Onboarding
Generates a comprehensive developer onboarding guide (ONBOARDING.md) by reading the codebase: directory map, entry points, environment variables, key commands, and architecture overview.From its SKILL.md
npx -y skills add RealDougEubanks/ClaudeMarketplace --skill onboardingAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
5.4 KB, ~1.3k tokens by cl100k_base, as published. Nobody here has run it
Onboarding
Generate a comprehensive developer onboarding guide for an unfamiliar codebase and write it to docs/ONBOARDING.md.
Instructions
-
Use Read on
README.md, then attempt to read whichever of the following exist:package.json,pyproject.toml,go.mod,CLAUDE.md,docs/assumptions.md. -
Use Glob to map the top-level directory structure (
*). For each top-level folder found, describe its purpose based on its name and contents (e.g.,src/→ application source,scripts/→ automation scripts,docs/→ project documentation). -
Use Glob to find entry points matching:
index.*,main.*,server.*,app.*,cmd/**/*. Read the primary entry point to understand how the application starts. -
Use Read on any Makefile,
package.json(scripts section), orTaskfile.ymlto identify key commands: install, run, test, build, lint. -
Use Glob to find
.env.exampleor any env var documentation files. List all required environment variables with their descriptions.SECURITY: Read
.env.exampleonly — never read.envor any file containing real credential values, and never include actual secret values in the generated guide. Document variable names and descriptions only. -
Use Bash to count files by detected language type. Adapt the command to the language detected:
- TypeScript/JavaScript:
find . -name "*.ts" -o -name "*.js" | grep -v node_modules | wc -l - Python:
find . -name "*.py" | grep -v __pycache__ | wc -l - Go:
find . -name "*.go" | wc -l
- TypeScript/JavaScript:
-
Generate architecture diagram.
a. Use Read on the primary entry point file identified in step 3 to understand how the application initializes and what it connects to.
b. Use Glob to find configuration files that reveal infrastructure:
docker-compose.yml,*.env.example,infrastructure/**,terraform/**,serverless.yml,.github/workflows/**.c. Use Grep to identify major inter-module dependencies: import/require/use statements at the top of the entry point and primary route/handler files.
d. Generate a Mermaid diagram using the most appropriate type:
- For web apps with a request flow:
sequenceDiagramshowing Client → Load Balancer → App Server → Database/Cache/Queue - For microservices or modular apps:
graph LRshowing service dependencies - For simple single-module apps:
graph TDshowing function/module call flow
e. Include the diagram in the generated
docs/ONBOARDING.mdunder a "## Architecture" section, wrapped in a fenced code block withmermaidsyntax tag.f. Add a note: "This diagram was auto-generated and may not capture all relationships. Review and update as the architecture evolves."
Example output to include in ONBOARDING.md:
## Architecture ```mermaid sequenceDiagram Client->>+ALB: HTTPS Request ALB->>+AppServer: Forward AppServer->>+PostgreSQL: Query PostgreSQL-->>-AppServer: Result AppServer->>+Redis: Cache write AppServer-->>-ALB: Response ALB-->>-Client: HTTPS Response ``` > This diagram was auto-generated and may not capture all relationships. Review and update as the architecture evolves. - For web apps with a request flow:
-
Use Glob to check for
docs/agentRoster.md. If it exists, read it and include the agent roster section in the guide. -
Write the completed onboarding guide to
docs/ONBOARDING.mdusing Write, following the output structure below.
Output Structure
Write the following document to docs/ONBOARDING.md:
# Developer Onboarding Guide — <Project Name>
## What This Project Does
<1-2 sentence summary from README>
## Tech Stack
| Layer | Technology |
|-------|-----------|
| Language | ... |
| Framework | ... |
| Database | ... |
| CI/CD | ... |
## Directory Map
| Path | Purpose |
|------|---------|
| `src/` | ... |
## Getting Started
```bash
# 1. Install dependencies
npm install
# 2. Configure environment
cp .env.example .env
# Edit .env: fill in ...
# 3. Run locally
npm run dev
Key Entry Points
src/index.ts:1— Application bootstrapsrc/routes/— API route definitions
Environment Variables
| Variable | Required | Description |
|---|---|---|
| DATABASE_URL | Yes | PostgreSQL connection string |
Key Commands
| Command | What it does |
|---|---|
npm run dev | Start dev server with hot reload |
npm test | Run test suite |
Architecture Overview
<brief description of the main data/request flow>
Agent Roster
<include only if docs/agentRoster.md exists>
How to Contribute
<derive from the target project's own conventions — see note below>
For the "How to Contribute" section: read the target project's `CONTRIBUTING.md`, `CLAUDE.md`, or `.github/PULL_REQUEST_TEMPLATE.md` and summarize *that project's* branching, review, and merge rules. Do not assume any particular branch-prefix or approval policy. If no convention docs exist, fall back to generic guidance: "Create a branch, open a PR, and request review — confirm the team's specific conventions with a maintainer."
After writing the file, confirm to the user that `docs/ONBOARDING.md` has been created and summarize the key sections included.
What ships with it: 4 files
3.5 KB alongside SKILL.md
.claude-plugin/
- plugin.json513 B
- metadata.json646 B
- README.md2.3 KB
- .scan-exempt71 B
Gives 0 of the 12 instructions most codebase onboarding skills give in ~1.3k tokens
Counted across 307 of the 325 authors here whose files we hold, read 2026-09-06
- Focus first session on one successful outcomein 34 of 307, across 15 files
- Show progress and celebrate completionsin 32 of 307, across 13 files
- Prefer interactive doing over tutorialsin 32 of 307, across 13 files
- Remove every step between signup and core valuein 32 of 307, across 13 files
- Keep checklists to 3-7 items ordered by valuein 32 of 307, across 13 files
- Read product marketing context before asking questionsin 28 of 307, across 13 files
- Focus fixes on the biggest funnel drop-offsin 22 of 307, across 7 files
- Define activation as the action most correlated with retentionin 20 of 307, across 6 files
- Give one clear next action at every stepin 19 of 307, across 8 files
- Understand product context and current state before recommendingin 15 of 307, across 3 files
- Limit guided tours to five dismissable stepsin 15 of 307, across 6 files
- Trace one request from entry to responsein 14 of 307, across 8 files
Said here and by no other author read
- Map top-level directories with Glob
- Extract key commands from build files
- List environment variables from example files
- Count files per language with Bash
- Trace module dependencies with Grep
- Generate a Mermaid architecture diagram
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.