Templateclaw setup
32 production-ready templates as Claude Code skills. Type /templateclaw to scaffold any project. Landing pages, dashboards, UI components, project setup, dev methodology.
npx -y skills add jeromwolf/templateclaw --skill templateclaw-setupAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Generate project setup files — README.md, CLAUDE.md, AGENTS.md, .env template, Docker Compose. Best practices for modern development teams and AI-assisted coding.
SKILL.md
3.2 KB, as published. Nobody here has run it
TemplateClaw — Project Setup Generator
Generate production-quality project setup files following 2026 best practices.
When Invoked
- If argument provided (e.g.,
/templateclaw-setup readme), generate that file - If "all", generate all setup files for the current project
- If no argument, detect the project type from existing files and suggest what's missing
Available Setup Files
README.md
Structure:
# Project Name
> One-line description
[Badges: CI, coverage, license, version]
[Screenshot/GIF placeholder]
## What it does
[2-3 sentences]
## Quick Start
[One-liner install + run]
## Features
[Bulleted list]
## Architecture
[Brief diagram or description]
## Development
[Setup, test, lint commands]
## Contributing
[Link to CONTRIBUTING.md]
## License
[MIT/Apache/etc.]
Adapt to project: Detect language from package.json/pyproject.toml/Cargo.toml and use appropriate commands.
CLAUDE.md (AI Agent Instructions)
Structure:
# Project Guide for AI Agents
## Project Overview
[What this project does, tech stack]
## Architecture
[Directory structure, key modules, data flow]
## Development Rules
[Coding conventions, naming, patterns]
## Testing
[How to run tests, coverage expectations]
## Common Tasks
[Frequent operations with exact commands]
## Do's and Don'ts
[Explicit rules for the AI agent]
Key principle: CLAUDE.md is for AI agents working on the project. Include concrete commands, file paths, and rules — not prose.
AGENTS.md (Multi-Agent Documentation)
Structure:
# Agent Hierarchy
## Primary Agent
- Role, capabilities, tools
## Specialist Agents
- Per-domain agent definitions
## Coordination
- How agents communicate
- Task delegation rules
## Boundaries
- What each agent can/cannot modify
.env Template (.env.example)
- Group by service (DB, API, Auth, etc.)
- Include descriptions as comments
- Use placeholder values (never real secrets)
- Reference to secrets manager if applicable
# === Database ===
DATABASE_URL=postgresql://user:password@localhost:5432/mydb
DATABASE_POOL_SIZE=10 # Max concurrent connections
# === Authentication ===
JWT_SECRET=your-secret-here # Generate: openssl rand -hex 32
JWT_EXPIRY=24h
Docker Compose (docker-compose.yml)
- Multi-stage Dockerfile reference
- Service definitions (app, db, redis, etc.)
- Health checks
- Volume mounts for persistence
- Environment variable references from .env
- Network isolation
- Development overrides (docker-compose.override.yml)
Auto-Detection
When no argument is given, check for:
package.json→ Node.js project setuppyproject.toml/requirements.txt→ Python project setupCargo.toml→ Rust project setupgo.mod→ Go project setup- Existing files → suggest only what's missing
Output
Write files directly to the project root. If a file already exists, show a diff preview and ask before overwriting.