ratacat/claude-skills/project-setup

Claude Code and agent skill by ratacat/claude-skills

Trust tier 2
  • community
  • ext:[{"type":"hook","description":"Pre/post lifecycle hooks"}]
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Bootstrap new projects with strong typing, linting, formatting, and testing. Supports Python, TypeScript, and other languages with research fallback.

Install

npx vskill@latest install ratacat/claude-skills/project-setup

Semi-extensibleMentions customization, but needs skill-specific knowledge. Read the extensible skills standard

SKILL.md

Project Setup

Core Principles

  • Strong Typing: Strict mode enabled; types catch bugs at compile time
  • Strong Linting: Strict rules by default; easier to disable than add later
  • Auto Formatting: Automated and consistent; no manual formatting
  • Checks at Every Stage: Pre-commit hooks + CI; catch issues early
  • Co-located Tests: foo.ts → foo.test.ts; obvious what's tested
  • Behavior-Focused: Test what code does, not how; mock only external boundaries

Workflow

  1. Check reference/ for language guide (Python, TypeScript)
  2. If no guide: WebSearch "[language] project setup best practices"
  3. Follow setup: typing → linting → formatting → testing → pre-commit → CI
  4. For existing projects: migrate incrementally in same order

Reference Files

  • reference/python.md - uv, ruff, basedpyright, pytest
  • reference/typescript.md - pnpm, ESLint, Prettier, Vitest
  • reference/common-patterns.md - Testing philosophy, CI patterns, security

Tool Selection

Prefer tools that are: ecosystem standard, actively maintained, strict by default, fast, well-integrated (editor + CI + pre-commit).

Quality Checklist

  • [ ] Typing: Strictest mode, no any without justification
  • [ ] Linting: Strict rules, warnings as errors
  • [ ] Formatting: Auto-format on save + pre-commit
  • [ ] Testing: Co-located tests, coverage >80%
  • [ ] Pre-commit: Format, lint, type-check
  • [ ] CI: Same checks + coverage reporting
  • [ ] README: Setup instructions
  • [ ] All checks pass on initial commit

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
40
Repository forks
8
7-day trend score
19

Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 13 May 2026, 5 months ago.

Extension points

  • hookPre/post lifecycle hooks

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/ratacat/claude-skills/project-setup/badge)](https://verified-skill.com/skills/ratacat/claude-skills/project-setup)

Something wrong with this skill or its page? Tell us.