startproject

Coordinate multi-agent project kickoff across Gemini, Codex, and Claude.

17|5|Updated Jan 31, 2026
One-click install
npx skills add https://github.com/gaebalai/claude-code-orchestrator --skill startproject-gaebalai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: startproject
Source: https://github.com/gaebalai/claude-code-orchestrator/tree/main/.claude/skills/startproject
Command: npx skills add https://github.com/gaebalai/claude-code-orchestrator --skill startproject-gaebalai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Orchestrates cross-agent collaboration to start a project and ensure quality via multi-session reviews across Gemini, Codex, and Claude.

Core Features & Use Cases

  • Phase-based multi-agent project kickoff from research to review
  • Automatic CLAUDE.md updates to persist context across sessions
  • Task creation workflow via TodoWrite to organize implementation work
  • Structured phase gates and reviewer roles for quality assurance

Quick Start

Initiate a new project using the startproject workflow and guide Gemini, Codex, and CLAUDE through all six phases from research to multi-session review.

Frequently Asked Questions about startproject

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I coordinate a multi-agent project kickoff across different AI coding assistants?

Multi-agent project kickoff is orchestrated by coordinating Gemini, Codex, and Claude through structured phases from research to review, ensuring cross-agent collaboration quality via multi-session reviews and phase gates.

What is the best way to persist project context across multiple AI coding sessions?

Persisting project context across sessions requires automatic CLAUDE.md updates that record phase progress and decisions, allowing different agents to resume work with full historical awareness.

Can I use this workflow to generate implementation tasks for new feature initiatives?

Yes, the workflow supports new feature initiatives and research-driven development by using TodoWrite to generate structured tasks and organize implementation work across configured phase gates.

How does a multi-agent workflow handle post-implementation reviews?

Post-implementation reviews in a multi-agent workflow are handled through structured phase gates and reviewer roles that enforce quality assurance across sessions before a project phase is marked complete.

Does multi-agent orchestration work without predefined dependencies?

Yes, this multi-agent orchestration operates independently without external dependencies, running entirely on the coordination logic between Gemini, Codex, and Claude to manage the project lifecycle.

Why use phase gates instead of a continuous workflow for cross-agent development?

Phase gates enforce quality assurance by requiring multi-session reviews at specific milestones, preventing error propagation across agents compared to a continuous workflow lacking structured validation checkpoints.