codebase-onboarding · spencerpauly — Claude Code skill: map a repo into ONBOARDING.md
Fires five explore subagents in parallel to cover architecture, data models, APIs, auth and deployment, then merges their findings into one onboarding doc.
npx skills add spencerpauly/awesome-cursor-skills --skill codebase-onboarding -a claude-codeWhat codebase-onboarding does
The skill spawns 5 explore subagents at once. Each takes one area: directory layout and framework, database schemas and ORM, API routes, authentication, deployment config. The subagents are read-only, so nothing in your repo changes.
Results get merged into a single document with Quick Start, Architecture, Data Models, API Reference, Authentication, Deployment and a list of key files. It lands in ONBOARDING.md at the project root unless you name another path. Quick Start holds the install, migration and dev-server commands the agents found in the repo.
On a monorepo the skill suggests one extra agent per app or package. The output is meant to be opinionated: it points at the files to start with and calls out gotchas like easy-to-forget env vars and required system dependencies. If a project has no schemas or migrations, that section comes back empty, which is worth checking before you trust the rest.
What it helps with
- get oriented in an unfamiliar repo before the first edit
- build a map of endpoints and their auth requirements
- list every database schema and how entities relate
- figure out how the project builds and deploys
- write onboarding notes for a new teammate
Example prompts for the agent
- run codebase-onboarding on this repo and save the result to ONBOARDING.md
- generate an onboarding doc for the monorepo, one agent per package
- map the auth flow and API of this project into ONBOARDING.md
How to install codebase-onboarding
1Skills CLI (Vercel)
npx skills add spencerpauly/awesome-cursor-skills --skill codebase-onboarding -a claude-code2Manually: put the files in place
~/.claude/skills/codebase-onboarding/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/codebase-onboarding/
1Skills CLI (Vercel)
npx skills add spencerpauly/awesome-cursor-skills --skill codebase-onboarding -a codex2Manually: put the files in place
.agents/skills/codebase-onboarding/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add spencerpauly/awesome-cursor-skills --skill codebase-onboarding -a cursor2Manually: put the files in place
.cursor/skills/codebase-onboarding/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install spencerpauly/awesome-cursor-skills codebase-onboarding2Manually: put the files in place
.github/skills/codebase-onboarding/SKILL.md1Skills CLI (Vercel)
npx skills add spencerpauly/awesome-cursor-skills --skill codebase-onboarding -a gemini-cli2Platform CLI
gemini skills install https://github.com/spencerpauly/awesome-cursor-skills --path resources/codebase-onboardingManually: put the files in place
.devin/skills/codebase-onboarding/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add spencerpauly/awesome-cursor-skills --skill codebase-onboarding -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about codebase-onboarding
How do I install codebase-onboarding in Claude?
Run npx skills add spencerpauly/awesome-cursor-skills --skill codebase-onboarding -a claude-code. The skill ends up at ~/.claude/skills/codebase-onboarding/SKILL.md.
What does codebase-onboarding do?
It launches 5 explore subagents in parallel — architecture, data models, APIs, auth, deployment — and synthesizes their findings into one onboarding document.
Where does the document go?
By default to ONBOARDING.md in the project root. You can specify a different path in your request.
Source text
SKILL.md · CC0-1.0
--- name: codebase-onboarding description: Launch multiple explore subagents in parallel to investigate architecture, data models, auth, APIs, and deployment. Synthesize into an onboarding document. user-invocable: true --- # Codebase Onboarding Generate a comprehensive onboarding document for a codebase by exploring it in parallel. ## Workflow ### 1. Launch Parallel Explorers Spawn 5 `explore` subagents, each investigating a different area: **Agent 1 — Architecture & Structure** > "Map the top-level directory structure. Identify the framework (Next.js, Express, Django, etc.), monorepo tools (turbo, nx), and key config files. List every app/package and what it does." **Agent 2 — Data Models & Database** > "Find all database schemas, ORM models, migrations, and seed files. List every entity, its fields, and relationships. Identify the database (Postgres, MySQL, MongoDB, etc.) and ORM (Prisma, Drizzle, SQLAlchemy, etc.)." **Agent 3 — API Routes & Endpoints** > "Find all API route definitions. List every endpoint with its HTTP method, path, auth requirements, and what it does. Identify the API style (REST, GraphQL, tRPC)." **Agent 4 — Authentication & Authorization** > "Find how auth works. Identify the auth provider (Auth.js, Clerk, Supabase Auth, custom), session management, protected routes, role/permission checks, and middleware." **Agent 5 — Deployment & Infrastructure** > "Find deployment config (Dockerfile, Vercel config, fly.toml, terraform), CI/CD pipelines (GitHub Actions, etc.), environment variables needed, and how to run the app locally." ### 2. Synthesize Combine the results from all 5 agents into a single onboarding document: ```markdown # Codebase Onboarding ## Quick Start 1. Clone the repo 2. Install dependencies: `<command>` 3. Set up environment: copy `.env.example` to `.env` 4. Run database migrations: `<command>` 5. Start dev server: `<command>` ## Architecture <Agent 1 findings> ## Data Models <Agent 2 findings> ## API Reference <Agent 3 findings> ## Authentication <Agent 4 findings> ## Deployment <Agent 5 findings> ## Key Files to Know - `<file>` — <why it matters> ``` ### 3. Save Write the document to `ONBOARDING.md` in the project root, or wherever the user specifies. ## Tips - Each explore agent is read-only and fast — the whole process takes under a minute - For monorepos, consider one additional agent per app/package - The document should be opinionated — highlight the "start here" files, not just list everything - Include gotchas: common setup issues, env vars that are easy to forget, required system dependencies
© spencerpauly · CC0-1.0 · spencerpauly/awesome-cursor-skills
Similar skills
All skills for Agent setup: memory, context, orchestration →codebase-onboarding by other authors comes first.