메뉴
Launch multiple explore subagents in parallel to investigate architecture, data models, auth, APIs, and deployment. Synthesize into an onboarding document.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Generate or edit images using the OpenAI Image API (gpt-image-2). Use when the user asks to generate, create, draw, render, illustrate, mock up, or edit an image, icon, logo, mockup, illustration, OG image, blog hero, marketing asset, or similar visual. Also use when the user supplies a reference image and asks to modify, restyle, or remix it. Triggers on: "generate an image", "create an image", "make a picture of", "edit this image", "restyle this", "make a mockup of", "draw a", "render a", "illustration of".
When the same multi-step workflow repeats in Cursor (user corrections or agent redos), capture it as a new SKILL.md under .cursor/skills/ so future sessions load it automatically.
After navigating and interacting in Cursor's built-in browser, use browser_network_requests to audit every fetch/XHR for failures, slowness, duplicate calls, and suspicious payloads. Use for API-heavy pages and after backend or client networking changes.
When GitHub Actions fails, fetch failing job logs and assign each failing job to a separate subagent that fixes its slice of the problem in parallel. Use for multi-job CI failures where jobs are independent.
Run four parallel read-only subagents that each review the same diff from a different lens — security, performance, correctness, and readability — then merge findings into one report. Use before merging large or risky PRs.
Execute a user flow step-by-step in Cursor's built-in browser while documenting each action, then emit a Playwright test that replays the same flow using stable selectors derived from the accessibility tree.
| 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 |
Generate a comprehensive onboarding document for a codebase by exploring it in parallel.
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."
Combine the results from all 5 agents into a single onboarding document:
# 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>
Write the document to ONBOARDING.md in the project root, or wherever the user specifies.