project-scaffolder
Guide for setting up Claude Code infrastructure in new or existing projects
Best use case
project-scaffolder is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Guide for setting up Claude Code infrastructure in new or existing projects
Teams using project-scaffolder should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/project-scaffolder/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How project-scaffolder Compares
| Feature / Agent | project-scaffolder | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Guide for setting up Claude Code infrastructure in new or existing projects
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Project Scaffolder
## Overview
This skill guides the process of setting up Claude Code infrastructure in a project. It handles stack detection, template selection, and file generation. Use this when setting up Claude Code for a new project or adding it to an existing codebase.
## Quick Reference
| Stack | Detection Files | Primary Use |
|-------|-----------------|-------------|
| TypeScript | `tsconfig.json`, `*.ts`, `*.tsx` | React/Node fullstack |
| Python | `pyproject.toml`, `requirements.txt` | FastAPI/Django backend |
| Rust | `Cargo.toml`, `*.rs` | Axum/Actix backend |
## Stack Detection
### TypeScript Detection
Look for:
```
tsconfig.json
package.json (with "typescript" in dependencies/devDependencies)
*.ts or *.tsx files in src/
```
Indicators of specific frameworks:
- `next.config.js` → Next.js
- `vite.config.ts` → Vite
- `express` in package.json → Express backend
- `prisma/` directory → Prisma ORM
### Python Detection
Look for:
```
pyproject.toml
requirements.txt
setup.py
*.py files
```
Indicators of specific frameworks:
- `fastapi` in dependencies → FastAPI
- `django` in dependencies → Django
- `flask` in dependencies → Flask
- `alembic/` directory → Alembic migrations
### Rust Detection
Look for:
```
Cargo.toml
Cargo.lock
src/main.rs or src/lib.rs
```
Indicators of specific frameworks:
- `axum` in Cargo.toml → Axum
- `actix-web` in Cargo.toml → Actix-web
- `diesel` in Cargo.toml → Diesel ORM
- `sqlx` in Cargo.toml → SQLx
## Skill Selection Matrix
Based on detected stack, select appropriate skills:
### Universal Skills (All Stacks)
| Skill | Purpose |
|-------|---------|
| `git-workflow` | Git conventions, branching |
| `dev-docs-workflow` | Context management |
| `code-review-workflow` | Review checklists |
| `skill-developer` | Creating new skills |
### Domain Skills (Cross-Cutting)
| Skill | Purpose | When to Include |
|-------|---------|-----------------|
| `api-validation` | Request validation | Any API project |
| `auth-guidelines` | Security patterns | Auth features |
| `error-handling` | Error patterns | All projects |
| `error-tracking` | Sentry integration | Production apps |
### TypeScript-Specific Skills
| Skill | Purpose |
|-------|---------|
| `backend-dev-guidelines` | Express/Node patterns |
| `frontend-dev-guidelines` | React/MUI patterns |
| `database-guidelines` | Prisma patterns |
| `testing-guidelines` | Jest/Vitest patterns |
| `state-management` | TanStack/Zustand |
### Python-Specific Skills
| Skill | Purpose |
|-------|---------|
| `python-backend-guidelines` | FastAPI/Django patterns |
| `python-database-guidelines` | SQLAlchemy patterns |
| `python-testing-guidelines` | pytest patterns |
### Rust-Specific Skills
| Skill | Purpose |
|-------|---------|
| `rust-backend-guidelines` | Axum/Actix patterns |
| `rust-database-guidelines` | Diesel/SQLx patterns |
| `rust-testing-guidelines` | cargo test patterns |
| `rust-error-handling` | Result/Option patterns |
| `rust-ownership` | Borrow checker patterns |
## CLAUDE.md Generation
### Template Variables
| Variable | Source | Example |
|----------|--------|---------|
| `{{PROJECT_NAME}}` | Directory name | "my-app" |
| `{{FRAMEWORK_VERSION}}` | Constant | "1.0.0" |
| `{{STACK_NAME}}` | Manifest displayName | "TypeScript/React/Node" |
| `{{STACK_VERSION}}` | Manifest version | "1.0.0" |
| `{{TIMESTAMP}}` | Current date | "2025-12-07" |
### Required Sections
Every CLAUDE.md should include:
1. **Quick Commands** - Build, test, lint, format
2. **Project Structure** - Directory layout
3. **Tech Stack** - Technologies used
4. **Dev Docs Workflow** - How to use /dev-docs
5. **Available Skills** - Listed by category
6. **Available Agents** - With usage examples
7. **Coding Conventions** - Project-specific rules
## Directory Structure
After initialization:
```
project/
├── CLAUDE.md # Generated from template
├── .claude/
│ ├── settings.json # Hook configurations
│ ├── hooks/ # Automation hooks
│ ├── skills/ # Skill files
│ ├── commands/ # Slash commands
│ ├── agents/ # Specialized agents
│ ├── templates/ # Scaffolding templates
│ └── cache/ # Session cache
└── dev/
└── active/ # Dev docs workspace
```
## Customization Points
After scaffolding, users should customize:
### In CLAUDE.md
- Project structure section
- Coding conventions
- Quick commands (if different from defaults)
### In skill-rules.json
- Add project-specific keywords
- Adjust enforcement levels
- Add custom file triggers
### Create Custom Skills
For project-specific patterns not covered by standard skills.
