Codebase Onboarding

Analyze a codebase and generate onboarding documentation for engineers, tech leads, and contractors. Fast fact-gathering and repeatable onboarding outputs. Use when onboarding a new engineer, writing architecture-overview docs for a new project, or producing tech-lead briefings for unfamiliar repos.

Published by @Alireza Rezvani·0 agent reads / 30d·0 saves·

Codebase Onboarding

Tier: POWERFUL
Category: Engineering
Domain: Documentation / Developer Experience


Overview

Analyze a codebase and generate onboarding documentation for engineers, tech leads, and contractors. This skill is optimized for fast fact-gathering and repeatable onboarding outputs.

Core Capabilities

  • Architecture and stack discovery from repository signals
  • Key file and config inventory for new contributors
  • Local setup and common-task guidance generation
  • Audience-aware documentation framing
  • Debugging and contribution checklist scaffolding

When to Use

  • Onboarding a new team member or contractor
  • Rebuilding stale project docs after large refactors
  • Preparing internal handoff documentation
  • Creating a standardized onboarding packet for services

Quick Start

# 1) Gather codebase facts
python3 scripts/codebase_analyzer.py /path/to/repo

# 2) Export machine-readable output
python3 scripts/codebase_analyzer.py /path/to/repo --json

# 3) Use the template to draft onboarding docs
# See references/onboarding-template.md

Recommended Workflow

  1. Run scripts/codebase_analyzer.py against the target repository.
  2. Capture key signals: file counts, detected languages, config files, top-level structure.
  3. Fill the onboarding template in references/onboarding-template.md.
  4. Tailor output depth by audience:
    • Junior: setup + guardrails
    • Senior: architecture + operational concerns
    • Contractor: scoped ownership + integration boundaries

Onboarding Document Template

Detailed template and section examples live in:

  • references/onboarding-template.md
  • references/output-format-templates.md

Common Pitfalls

  • Writing docs without validating setup commands on a clean environment
  • Mixing architecture deep-dives into contractor-oriented docs
  • Omitting troubleshooting and verification steps
  • Letting onboarding docs drift from current repo state

Best Practices

  1. Keep setup instructions executable and time-bounded.
  2. Document the "why" for key architectural decisions.
  3. Update docs in the same PR as behavior changes.
  4. Treat onboarding docs as living operational assets, not one-time deliverables.

Bundled with this artifact

4 files

Reference files that ship alongside this artifact. Agents pull these in only when the task needs them.

More on the bench

SKILL0

Context Mode

Activate output filtering, session logging, and auto-resume to keep Claude Code sessions productive across resets. Use when starting a long or complex coding session, when previous sessions lost context mid-task, or when you need Claude to resume exactly where it left off after a reset. Installs a session.log at project root, filters verbose command output to preserve context, and automatically resumes in-progress tasks after any Claude reset.

product-management+2
0
SKILL0

Handoff 2

Compact the current conversation into a handoff document for another agent to pick up. Save to a user-configured location (OS temp, home folder, or per-project .handoff/), redact secrets before write, suggest skills for the next session, and auto-load the latest handoff on the next SessionStart. First-run setup asks where to save so the project folder never gets cluttered. Use when the user says 'hand this off', 'handoff doc', 'summarize this for a new session', 'compact this conversation', 'I'm ending this session', 'pick this up later', or any variation signaling intent to pass work to a fresh agent. Also trigger on implicit signals: the user announcing they're switching machines, ending the day mid-task, or context is growing long without a natural stopping point.

software-engineering+2
0
SKILL0

Collab Proof

Use when you want to understand what Claude contributed vs what you drove in a session. Triggers on: /collab-proof, session retrospective, ai contribution analysis, collaboration evidence, what did claude do.

software-engineering+2
0