Agent skill

maestro:brainstorming

Use before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Stars 26
Forks 4

Install this agent skill to your Project

npx add-skill https://github.com/ReinaMacCredy/maestro/tree/main/.codex/skills/maestro:brainstorming

SKILL.md

Brainstorming Ideas Into Designs

Overview

Help turn ideas into fully formed designs and specs through natural collaborative dialogue.

Start by understanding the current project context, then run the structured interview in reference/interview-guide.md to refine the idea. Once you understand what you're building, present the design in small sections (200-300 words), checking after each section whether it looks right so far.

The Process

Understanding the idea:

  • Check out the current project state first (files, docs, recent commits)
  • Read reference/interview-guide.md and follow its question sequence
  • Skip questions the user already answered in their initial request
  • Offer multiple-choice options where the guide provides them
  • Only one question per message (two max if closely related)
  • Summarize your understanding before moving to approaches

Exploring approaches:

  • Propose 2-3 different approaches with trade-offs
  • Present options conversationally with your recommendation and reasoning
  • Lead with your recommended option and explain why

Presenting the design:

  • Once you believe you understand what you're building, present the design
  • Break it into sections of 200-300 words
  • Ask after each section whether it looks right so far
  • Cover: architecture, components, data flow, error handling, testing
  • Be ready to go back and clarify if something doesn't make sense

Chaining Into Maestro

Brainstorming produces understanding, not documents. The validated design feeds directly into the maestro workflow -- never into standalone files under docs/.

When the design is validated, chain forward:

  1. Create the feature: maestro feature-create <name> -- this registers the feature in the maestro tracker
  2. Save discovery context: maestro context-write --feature <name> --name brainstorm --content "<validated design>" -- persists the brainstorming output where the planner can reference it
  3. Choose the planning path based on complexity:
    • Simple/well-understood: maestro plan-write --feature <name> -- write the plan directly from the brainstorming output
    • Ambitious/multi-component: Load maestro:design or maestro:new-track for deeper discovery and structured spec generation

The brainstorming output becomes the ## Discovery section that plan-write requires. Do not write design docs to docs/plans/ -- that bypasses the maestro workflow and leaves the design disconnected from execution.

Key Principles

  • One question at a time - Don't overwhelm with multiple questions
  • Multiple choice preferred - Easier to answer than open-ended when possible
  • Skip what's known - If the user gave details upfront, acknowledge them and move on
  • YAGNI ruthlessly - Remove unnecessary features from all designs
  • Explore alternatives - Always propose 2-3 approaches before settling
  • Incremental validation - Present design in sections, validate each
  • Be flexible - Go back and clarify when something doesn't make sense
  • Challenge assumptions - Surface fragile assumptions, ask what changes if they fail, offer lean fallback options

Expand your agent's capabilities with these related and highly-rated skills.

ReinaMacCredy/maestro

maestro-skill-author

Create, update, or debug maestro built-in skills. Covers SKILL.md frontmatter, reference directory structure, step-file architecture, build-time embedding, naming conventions, alias management, and registry validation. Use when creating a new maestro built-in skill, modifying an existing SKILL.md, adding reference files, debugging skill loading failures, updating the skills registry, or working on the skills full port. Also use when frontmatter validation fails, skills don't appear in skill-list, or reference files fail to load.

26 4
Explore
ReinaMacCredy/maestro

maestro:brainstorming

Use before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

26 4
Explore
ReinaMacCredy/maestro

mcp-builder

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

26 4
Explore
ReinaMacCredy/maestro

maestro:plan-review-loop

Deep-review any plan (maestro, Codex, Claude Code plan mode, or plain markdown) using iterative subagent review loops with BMAD-inspired adversarial edge-case discovery. Spawns reviewer subagents that find issues using pre-mortem, inversion, and red-team techniques, auto-fixes them with structured fix strategies, and re-reviews until the plan passes with zero actionable issues. Use when the user says 'review the plan', 'deep review', 'check the plan thoroughly', 'review loop', 'validate before approving', or wants rigorous plan validation before execution. Also use proactively before plan-approve when the plan is complex or high-risk.

26 4
Explore
ReinaMacCredy/maestro

maestro:research

Structured research workflow for maestro features. Guides tool selection across three tiers (codebase exploration, Context7 for library docs, NotebookLM for deep analysis), defines research patterns, finding organization via memory_write, and completion criteria. Use during the research pipeline stage after feature_create and before plan_write. Also use when investigating a problem space, comparing technical approaches, gathering context on unfamiliar code, or needing to understand external library APIs before making architectural decisions.

26 4
Explore
ReinaMacCredy/maestro

cli-for-agents

Designs or reviews CLIs so coding agents can run them reliably: non-interactive flags, layered --help with examples, stdin/pipelines, fast actionable errors, idempotency, dry-run, and predictable structure. Use when building a CLI, adding commands, writing --help, or when the user mentions agents, terminals, or automation-friendly CLIs.

26 4
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results