project-onboarding

name	project-onboarding
description	Guided project onboarding for new codebases. Helps agents understand project structure, build systems, test commands, and development workflows by creating persistent knowledge memories.
version	1.1.0
model	sonnet
invoked_by	both
user_invocable	true
tools	["Read","Glob","Grep","Bash","Write"]
best_practices	["Perform onboarding before starting any substantial work on unfamiliar projects","Create structured memories for reuse across sessions","Focus on actionable information (build commands, test commands, key directories)","Validate discovered information by running commands when safe","Keep memories concise and well-organized"]
error_handling	graceful
streaming	supported
verified	true
lastVerifiedAt	"2026-02-22T00:00:00.000Z"
source	builtin
trust_score	100
provenance_sha	dc336a8cafc78166

Project Onboarding Specialist - Guided codebase exploration and knowledge capture for rapid project understanding. - Discovering project structure and organization patterns - Identifying build systems and package managers - Finding test commands and coverage configuration - Mapping key directories and entry points - Creating persistent memories for future sessions - Generating project overview documentation - Identifying development workflows and conventions

When to Use

Invoke this skill when:

• Starting work on an unfamiliar codebase
• After context is lost (new session)
• When check_onboarding_performed indicates no memories exist
• When user asks to "learn about this project" or "understand this codebase"

Onboarding Workflow

Step 1: Check Existing Knowledge

First, check if onboarding was already performed:

List files in: .claude/context/memory/
Look for: project-structure.md, build-commands.md, test-commands.md

If memories exist, read them and skip to Step 6 (Validation).

Step 2: Project Discovery

First, classify the project:

Greenfield vs Brownfield Detection

Indicator	Present?	Classification
.git directory with history	Yes	Brownfield
Package manifest (package.json, requirements.txt, etc.)	Yes	Brownfield
Source directories (src/, app/, lib/) with code	Yes	Brownfield
Dirty git status (uncommitted changes)	Yes	Brownfield (warn user)
Empty or only README.md	None of above	Greenfield

For Brownfield Projects:

1. Respect Ignore Files: Check .gitignore and .claudeignore BEFORE scanning
2. Efficient File Triage:
   • Use git ls-files to list tracked files (respects .gitignore)
   • For large files (>1MB): Read only head/tail (first and last 20 lines)
   • Skip binary files, node_modules, build artifacts

**User Request**: "I need to understand this codebase" **Related Skills**: - `project-analyzer` - Deep automated analysis (complements onboarding) - `repo-rag` - Semantic search for patterns - `session-handoff` - Prepare context for new sessions