## Workflow
### New Project
1. Create project directory
2. Initialize stack (npm init, cargo init, etc.)
3. Run `/init-claude-code`
4. Customize CLAUDE.md
5. Start developing with skills
### Existing Project
1. Navigate to project root
2. Run `/init-claude-code`
3. Review detected stack (confirm or override)
4. Review generated CLAUDE.md
5. Merge with existing documentation if needed
## Troubleshooting
### Multiple Stacks Detected
If project has multiple config files:
- Ask user which is primary
- Consider monorepo setup
- May need custom configuration
### No Stack Detected
If no config files found:
- Ask user to specify stack
- Or create minimal config first
### Missing Skills
Some skills may not exist yet:
- Note which are missing
- Continue with available skills
- Create missing skills as needed
## Resources
| Topic | Link |
|-------|------|
| Stack Detection | [mdc:resources/detection-patterns.md] |
| Skill Matrix | [mdc:resources/skill-matrix.md] |
| Template Guide | [mdc:resources/template-guide.md] |Related Skills
project-qtax
UK taxation expert for HMRC compliance, Making Tax Digital (MTD ITSA/VAT) and Self-Assessment: explain tax treatment; compute income tax/NI/dividend/CGT with band-by-band breakdown; advise on deadlines/forms/penalties; and support MTD developer integration + tax software UX/flows. Use WebSearch (gov.uk/HMRC) to verify current rates and mandation timelines. (project)
project-overview
Background knowledge about CaCrFeedFormula project architecture, features, and context. Automatically loaded for AI reference, not directly user-invocable.
project-orchestration
Orchestrate multi-agent workflows for feature development using planning agents, context handoff, and stage management
project-object
Session memory that compounds - remember decisions, patterns, and corrections across AI coding sessions. Includes standards injection for consistent code quality.
project-mngt
Product Owner / Project Manager skill for MVP/MMP/MMR implementation planning
project-logger
SQLite-based project documentation logger for tracking API references, components, and project progress. Use this skill when documenting code changes, adding API documentation, recording component updates, or tracking project milestones. Automatically invoked when user mentions documentation, changelog, API docs, component docs, or project updates.
project-init
Automatically detects new project initialization, collaborates with user on project planning, and sets up the appropriate tech stack with matching skills and agents. Use when starting a new project, creating a new repository, or working in an empty/minimal directory that needs project structure.
project-index
Use this skill for large project maintenance with layered CLAUDE.md index system. Triggers when users need to (1) analyze and document existing codebases, (2) generate hierarchical CLAUDE.md files for modules, (3) set up incremental update hooks after code changes, or (4) navigate large projects efficiently. Supports legacy project onboarding and automatic context management.
project-guidelines-example
Example project-specific skill template based on a real production application.
project-development
This skill should be used when the user asks to "start an LLM project", "design batch pipeline", "evaluate task-model fit", "structure agent project", or mentions pipeline architecture, agent-assisted development, cost estimation, or choosing between LLM and traditional approaches.
project-context-discovery
Discover project structure, package managers, test frameworks, and automation without hardcoded assumptions
project-claude-initializer
為新專案初始化 Claude Code 配置,建立標準化的 .claude 目錄、CLAUDE.md 和 gitignore。當使用者說「初始化 Claude 配置」、「設定專案 Claude」時使用。