Skill

codebase-onboarding

Analyze an unfamiliar codebase and generate a structured onboarding guide with architecture map, key entry points, conventions, and a starter CLAUDE.md.

npx claudepluginhub nassimbf/ftitos-claude-code

Tool Access

This skill uses the workspace's default tool permissions.

Preview

Systematically analyze an unfamiliar codebase and produce a structured onboarding guide.

SKILL.md

Similar Skills

cache-components

139.3k

Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.

cache-components

mcp-builder

124.2k

Guides building MCP servers enabling LLMs to interact with external services via tools. Covers best practices, TypeScript/Node (MCP SDK), Python (FastMCP).

9 files

anthropics-skills-13

Stats

Stars2

Forks0

Last CommitApr 18, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

Codebase Onboarding

Systematically analyze an unfamiliar codebase and produce a structured onboarding guide.

When to Use

First time opening a project with Claude Code
Joining a new team or repository
User asks "help me understand this codebase"
User asks to generate a CLAUDE.md for a project

How It Works

Phase 1: Reconnaissance

Gather raw signals about the project without reading every file:

Package manifest detection -- package.json, go.mod, Cargo.toml, pyproject.toml, pom.xml, etc.
Framework fingerprinting -- next.config., nuxt.config., django settings, flask app factory, etc.
Entry point identification -- main., index., app., server., cmd/, src/main/
Directory structure snapshot -- Top 2 levels, ignoring node_modules, vendor, .git, dist
Config and tooling detection -- .eslintrc*, tsconfig.json, Makefile, Dockerfile, CI configs
Test structure detection -- tests/, tests/, *_test.go, *.spec.ts, pytest.ini

Phase 2: Architecture Mapping

From the reconnaissance data, identify:

Tech Stack: Language(s), framework(s), database(s), build tools, CI/CD
Architecture Pattern: Monolith, monorepo, microservices, or serverless
Key Directories: Map top-level directories to their purpose
Data Flow: Trace one request from entry to response

Phase 3: Convention Detection

Identify patterns the codebase already follows:

Naming Conventions: File naming, component naming, test file patterns
Code Patterns: Error handling style, dependency injection, async patterns
Git Conventions: Branch naming, commit message style, PR workflow

Phase 4: Generate Onboarding Artifacts

Output 1: Onboarding Guide

# Onboarding Guide: [Project Name]

## Overview
[2-3 sentences: what this project does and who it serves]

## Tech Stack
| Layer | Technology | Version |
|-------|-----------|---------|
| ...   | ...       | ...     |

## Architecture
[Diagram or description of how components connect]

## Key Entry Points
- **API routes**: path -- description
- **Database**: path -- data model source of truth

## Common Tasks
- **Run dev server**: `command`
- **Run tests**: `command`
- **Run linter**: `command`

Output 2: Starter CLAUDE.md

Generate or update a project-specific CLAUDE.md based on detected conventions. If CLAUDE.md already exists, enhance it -- preserve existing instructions.

Best Practices

Don't read everything -- use Glob and Grep, not Read on every file
Verify, don't guess -- trust the code over config if they conflict
Respect existing CLAUDE.md -- enhance rather than replace
Stay concise -- scannable in 2 minutes
Flag unknowns -- "Could not determine test runner" is better than a wrong answer

Anti-Patterns

CLAUDE.md longer than 100 lines
Listing every dependency -- highlight only the ones that shape how you write code
Describing obvious directory names
Copying the README -- the onboarding guide adds structural insight the README lacks