auto-setup
Auto-setup detects a new project's type and language by checking for configuration files like package.json, pyproject.toml, or Cargo.toml, then automatically configures quality gates for linting, type checking, testing, and formatting specific to that stack. Use this when starting work on an unfamiliar codebase or onboarding to a new project to establish consistent tooling without manual configuration.
git clone --depth 1 https://github.com/rohitg00/pro-workflow /tmp/auto-setup && cp -r /tmp/auto-setup/skills/auto-setup ~/.claude/skills/auto-setupSKILL.md
# Auto Setup
Detect project type and configure pro-workflow quality gates automatically.
## Trigger
Use when:
- Starting work on a new project
- Onboarding to an unfamiliar codebase
- Setting up CI integration
## Detection
### Step 1: Identify Project Type
```bash
ls package.json pyproject.toml Cargo.toml go.mod Gemfile pom.xml build.gradle 2>/dev/null
```
### Step 2: Configure Quality Gates
**Node.js/TypeScript:**
```json
{
"lint": "npm run lint",
"typecheck": "npx tsc --noEmit",
"test": "npm test -- --changed --passWithNoTests",
"format": "npx prettier --check ."
}
```
**Python:**
```json
{
"lint": "ruff check .",
"typecheck": "mypy .",
"test": "pytest --tb=short -q",
"format": "ruff format --check ."
}
```
**Rust:**
```json
{
"lint": "cargo clippy -- -D warnings",
"typecheck": "cargo check",
"test": "cargo test --quiet",
"format": "cargo fmt --check"
}
```
**Go:**
```json
{
"lint": "golangci-lint run",
"typecheck": "go vet ./...",
"test": "go test ./... -count=1",
"format": "gofmt -l ."
}
```
### Step 3: Verify Tools Are Installed
Run each command with `--version` or `--help` to confirm availability. Report missing tools.
### Step 4: Create Configuration
Generate a `.claude/settings.json` with:
- Quality gate commands for the detected project type
- Suggested permission rules (user reviews and approves)
- Hook configuration for the project
## Output
```text
AUTO SETUP
Project type: [Node.js/Python/Rust/Go/Mixed]
Package manager: [npm/pnpm/yarn/pip/cargo]
Quality gates configured:
lint: [command] ✓
typecheck: [command] ✓
test: [command] ✓
format: [command] ✓
Missing tools:
- [tool] — install with: [command]
Settings written to: .claude/settings.json
```
## Rules
- Never overwrite existing settings without asking
- Detect, don't assume — check for tool presence
- Support monorepos (check for workspaces config)
- Report missing tools with install commandsAnalyzes and optimizes context window usage across sessions. Use when context feels bloated, sessions run slow, or approaching compaction limits.
Analyze session token usage and cost patterns. Identify expensive operations and recommend optimizations. Use to understand and reduce session costs.
Specialized debugging agent. Use when facing hard bugs, test failures, or runtime errors that need systematic investigation.
Multi-phase development agent. Research > Plan > Implement with validation gates. Use PROACTIVELY when building features that touch >5 files or require architecture decisions.
Analyze permission denial patterns and generate optimized alwaysAllow/alwaysDeny rules. Use when permission prompts slow down workflow.
Break down complex tasks into implementation plans before writing code. Use when task touches >5 files, requires architecture decisions, or has unclear requirements.
Code review specialist that verifies every finding against actual code before reporting. Use before committing, for PR reviews, or after major changes.
Confidence-gated exploration that assesses readiness before implementation. Scores 0-100 across five dimensions and gives GO/HOLD verdict.