Codebase Onboarding logo

Codebase Onboarding

Community
andreaswasita
codebase-onboarding

Maps an unfamiliar repo before touching its code.

Overview

Publisherandreaswasita
Repositorycopilot-agents-dojo
Skill namecodebase-onboarding
Stars
54
Forks
15
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by andreaswasita on GitHub. Read the source before you install it.

Installation

Install the Codebase Onboarding AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/andreaswasita/copilot-agents-dojo/tree/main/skills/codebase-onboarding
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/andreaswasita/copilot-agents-dojo.git /tmp/copilot-agents-dojo
mkdir -p .claude/skills
cp -r /tmp/copilot-agents-dojo/skills/codebase-onboarding .claude/skills/codebase-onboarding
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Codebase Onboarding in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Codebase Onboarding on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Codebase Onboarding is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Codebase Onboarding Skill

Builds a working mental model of an unfamiliar repository before making changes: language, framework, structure, conventions, entry points, and test pattern. Does NOT exhaustively read every file — surveys strategically, then drills in where the work demands it.

When to Use

  • Working in a new or unfamiliar repository.
  • Before making changes to code you have not read.
  • When a project lacks documentation.
  • User asks you to "look at this repo" or "understand this project".
  • Briefing a sub-agent on context before delegating.
  • NOT when you already have a recent mental model of this repo — re-onboarding wastes turns.

Prerequisites

  • Read access to the repository.
  • The view, grep, and glob Copilot tools.
  • The powershell tool to inspect files outside the source tree (lockfiles, etc.).
  • Ability to run the project's test command (later, optional).

How to Run

text
1. Survey the top-level layout with `glob`.
2. Read manifest files (package.json, pyproject.toml, go.mod, *.csproj, pom.xml).
3. Read the README.
4. Identify the architecture pattern from directory names.
5. Open the entry point and one representative test.
6. Note conventions: naming, imports, error handling, test layout.
7. Write a short Quick Map (5–10 lines) for your future self.

Quick Reference

Survey targetToolWhy
Top-level layoutglob '*'Frames the project
Source layoutglob 'src/**' (or repo equivalent)Spots architecture pattern
Manifestsview package.json / view pyproject.tomlLanguage, framework, scripts
READMEview README.mdAuthor's intent
Entry pointview src/main.* / view cmd/main.goHow startup actually works
Testsview one representative testPattern + framework
Directory signalArchitecture clue
src/controllers/ or src/routes/MVC / route-based
src/features/ or src/modules/Feature / domain-driven
packages/ or apps/Monorepo
src/components/Component-based frontend
cmd/ and internal/Go standard layout
src/main/java/Java / Spring
Dockerfile + docker-compose.ymlContainerized service set

Procedure

Step 1: Survey the Landscape

Use glob on *, then on src/** (or the equivalent). Note top-level files. Use view on the manifest file for the stack — package.json, pyproject.toml, go.mod, *.csproj, pom.xml.

Step 2: Read the README

Open README.md with view. The author usually states the project's purpose, run instructions, and conventions in the first hundred lines.

Step 3: Identify Architecture

Match the directory layout to the table above. Note any divergence — those are the "interesting" parts.

Step 4: Read the Entry Point

Open the entry file with view: src/main.ts, src/app.py, cmd/main.go, Program.cs. Trace the startup path one level deep. You are mapping shape, not deeply auditing logic.

Step 5: Sample One Test

Use glob to locate tests (**/*.test.*, **/test_*.py, **/*_test.go). Open one with view. Note framework, fixture style, and where tests live relative to source.

Step 6: Capture the Quick Map

Write a 5–10 line summary for your own use (and to brief sub-agents):

markdown
## Quick Map: <repo-name>
- Language: TypeScript (strict mode)
- Framework: Next.js 14 (App Router)
- Tests: Vitest, co-located `*.test.ts`
- Patterns: Server Components default, Server Actions for mutations
- Entry: `src/app/layout.tsx`
- API: `src/app/api/`
- Models: `src/lib/models/`
- Build: `npm run build`. Deploy: Vercel.

Pitfalls

  • DO NOT start editing before completing the survey. You will pick the wrong directory.
  • DO NOT ask the user what stack it is when the manifest answers the question.
  • DO NOT read the repo linearly file by file. Survey strategically.
  • DO NOT impose your preferred conventions. Match the existing style even if you would do it differently.
  • DO NOT skip reading at least one existing test — tests are executable docs.

Verification

  • Quick Map written (language, framework, tests, entry, build).
  • At least one existing test file was opened with view.
  • Architecture pattern is named (MVC / monorepo / etc.).
  • Run command is identified and recorded.
  • Naming/convention rules are noted before any new file is created.

Frequently asked questions

What does the Codebase Onboarding AI skill do?

Maps an unfamiliar repo before touching its code.

Why use Codebase Onboarding on TypingMind?

Because you install it once and use it with any model. Codebase Onboarding is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Codebase Onboarding in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/andreaswasita/copilot-agents-dojo/tree/main/skills/codebase-onboarding. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Codebase Onboarding?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Codebase Onboarding?

As many as you like. As long as a model supports skills, you can use Codebase Onboarding with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Codebase Onboarding AI skill free?

Yes. It is published on GitHub by andreaswasita under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