Codebase Onboarding
Auto-generate onboarding docs from codebase analysis.
$skillfish add ~skills/codebase-onboarding What This Skill Can Do
Concrete capabilities you get when you install this skill.
Generate architecture overviews and domain maps for unfamiliar codebases
Identify and explain non-obvious design patterns and architectural decisions
Extract implicit ADRs (Architecture Decision Records) from code signals
Produce onboarding docs covering setup, conventions, and first-week tickets
Map data flow across services, queues, and external integrations
Flag undocumented areas and high-risk code regions for new team members
Real Conversations
See how the Codebase Onboarding skill responds to actual requests. These are representative examples of what your AI agent will produce.
We hired a senior backend engineer starting Monday. Our codebase is a Django 4.2 + React 18 monorepo with no onboarding docs. What should auto-generated docs cover?
Here's what the codebase analysis generates, structured for a backend-focused engineer:
Generated: Codebase Onboarding Guide
Architecture Overview
monorepo/
├── backend/ # Django 4.2 — REST API (DRF)
│ ├── apps/ # Domain modules: users, billing, core
│ ├── config/ # settings/, urls.py, wsgi.py
│ └── requirements/ # base.txt, dev.txt, prod.txt
├── frontend/ # React 18 + Vite
└── infra/ # Terraform + Docker Compose
Local Setup (detected from Makefile + docker-compose.yml)
git clone git@github.com:org/repo.git && cd repo
cp backend/.env.example backend/.env
docker compose up -d db redis
cd backend
pip install -r requirements/dev.txt
python manage.py migrate
python manage.py runserver # → http://localhost:8000
Key Patterns to Know
- Service layer: business logic in
apps/*/services.py, not in views - Permissions: custom DRF permission classes in
core/permissions.py - Tests: pytest-django, factories in
tests/factories.py, run withmake test - Migrations: never edit existing migration files; always
makemigrations
Suggested First Week Tickets
- Fix a bug in
apps/billing/— gets you into the payment flow - Add a field to an existing DRF serializer — touches models, migrations, tests
Who to Ask
- Django architecture → @lead-backend
- CI/deploy pipeline → @devops-lead
This is generated from static analysis of your repo structure, Makefile, docker-compose.yml, and README. Point me at your repo root to generate the real version with actual command names and module paths.
Get Started
How to install and use this skill in your preferred environment.
Skills are designed for AI coding agents (Claude Code, Cursor, Windsurf) and IDE-based workflows where the agent can read files, run scripts, and act on your codebase. Web-based AI can use the knowledge and frameworks, but won't have tool access.
Models & Context
Which AI models and context windows work best with this skill.
Recommended Models
Larger models produce more detailed, production-ready outputs.
Context Window
This skill's SKILL.md is typically 3–10 KB — fits in any modern context window.
All current frontier models (Claude, GPT, Gemini) support 100K+ context. Use the full window for complex multi-service work.
Pro tips for best results
Be specific
Include numbers — users, budget, RPS — so the skill can size the architecture.
Share constraints
Compliance needs, team size, and existing stack all improve the output.
Iterate
Start with a high-level design, then ask follow-ups for IaC, cost analysis, or security review.
Combine skills
Pair with companion skills below for end-to-end coverage.
Ready to try Codebase Onboarding?
Install the skill and start getting expert-level guidance in your workflow — any agent, any IDE.
$skillfish add ~skills/codebase-onboarding