How do I install the Codebase Onboarding skill?

Run npx skillmds@latest add droodotfoo/codebase-onboarding in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Codebase Onboarding safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Codebase Onboarding?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Codebase Onboarding free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Codebase Onboarding?

DROOdotFOO (@droodotfoo) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Codebase Onboarding by droodotfoo — Agent Skill

Name: Codebase Onboarding
Author: DROOdotFOO

Codebase Onboarding

Auto-generate onboarding documentation from codebase analysis, tailored to the reader's experience level. TRIGGER when: user asks to onboard someone to a codebase, document this codebase, generate project documentation for new team members, write a codebase walkthrough or tour, create a getting-started guide, or explain a codebase to a specific audience. DO NOT TRIGGER when: user wants API reference docs (use language-specific tooling), or wants to understand a single file (just read it).

DROOdotFOO fd41cbf 3 files · 4.8 KB Updated Sep 17, 2026

File contents

codebase-onboarding

Auto-generate onboarding documentation from codebase analysis. Audience-aware output for junior developers, senior engineers, and contractors.

What You Get

Architecture overview derived from actual code structure
Key entry points and control flow
Testing strategy and deployment process
Domain glossary extracted from code and comments
Audience-tailored depth and focus

Workflow

Analyze -- Scan the codebase to discover stack, structure, and patterns
Capture signals -- Identify entry points, config files, CI/CD, test patterns, dependency graph, domain terms
Fill template -- Populate the output format sections
Tailor -- Adjust depth and emphasis for the target audience

Analysis signals

Signal	Where to look
Language/framework	package.json, mix.exs, go.mod, Cargo.toml, pyproject.toml
Entry points	main files, router definitions, CLI entry points
Config	.env.example, config/, settings files
CI/CD	.github/workflows/, Makefile, Dockerfile
Tests	test/, spec/, tests/, *_test.go
Database	migrations/, schema files, ORM models
API surface	OpenAPI specs, GraphQL schema, route definitions
Domain terms	README, doc comments, module names, type names
Dependencies	Lock files, vendor/, package manifests
Dev setup	Makefile, docker-compose.yml, devcontainer.json

Rules

Derive everything from the actual codebase -- do not fabricate
Flag gaps explicitly ("No CI/CD configuration found")
Keep the glossary to terms a newcomer would not know
Link to actual files using relative paths
If the audience is not specified, ask before generating

Reference

File	Topic
audience-profiles.md	Junior/Senior/Contractor focus areas
output-template.md	Markdown template for the onboarding doc

---name: codebase-onboardingdescription: Auto-generate onboarding documentation from codebase analysis, tailored to the reader's experience level. TRIGGER when: user asks to onboard someone to a codebase, document this codebase, generate project documentation for new team members, write a codebase walkthrough or tour, create a getting-started guide, or explain a codebase to a specific audience. DO NOT TRIGGER when: user wants API reference docs (use language-specific tooling), or wants to understand a single file (just read it).---# codebase-onboardingAuto-generate onboarding documentation from codebase analysis. Audience-awareoutput for junior developers, senior engineers, and contractors.## What You Get- Architecture overview derived from actual code structure- Key entry points and control flow- Testing strategy and deployment process- Domain glossary extracted from code and comments- Audience-tailored depth and focus## Workflow1. **Analyze** -- Scan the codebase to discover stack, structure, and patterns2. **Capture signals** -- Identify entry points, config files, CI/CD, test patterns, dependency graph, domain terms3. **Fill template** -- Populate the output format sections4. **Tailor** -- Adjust depth and emphasis for the target audience## Analysis signals| Signal | Where to look || ------------------ | -------------------------------------------------- || Language/framework | package.json, mix.exs, go.mod, Cargo.toml, pyproject.toml || Entry points | main files, router definitions, CLI entry points || Config | .env.example, config/, settings files || CI/CD | .github/workflows/, Makefile, Dockerfile || Tests | test/, spec/, __tests__/, *_test.go || Database | migrations/, schema files, ORM models || API surface | OpenAPI specs, GraphQL schema, route definitions || Domain terms | README, doc comments, module names, type names || Dependencies | Lock files, vendor/, package manifests || Dev setup | Makefile, docker-compose.yml, devcontainer.json |## Rules1. Derive everything from the actual codebase -- do not fabricate2. Flag gaps explicitly ("No CI/CD configuration found")3. Keep the glossary to terms a newcomer would not know4. Link to actual files using relative paths5. If the audience is not specified, ask before generating## Reference| File | Topic ||------|-------|| [audience-profiles.md](audience-profiles.md) | Junior/Senior/Contractor focus areas || [output-template.md](output-template.md) | Markdown template for the onboarding doc |

Frequently asked questions