agentleFS
Sign inStart free
dcs-sonidcs-soni/skills/codebase-onboarding/SKILL.md

codebase-onboarding

Skill1 starsChanged 10 months agoMITView on GitHub

Help developers understand unfamiliar codebases quickly. Use when

We split this skill into the rules it gives an agent

11 rules. 0 are common, 7 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 47 edited versions we read keep these.

  • 7

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When a user asks to understand a codebase:

    line 14
  2. Distinctive:

    Run the structure analyzer to understand the project layout:

    line 30
  3. Distinctive:

    Read and analyze the core components:

    line 60
  4. Very specific:

    Use Glob and Read tools to explore these directories.

    line 68
  5. Distinctive:

    Create a comprehensive onboarding document:

    line 99
  6. Very specific:

    Run analyze_structure.py → Detects Node.js/Express

    line 156
  7. Very specific:

    Run find_entry_points.py → Finds src/index.js, route files

    line 157
  8. Very specific:

    Read package.json, tsconfig.json for dependencies

    line 158
  9. Distinctive:

    Create ONBOARDING.md with quick reference

    line 161
  10. Distinctive:

    Document ORM patterns and migrations

    line 173
  11. Distinctive:

    Start high-level: - Don't dive into implementation details initially

    line 178

“Common” is measured: kept by at least 6 in 10 of the 47 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Codebase Onboarding Skill

A comprehensive skill to help new developers understand large codebases quickly by generating architecture overviews, identifying entry points, tracing data flows, and creating navigable codebase maps.

Quick Start

When a user asks to understand a codebase:

Onboarding Progress:
- [ ] Step 1: Analyze project structure
- [ ] Step 2: Identify entry points
- [ ] Step 3: Map key components
- [ ] Step 4: Trace data flows
- [ ] Step 5: Document patterns
- [ ] Step 6: Generate onboarding guide

Workflow

Step 1: Analyze Project Structure

Run the structure analyzer to understand the project layout:

python .claude/skills/codebase-onboarding/scripts/analyze_structure.py .

This will output:

  • Project type (Node.js, Python, Go, etc.)
  • Directory structure with descriptions
  • Key configuration files found
  • Detected frameworks and libraries

Step 2: Identify Entry Points

Find where the application starts and its main interfaces:

python .claude/skills/codebase-onboarding/scripts/find_entry_points.py .

Entry points include:

  • Main application files (index.js, main.py, main.go)
  • API route handlers
  • CLI entry points
  • Event handlers and listeners

Step 3: Map Key Components

Read and analyze the core components:

  1. Models/Types - Data structures used throughout
  2. Services - Business logic implementations
  3. Controllers/Handlers - Request handling
  4. Utilities - Shared helper functions
  5. Configuration - App settings and constants

Use Glob and Read tools to explore these directories.

Step 4: Trace Data Flows

For each major feature, trace how data moves:

python .claude/skills/codebase-onboarding/scripts/trace_data_flow.py . --feature "user authentication"

Document:

  • Input sources (API, CLI, events)
  • Processing steps
  • Data transformations
  • Output destinations (DB, API, files)

Step 5: Document Patterns

Identify recurring patterns in the codebase. See PATTERNS.md for common patterns to look for.

Key patterns to identify:

  • Architectural patterns (MVC, Clean Architecture, etc.)
  • Error handling approaches
  • Logging conventions
  • Testing strategies
  • Naming conventions

Step 6: Generate Onboarding Guide

Create a comprehensive onboarding document:

python .claude/skills/codebase-onboarding/scripts/generate_map.py . --output ONBOARDING.md

The guide should include:

  • Architecture diagram (Mermaid)
  • Component overview
  • Data flow diagrams
  • "Where to find X" quick reference
  • Common tasks guide

Output Format

Generate documentation in this structure:

# [Project Name] - Developer Onboarding Guide

## Architecture Overview

[Mermaid diagram showing major components]

