TheSimpleApp

ultimate-onboard

0
0
# Install this skill:
npx skills add TheSimpleApp/agent-skills --skill "ultimate-onboard"

Install specific skill from multi-skill repository

# Description

Drop into ANY project and fully analyze, clean up, document, and configure for parallel agentic work. The nuclear option for project onboarding. Spawns parallel agents for maximum speed.

# SKILL.md


name: ultimate-onboard
description: Drop into ANY project and fully analyze, clean up, document, and configure for parallel agentic work. The nuclear option for project onboarding. Spawns parallel agents for maximum speed.
license: MIT
metadata:
author: thesimpleapp
version: "1.0"


Ultimate Project Onboarding

The nuclear option. Drop into ANY project and make it production-ready for agentic development.

What This Does

ANY PROJECT (messy, undocumented, unfamiliar)
                    ↓
           β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
           β”‚  ULTIMATE ONBOARD β”‚
           β”‚                   β”‚
           β”‚  5 Parallel Agentsβ”‚
           β”‚  Full Analysis    β”‚
           β”‚  Auto Cleanup     β”‚
           β”‚  Complete Docs    β”‚
           β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
                    ↓
PRODUCTION-READY (clean, documented, configured)

Phases

Phase 1: Parallel Analysis (5 Agents)

Spawn 5 agents simultaneously to map the entire codebase:

Agent 1: STRUCTURE
β”œβ”€β”€ Map folder structure
β”œβ”€β”€ Identify entry points
β”œβ”€β”€ Trace build pipeline
└── Output: STRUCTURE.md

Agent 2: PATTERNS
β”œβ”€β”€ Identify coding patterns
β”œβ”€β”€ Find inconsistencies
β”œβ”€β”€ Detect frameworks/libraries
└── Output: PATTERNS.md

Agent 3: DATA
β”œβ”€β”€ Map database schema
β”œβ”€β”€ Trace data flow
β”œβ”€β”€ Identify API contracts
└── Output: DATA_FLOW.md

Agent 4: DEPENDENCIES
β”œβ”€β”€ Audit package.json/pubspec
β”œβ”€β”€ Find outdated packages
β”œβ”€β”€ Security vulnerabilities
└── Output: DEPENDENCIES.md

Agent 5: TECH_DEBT
β”œβ”€β”€ Find code smells
β”œβ”€β”€ Identify dead code
β”œβ”€β”€ Measure complexity
└── Output: TECH_DEBT.md

Phase 2: Synthesis

Combine all 5 reports into unified understanding:

# Architecture Overview

## Tech Stack
- Frontend: [detected]
- Backend: [detected]
- Database: [detected]
- Infrastructure: [detected]

## Key Patterns
- State management: [pattern]
- API layer: [pattern]
- Component structure: [pattern]

## Critical Files
- Entry: [files]
- Config: [files]
- Core logic: [files]

## Health Score
- Code quality: X/10
- Documentation: X/10
- Test coverage: X/10
- Dependency health: X/10

Phase 3: Parallel Cleanup (Conditional)

If user approves, spawn cleanup agents:

Agent A: FORMATTING
β”œβ”€β”€ Apply consistent formatting
β”œβ”€β”€ Fix linting errors
β”œβ”€β”€ Standardize imports
└── Non-breaking changes only

Agent B: DEAD_CODE
β”œβ”€β”€ Remove unused imports
β”œβ”€β”€ Delete commented code
β”œβ”€β”€ Remove unreachable code
└── Safe deletions only

Agent C: NAMING
β”œβ”€β”€ Fix inconsistent naming
β”œβ”€β”€ Rename unclear variables
β”œβ”€β”€ Add missing type annotations
└── Semantic improvements

Agent D: STRUCTURE
β”œβ”€β”€ Move misplaced files
β”œβ”€β”€ Create missing folders
β”œβ”€β”€ Update imports
└── Organize by feature

Phase 4: Documentation Generation

Auto-generate all project docs:

CLAUDE.md
β”œβ”€β”€ Project summary
β”œβ”€β”€ Key patterns
β”œβ”€β”€ File locations
β”œβ”€β”€ Commands

