Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
athola avatar

Project Init

  • 94 installs
  • 325 repo stars
  • Updated August 2, 2026
  • athola/claude-night-market

Auto-detect Python, Rust, or TypeScript as the primary project language before the rest of claude-night-market init modules run.

About

project-init is a language-detection module from the claude-night-market skill set that decides whether your repo is primarily Python, Rust, or TypeScript/React before other init automation runs. It checks canonical manifest files first, falls back to counting extensions under src/, and only then prompts with a simple 1–3 menu. Edge cases include mixed-language trees and empty greenfield folders, where it either asks you to pick a primary language or assumes Python. Solo builders using Claude Night Market to standardize new repos benefit because agents get a single LANGUAGE variable instead of guessing from package.json noise. Wire it through project_detector.py as documented so subsequent scaffolding stays consistent across the monorepo-style skill bundle.

  • 3-signal detection: config files, src/ extension counts, then interactive menu
  • Recognizes pyproject.toml, Cargo.toml, and tsconfig.json-style stacks
  • Sets LANGUAGE to python, rust, or typescript for downstream night-market modules
  • Handles multi-language repos by asking for a primary language
  • Defaults to Python when no source files exist

Project Init by the numbers

  • 94 all-time installs (skills.sh)
  • Ranked #1,389 of 3,282 Productivity & Planning skills by installs in the Skillselion catalog
  • Security screen: LOW risk (skills.sh audit)
  • Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/athola/claude-night-market --skill project-init

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs94
repo stars325
Security audit3 / 3 scanners passed
Last updatedAugust 2, 2026
Repositoryathola/claude-night-market

What it does

Auto-detect Python, Rust, or TypeScript as the primary project language before the rest of claude-night-market init modules run.

Files

SKILL.mdMarkdownGitHub ↗

Table of Contents

Project Initialization Skill

Interactive workflow for initializing new software projects with complete development infrastructure.

Use When

  • Starting a new Python, Rust, or TypeScript project
  • Updating existing project tooling to current standards
  • Need to set up git, GitHub workflows, pre-commit hooks, Makefile
  • Want consistent project structure across team
  • Converting unstructured project to best practices
  • Adding missing configurations to established codebases

Workflow

1. Detect or Select Language

Load modules/language-detection.md

  • Auto-detect from existing files (pyproject.toml, Cargo.toml, package.json)
  • If ambiguous or empty directory, ask user to select
  • Validate language is supported (python, rust, typescript)

2. Collect Project Metadata

Load modules/metadata-collection.md

Gather:

  • Project name (default: directory name)
  • Author name and email
  • Project description
  • Language-specific settings:
  • Python: version (default 3.10)
  • Rust: edition (default 2021)
  • TypeScript: framework (React, Vue, etc.)
  • License type (MIT, Apache, GPL, etc.)

3. Review Existing Files

Check for existing configurations:

ls -la

Verification: Run the command with --help flag to verify availability.

If files exist (Makefile, .gitignore, etc.):

  • Show what would be overwritten
  • Ask for confirmation or selective overwrite
  • Offer merge mode (preserve custom content)

4. Render and Apply Templates

Load modules/template-rendering.md

Run initialization script:

python3 plugins/attune/scripts/attune_init.py \
  --lang {{LANGUAGE}} \
  --name {{PROJECT_NAME}} \
  --author {{AUTHOR}} \
  --email {{EMAIL}} \
  --python-version {{PYTHON_VERSION}} \
  --description {{DESCRIPTION}} \
  --path .

Verification: Run the command with --help flag to verify availability.

The script also scaffolds the project decision journal: docs/tradeoffs.md and docs/lessons-learned.md. These are append-only logs that later workflows (brainstorm, specify, plan, execute, review) write to as decisions and lessons arise. Existing journal files are never overwritten. The format follows the leyline:decision-journal contract; init uses leyline's template when present and a vendored copy otherwise, so it works with or without leyline installed.

Verification: Confirm docs/tradeoffs.md and docs/lessons-learned.md exist and each contains an ## Active index and an ## Archive section.

5. Initialize Git (if needed)

# Check if git is initialized
if [ ! -d .git ]; then
  git init
  echo "Git repository initialized"
fi

Verification: Run git status to confirm working tree state.

6. Verify Setup

Validate setup:

# Check Makefile targets
make help

# List created files
git status

Verification: Run git status to confirm working tree state.

7. Next Steps

Advise user to:

# Install dependencies and hooks
make dev-setup

# Run tests to verify setup
make test

# See all available commands
make help

Verification: Run pytest -v to verify tests pass.

Error Handling

  • Language detection fails: Ask user to specify --lang
  • Script not found: Guide to plugin installation location
  • Permission denied: Suggest chmod +x on scripts
  • Git conflicts: Offer to stash or commit existing work

Success Criteria

  • All template files created successfully
  • No overwrites without user confirmation
  • Git repository initialized
  • make help shows available targets
  • make test runs without errors (even if no tests yet)

Exit Criteria

  • [ ] Template files for the selected language are created (or, in dry-run,

reported) with no unconfirmed overwrites.

  • [ ] docs/tradeoffs.md and docs/lessons-learned.md exist, each with an

## Active index and an ## Archive section.

  • [ ] A pre-existing journal file is detected and left unmodified.
  • [ ] Git is initialized (unless --no-git) and make help lists targets.
  • [ ] Running with --dry-run writes no files, including the journal.

Examples

Example 1: New Python Project

**Verification:** Run `pytest -v` to verify tests pass.
User: /attune:project-init

Related skills

FAQ

Is Project Init safe to install?

skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.