## Project Structure

[Directory tree with descriptions]

## Key Components

[Table of important files and their purposes]

## Data Flows

[Diagrams showing how data moves through the system]

## Common Tasks

- How to add a new API endpoint
- How to add a new feature
- How to run tests
- How to deploy

## Patterns & Conventions

[Coding standards used in this project]

Examples

Example 1: Node.js Express API

User: "Help me understand this codebase"

Steps:

  1. Run analyze_structure.py → Detects Node.js/Express
  2. Run find_entry_points.py → Finds src/index.js, route files
  3. Read package.json, tsconfig.json for dependencies
  4. Map: routes/ → controllers/ → services/ → models/
  5. Generate architecture diagram
  6. Create ONBOARDING.md with quick reference

Example 2: Python Django Project

User: "I'm new to this project, give me an overview"

Steps:

  1. Detect Django from manage.py, settings.py
  2. Find apps in INSTALLED_APPS
  3. Map: urls.py → views.py → models.py
  4. Trace request flow through middleware
  5. Document ORM patterns and migrations
  6. Generate Django-specific onboarding guide

Tips for Success

  1. Start high-level - Don't dive into implementation details initially
  2. Follow imports - Trace import chains to understand dependencies
  3. Read tests - Tests often reveal intended behavior
  4. Check docs/ - Existing documentation is valuable context
  5. Look for README - Project README often explains structure

Related Skills

  • For API documentation: see API docs skill
  • For dependency analysis: see dependency audit skill
  • For code quality: see code review skill

Download now (ZIP)

  • Other versions51 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 51

    1. loulanyue/awesome-claude-notes★ 272same name
    2. Fmarzochi/EGC★ 61same name
    3. kumaran-is/claude-code-onboarding★ 35same name
    4. Hassaan146/claude-skills★ 18same name
    5. kaizakin/dotfiles★ 16same name
    6. woxiangyangzhimao/skills★ 14same name
    7. gongyijie85/dsh-ecc★ 8same name
    8. hukusuke1007/agent-skills★ 8same name
    9. mxrsv/agents-skills★ 8same name
    10. zero-click/zero-ratchet★ 8same name

    41 more not listed

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • Used alongsideProjects with it also use pytorch-patterns, continuous-agent-loop and 10 more.

    Other files people use alongside this one.

    Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
    • Yog-SothoSkill

      pytorch-patterns

      PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading. Always activate when the user is writing PyTorch models or training scripts, reviewing deep learning code, debugging training loops or data pipelines, optimizing GPU memory or training speed, setting up reproducible experiments, implementing transfer learning or fine-tuning, or asks anything about nn.Module, DataLoader, autograd, AMP, or torch.compile.

      Also in 6 projects that use this

    • junimnjwSkill

      continuous-agent-loop

      Patterns for continuous autonomous agent loops with quality gates, evals, and recovery controls.

      Also in 7 projects that use this

    • loulanyueSkill

      nuxt4-patterns

      Nuxt 4 app patterns for hydration safety, performance, route rules, lazy loading, and SSR-safe data fetching with useFetch and useAsyncData.

      Also in 4 projects that use this

    • royaluniondesign-sysSkill

      content-hash-cache-pattern

      Cache expensive file processing results using SHA-256 content hashes — path-independent, auto-invalidating, with service layer separation.

      Also in 5 projects that use this

    • loulanyueSkill

      safety-guard

      Also in 5 projects that use this

    • junimnjwSkill

      carrier-relationship-management

      Codified expertise for managing carrier portfolios, negotiating freight rates, tracking carrier performance, allocating freight, and maintaining strategic carrier relationships. Informed by transportation managers with 15+ years experience. Includes scorecarding frameworks, RFP processes, market intelligence, and compliance vetting. Use when managing carriers, negotiating rates, evaluating carrier performance, or building freight strategies.

      Also in 4 projects that use this

    • +3 more from junimnjw
  • In this repository7 other files it gives its agents.

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free