Skip to content
Skills Library
Programming · Writing

codebase-onboarding

/codebase-onboarding

Map an unfamiliar repository into an onboarding guide (stack, architecture, entry points, conventions, commands) and a starter or refreshed agent instructions file (AGENTS.md or CLAUDE.md). Use when joining a project, asked to explain a codebase, or to create or refresh that file.

Licence
MIT
Last repository change
05.11.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 05.11.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Map an unfamiliar repository into an onboarding guide (stack, architecture, entry points, conventions, commands) and a starter or refreshed agent instructions file (AGENTS.md or CLAUDE.md). Use when joining a project, asked to explain a codebase, or to create or refresh that file.

Original author description

Map an unfamiliar repository into an onboarding guide (stack, architecture, entry points, conventions, commands) and a starter or refreshed agent instructions file (AGENTS.md or CLAUDE.md). Use when joining a project, asked to explain a codebase, or to create or refresh that file.

How it works

  1. 1. Recon
  2. 2. Architecture
  3. 3. Conventions
  4. 4. Output
  5. Rules
Original SKILL.md headings · 47 lines, 358 words
SKILL.md preview
---
name: codebase-onboarding
description: "Map an unfamiliar repository into an onboarding guide (stack, architecture, entry points, conventions, commands) and a starter or refreshed agent instructions file (AGENTS.md or CLAUDE.md). Use when joining a project, asked to explain a codebase, or to create or refresh that file."
---

# codebase-onboarding

## 1. Recon

Use Glob and Grep in parallel; read files only to settle ambiguous signals.

- Manifests: `package.json`, `pyproject.toml`, `go.mod`, `Cargo.toml`, `pom.xml`, `build.gradle`, `Gemfile`, `composer.json`, `mix.exs`, `pubspec.yaml`
- Framework markers: `next.config.*`, `nuxt.config.*`, `vite.config.*`, `angular.json`, Django settings, Flask app factory, FastAPI main, Rails config
- Entry points: `main.*`, `index.*`, `app.*`, `server.*`, `cmd/`, `src/main/`
- Tree: top two levels, skipping `node_modules`, `vendor`, `.git`, `dist`, `build`, `.next`, `__pycache__`
- Tooling: `eslint.config.*`, `.eslintrc*`, `.prettierrc*`, `tsconfig.json`, `Makefile`, `Dockerfile`, `docker-compose*`, `.github/workflows/`, `.env.example`
- Tests: `tests/`, `test/`, `__tests__/`, `*.test.*`, `*.spec.*`, `*_test.go`, Jest, Vitest, or pytest config

## 2. Architecture

- Stack: languages and versions, frameworks, key libraries, databases and ORMs, build tools, CI/CD.
- Shape: monolith, monorepo, microservices, or serverless; frontend/backend split; API style (REST, GraphQL, gRPC, tRPC).
- Purpose of each top-level directory.
- One request traced end to end: entry (router, handler), validation, business logic, data access.

## 3. Conventions

- Naming of files, components or classes, and tests.
- Error handling style, dependency injection vs direct imports, state management, async style.
- Git: branch names, commit style, merge strategy, from recent history. With no or shallow history, write "Git history unavailable or too shallow".

## 4. Output

Onboarding guide, readable in two minutes:
Overview (2-3 sentences); Tech stack (layer, technology, version); Architecture; Key entry points; Directory map; Request lifecycle; Conventions; Common tasks (dev, test, lint, migrate, build commands); Where to look (task to path).

Agent instructions file (`AGENTS.md`, or `CLAUDE.md` for Claude Code), under 100 lines:
Tech stack; Code style; Testing (command, file pattern, coverage command if configured); Build and run (dev, build, lint); Project structure; Conventions (commits, PRs, error handling).

If that file exists, read it first, keep its project-specific instructions, extend it, and mark what changed.

- "Onboard me": full guide in the chat, plus the instructions file in the repo root.
- "Create or update AGENTS.md or CLAUDE.md": steps 1-3, then that file only.

## Rules

- When config and code disagree, trust the code.
- State unknowns ("could not determine test runner") instead of guessing.
- List only dependencies that shape how code is written.
- Do not explain obvious directories or repeat the README.

Versions

RepositoryScoreLicence
This page · ssvinar/senior-agent-skills100MIT
ericrisco/rsc-harness100MIT
FrancoStino/opencode-skills-collection100MIT
neuromechanist/research-skills100BSD-3-Clause
alirezarezvani/claude-skills100MIT
sickn33/agentic-awesome-skills100MIT
kannnnna9/ultracode100MIT
reddygopalkrishna/developer-agent-skills100MIT
SHRIJANAGAIN/Nemo-Cli100Apache-2.0

Database snapshot: 13.11.2026 · package version d1d2c9ebee44 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 86codebase-understanding
    Map an unfamiliar repository into source-linked components, symbols, dependencies and an onboarding tour, or update an existing architecture map after changes. Use for understanding code structure; runtime validation and implementation belong to their own workflows.
  • 100onboard-codebase
    Map an unfamiliar repository from the files actually read (what it is, entry points, how to run and test it, conventions, risks) and propose lines for the project memory. Use it when starting in a project new to you, when asked to explain or map a codebase, or while its memory is empty.
  • 90explain-codebase
    Onboard to an unfamiliar codebase by mapping its architecture, entry points, and data flow. Use when starting work in a new or unknown repository and you need a navigable mental model fast.
  • 90repo-onboarding
    Use when starting in an unfamiliar repository, new codebase, greenfield checkout, or 'where do I start' moment and you need a fast structured map of stack, entrypoints, patterns, risks, and next steps before any edits. Triggers: onboard me to this repo, map the codebase, explore unfamiliar project.
  • 90understand-onboard
    Use when you need to generate an onboarding guide for new team members joining a project
  • 100create-agents-md
    Use when the user asks to create AGENTS.md, generate agent instructions for a repository, set up CLAUDE.md, or wants to document project conventions for coding agents. Also use when user says "create agents md", "setup agent docs", or "initialize repo for agents".

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.