maestro-spec-generate

Generate 7-phase specification packages from topics, files, or brainstorm sessions.

511|63|Updated Mar 17, 2026
One-click install
npx skills add https://github.com/catlog22/Maestro-Flow --skill maestro-spec-generate
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: maestro-spec-generate
Source: https://github.com/catlog22/Maestro-Flow/tree/main/.codex/skills/maestro-spec-generate
Command: npx skills add https://github.com/catlog22/Maestro-Flow --skill maestro-spec-generate

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Converts high-level ideas or brainstorm outputs into a complete, traceable specification package by orchestrating parallel research and a sequential document synthesis pipeline, removing manual coordination and fragmented research artifacts.

Core Features & Use Cases

  • Two-wave CSV pipeline: Wave 1 runs parallel domain, competitive, and tech-stack research agents; Wave 2 runs a sequential 7-phase document chain to produce product brief, PRD, architecture, data model, API spec, UI wireframes, and roadmap.
  • CSV source-of-truth and discovery board: Maintains tasks.csv as the master state, discoveries.ndjson as an append-only exploration log, and produces consolidated outputs like context.md and a spec package folder.
  • Operational controls: Supports auto-confirm (--yes), skip-research, brainstorm imports, codebase detection, readiness scoring, and graceful degradation when research fails.
  • Use Case: Quickly generate a production-ready spec package and roadmap from an idea, file reference, or brainstorm session for product planning and engineering handoff.

Quick Start

Run maestro-spec-generate with a topic or @file to produce a CSV-driven research pipeline and output a complete spec package.

Frequently Asked Questions about maestro-spec-generate

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

FAQPage Schema
How do I generate a complete product specification package from an idea or brainstorm session?

Generate a product specification package from an idea or file using a two-wave CSV pipeline that runs parallel research agents and a sequential synthesis chain to output PRDs, architecture, data models, APIs, and roadmaps.

What is a multi-agent CSV workflow for spec generation and how does it work?

A multi-agent CSV workflow for spec generation uses a two-wave pipeline where Wave 1 runs parallel domain, competitive, and tech-stack research agents, and Wave 2 runs a sequential 7-phase document chain to synthesize a complete spec package.

Can I skip the research phase and go straight to generating PRDs and architecture documents?

Yes, you can use skip-research mode to bypass the parallel research phase and proceed directly to the sequential 7-phase document synthesis chain to generate PRDs, architecture, API specs, and roadmaps.

Does the spec generation pipeline support importing existing brainstorm files and codebase detection?

The spec generation pipeline supports brainstorm imports, automatic codebase detection, and file references, allowing you to convert existing high-level ideas or brainstorm outputs directly into traceable specification packages.

How do I check product readiness and track research discoveries during specification generation?

Check product readiness and track discoveries through built-in readiness scoring and an append-only discoveries.ndjson exploration log, while maintaining tasks.csv as the master state for the entire CSV-driven research pipeline.

What happens if parallel research agents fail during the specification generation process?

If parallel research agents fail during specification generation, the pipeline features graceful degradation to ensure the sequential synthesis agent can still produce a consolidated context.md and spec package folder without blocking the workflow.