AgentStack
SKILL verified MIT Self-run

Onboard

skill-pvnarp-agent-skills-onboard · by pvnarp

Generates project onboarding guides by analyzing the codebase. Produces architecture overview, key file map, common workflows, and "where to look" reference. Use when someone new joins the project or when you need a codebase overview.

No reviews yet
0 installs
7 views
0.0% view→install

Install

$ agentstack add skill-pvnarp-agent-skills-onboard

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Onboard? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Project Onboarding

Analyze the codebase and produce a guide that answers: "I just cloned this repo. What do I need to know?"

Step 1: Project Overview

Determine from the codebase:

  • What is this? (product, library, service, CLI tool, etc.)
  • Who uses it? (end users, other developers, internal teams)
  • What language/framework? (detect from files, config, dependencies)
  • How is it structured? (monorepo, single app, microservices)

Step 2: Key File Map

Identify the most important files/directories:

ENTRY POINTS:
  [file] - [what starts here]

CONFIGURATION:
  [file] - [what it configures]

CORE LOGIC:
  [directory/file] - [what it does]

DATA LAYER:
  [directory/file] - [storage, schemas, migrations]

TESTS:
  [directory] - [test structure]

BUILD / DEPLOY:
  [file] - [how it builds/deploys]

Step 3: Architecture Snapshot

[Component A] → [Component B] → [Component C]
                      ↓
               [Data Store]
  • What are the major components?
  • How do they communicate?
  • Where does data flow?
  • What are the external dependencies?

Step 4: Common Workflows

"I want to add a new feature"

  1. Where to create files
  2. What patterns to follow (look at existing examples)
  3. How to test
  4. How to submit for review

"I want to fix a bug"

  1. How to reproduce (run locally, logs)
  2. Where to look (key modules, common sources of bugs)
  3. How to verify the fix

"I want to understand a feature"

  1. Start at [entry point]
  2. Follow the call chain through [key files]
  3. Data is stored in [data layer]

Step 5: Gotchas

Things that aren't obvious from reading the code:

  • Non-obvious environment requirements
  • Implicit dependencies between modules
  • Known quirks or workarounds
  • "Don't touch this because..." warnings
  • Patterns that look wrong but are intentional

Output Format

# [Project Name] - Onboarding Guide

## What Is This
[1-2 sentences]

## Quick Start
[Exact commands to clone, install, run, test]

## Architecture
[Diagram + brief explanation]

## Key Files
[Table of important files and what they do]

## Common Tasks
[Step-by-step for typical workflows]

## Gotchas
[Non-obvious things to know]

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.