: kept by at least 6 in 10 of the 40 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

Project Setup Skill

Use this skill when creating a new project. It establishes a consistent structure across all projects.

When to Use

  • Starting a new project
  • User asks to "set up a project" or "create a new project"
  • Bootstrapping a workspace for a new initiative

Project Location

All projects live in: ~/Developer/Projects/{project-name}/

Use kebab-case for project names (e.g., site-editor-navigation, wp-cowork-plugin).

Standard Structure

{project-name}/
├── .git/                 # Initialized git repo
├── .gitignore            # Standard ignores (see below)
├── README.md             # Project overview, quick start
├── CLAUDE.md             # Guidance for Claude Code / AI agents
├── docs/                 # Documentation
│   ├── overview.md       # Project overview (always create this)
│   └── (other docs)
└── logs/                 # Session logs, dev notes (git-ignored)
    └── (daily logs)

File Templates

README.md

# {Project Name}

{One-line description}

## Overview

{Brief explanation of what this project does and why it exists}

## Quick Start

```bash
cd ~/Developer/Projects/{project-name}
# Add setup commands here

Documentation

DocDescription
docs/Project documentation

Structure

{project-name}/
├── docs/          # Documentation
├── logs/          # Development logs (git-ignored)
└── README.md      # This file

Related

  • {Links to related issues, PRs, projects}

### CLAUDE.md

```markdown
# CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

## Project Overview

{One-line description of what this project is and its goal}

## Development

```bash
# Add common commands here

Architecture

{Brief description of tech stack, key patterns, important files}

Documentation

The /docs/ folder contains:

  • {List key docs}

Scope

  • In scope: {What this project covers}
  • Out of scope: {What it doesn't cover}

### docs/overview.md

Always create this file. It's the canonical project overview document — the first thing someone reads to understand the project.

```markdown
# {Project Name} — Overview

## What Is This?

{2-3 paragraphs explaining what the project does, why it exists, and how it works}

## Architecture

{How the project is structured — tech stack, key patterns, data flow}

## Links

- **Repo:** {URL}
- **P2/Discussion:** {URL if applicable}
- **Related:** {Other relevant links}

## Key People

- **{Name}** — {Role/context}

## What's Next

{Current focus, open questions, next steps}

Required sections: What Is This, Links. Other sections should be included when the information is available. Always capture links — they go stale fast and are hard to recover later.

.gitignore

# Logs - development session logs, not for version control
logs/

# Dependencies
node_modules/
vendor/
.venv/
__pycache__/

# Build outputs
dist/
build/
*.egg-info/

# Environment
.env
.env.local
.env*.local

# IDE / Editor
.idea/
.vscode/
*.swp
*.swo
*~

# OS
.DS_Store
Thumbs.db

# Package manager locks (uncomment if not needed)
# package-lock.json
# pnpm-lock.yaml
# composer.lock

Setup Procedure

  1. Create project directory
    mkdir -p ~/Developer/Projects/{project-name}
    cd ~/Developer/Projects/{project-name}
  2. Create folder structure
    mkdir -p docs logs
  3. Create .gitignore (use template above)
  4. Create README.md (use template above, fill in project details)
  5. Create CLAUDE.md (use template above, fill in project details)
  6. Create docs/overview.md (use template above — always include What Is This and Links sections at minimum)
  7. Initialize git
    git init
    git add -A
    git commit -m "Initial project setup"
  8. Report to user
    • Confirm project location
    • List created files
    • Suggest next steps (e.g., "Ready for docs, or should I scaffold something specific?")

Optional Additions

Depending on project type, may also create:

  • package.json — For Node.js projects
  • requirements.txt — For Python projects
  • composer.json — For PHP projects
  • Makefile — For projects with build steps
  • docker-compose.yml — For containerized projects

Ask the user if they want any of these, or infer from context.

Dev Server Projects

For projects with a dev server (Vite, webpack, Next.js, etc.):

1. Reserve a Port

Use portkeeper to avoid conflicts:

portman reserve {PORT} --name "{project-name}" --desc "{description}" --tags {tags}

2. Configure Network Access

Always expose dev servers on the local network so they're accessible from phones/tablets.

Vite (vite.config.js):

export default defineConfig({
  server: {
    port: {PORT},
    host: true,  // Expose on local network
  },
})

Next.js (package.json):

"scripts": {
  "dev": "next dev -p {PORT} -H 0.0.0.0"
}

Webpack (webpack.config.js):

devServer: {
  port: {PORT},
  host: '0.0.0.0',
}

Generic Node/Express:

app.listen(PORT, '0.0.0.0', () => { ... })

3. Document Access

In README.md, include:

## Development

Dev server: http://localhost:{PORT}
Network: http://{machine-ip}:{PORT} (for mobile testing)

The network IP can be found with ipconfig getifaddr en0 (macOS).

Logs Convention

The logs/ folder is for development session notes:

  • Format: MM-DD-YYYY-HHMM.md (e.g., 02-06-2026-1015.md)
  • Git-ignored so they don't clutter history
  • Useful for tracking decisions, debugging sessions, progress
  • Create an initial log entry during project setup

Sample Log (logs/MM-DD-YYYY-HHMM.md)

# {MM-DD-YYYY} {HH:MM}

## Session Focus

{What was worked on this session — one line}

## Notes

- {Key decisions, observations, or context}
- {Things tried, what worked, what didn't}

## Changes

- {Files created/modified}
- {Features added or bugs fixed}

## Next

- {What to pick up next time}
- {Open questions or blockers}

After Setup

Once project is created:

  1. Add the project to any project registry the user has configured
  2. Add to memory if significant
  3. Proceed with project-specific work

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.