.claude/
β”œβ”€β”€ rules/
β”‚   β”œβ”€β”€ business-logic.md
β”‚   β”œβ”€β”€ coding-standards.md
β”‚   └── architecture.md
└── standards/
    β”œβ”€β”€ components.md
    β”œβ”€β”€ testing.md
    └── api.md

docs/
β”œβ”€β”€ ARCHITECTURE.md
β”œβ”€β”€ API.md
β”œβ”€β”€ CONTRIBUTING.md
└── SETUP.md

Phase 5: Configure for Power Mode

Set up for parallel agentic development:

.claude/
β”œβ”€β”€ settings.json          # Model preferences
└── rules/
    β”œβ”€β”€ parallel-safe.md   # Which files can parallel edit
    β”œβ”€β”€ module-owners.md   # Agent assignments
    └── no-touch.md        # Critical files to protect

Execution Commands

Full Onboard (All Phases)

/ultimate-onboard

β†’ Runs all 5 phases
β†’ Creates all documentation
β†’ Configures for parallel work

Analysis Only

/ultimate-onboard --analyze-only

β†’ Phase 1 + 2 only
β†’ No changes to codebase
β†’ Outputs reports only

Quick Mode

/ultimate-onboard --quick

β†’ Single agent analysis
β†’ CLAUDE.md only
β†’ Fast for familiar codebases

Output Files

File Purpose
CLAUDE.md Primary project context
.claude/rules/*.md Coding rules and standards
docs/ARCHITECTURE.md System architecture
docs/TECH_DEBT.md Technical debt backlog
docs/API.md API documentation

Parallel Safety Rules

When spawning multiple agents:

SAFE to parallelize:
βœ“ Different feature folders
βœ“ Independent test files
βœ“ Separate documentation files
βœ“ Non-overlapping modules

NOT safe:
βœ— Shared utilities
βœ— Config files
βœ— Database migrations
βœ— Core type definitions

Detection Patterns

Framework Detection

React:     package.json has "react"
Next.js:   next.config.* exists
Vue:       package.json has "vue"
Flutter:   pubspec.yaml exists
Express:   package.json has "express"
Supabase:  supabase/ folder exists

Pattern Detection

State: Redux | Zustand | Riverpod | Context
API:   REST | GraphQL | tRPC
Style: Tailwind | CSS Modules | Styled
Test:  Jest | Vitest | pytest | flutter_test

Example Output: CLAUDE.md

# ProjectName

## Overview
E-commerce platform built with Next.js, Supabase, and Tailwind.

## Quick Commands
- `npm run dev` - Start development
- `npm run build` - Production build
- `npm test` - Run tests

## Architecture
- `/app` - Next.js app router pages
- `/components` - React components
- `/lib` - Utilities and helpers
- `/supabase` - Database migrations

## Key Patterns
- Server components by default
- Client components in `/components/client/`
- Supabase for auth and database
- Zustand for client state

## Database
- Supabase project: [ref]
- Key tables: users, products, orders
- RLS enabled on all tables

## Standards
See `.claude/rules/` for coding standards.

Integration

After onboarding, seamlessly use other skills:

/ultimate-onboard     β†’ Project fully understood
       ↓
/sprint-planning      β†’ Plan features with full context
       ↓
/parallel-swarm       β†’ Execute with multiple agents
       ↓
/code-review          β†’ Quality gate

Hardware Optimization

With 64 cores / 128GB RAM:

Phase 1: 5 parallel agents (analysis)
Phase 3: 4 parallel agents (cleanup)
Phase 4: 3 parallel agents (docs)

Total time: ~5 minutes for medium codebase
vs ~25 minutes sequential

Rollback

All changes are tracked:

# Undo cleanup changes
git checkout -- .

# Keep only documentation
git checkout -- src/
git add docs/ CLAUDE.md .claude/

# Supported AI Coding Agents

This skill is compatible with the SKILL.md standard and works with all major AI coding agents:

Learn more about the SKILL.md standard and how to use these skills with your preferred AI coding agent.