reversa-brainstorm

Orchestrates a five-stage ideation pipeline that clarifies raw ideas before development artifacts exist.

Updated Aug 14, 2026
One-click install
npx skills add https://github.com/Ruggery/OCR_Cartorio --skill reversa-brainstorm-ruggery
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: reversa-brainstorm
Source: https://github.com/Ruggery/OCR_Cartorio/tree/main/.agents/skills/reversa-brainstorm
Command: npx skills add https://github.com/Ruggery/OCR_Cartorio --skill reversa-brainstorm-ruggery

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Teams often jump from a raw idea straight into code or specs without separating the problem from the solution, exploring alternatives, or stress-testing assumptions. This Skill orchestrates the Reversa Ideation Team, a structured pipeline that clarifies an idea through framing, divergence, premortem risk analysis, and convergence before any development artifact is written. ## Core Features & Use Cases - Five-Stage Pipeline: Routes the idea through framer (framing.md), explorer (options.md), challenger (risks.md), arbiter (decision.md), and pre-spec (pre-spec.md) agents, writing artifacts into _reversa_sdd/brainstorms/. - Context Detection: Distinguishes greenfield projects from legacy codebases with existing reverse-engineering extraction, anchoring ideation accordingly. - Session Management: Tracks sessions in .reversa/active-ideation.json, detects in-progress sessions, derives the real stage from files on disk, and supports resuming, parallel sessions, or reopening a stage. - Use Case: A product owner says "quero pensar antes de codar" about a new OCR feature; the Skill opens session 001, records the literal idea, and hands off stage by stage until a decision and pre-spec are ready for /reversa-new or /reversa-requirements. ## Quick Start Ask the agent to run /reversa-brainstorm and describe your idea in one or two sentences to start a guided ideation session.

Frequently Asked Questions about reversa-brainstorm

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

FAQPage Schema
How do I structure idea brainstorming before writing code?▼

Run /reversa-brainstorm and state your idea in one or two sentences. The Skill opens a numbered session folder and routes the idea through framing, option exploration, premortem risk analysis, and a final decision, producing one Markdown artifact per stage.

What artifacts does the Reversa ideation pipeline produce?▼

Each session produces idea.md, framing.md, options.md, risks.md, decision.md, and pre-spec.md inside _reversa_sdd/brainstorms/<session-id>-<short-name>/. The decision artifact feeds directly into /reversa-new, /reversa-requirements, or /reversa-migrate.

Does reversa-brainstorm work on existing legacy codebases?▼

Yes. It detects legacy context when the output folder already contains Markdown files from a reverse-engineering extraction and anchors ideation to that mapped material. Greenfield projects without extraction are also fully supported.

Can I resume an interrupted ideation session?▼

Yes. The Skill reads .reversa/active-ideation.json and the files on disk to determine the real stage, then offers a menu to continue, start a parallel session, or reopen a specific stage. Disk state wins over stale metadata.

When should I not use a structured ideation pipeline?▼

Skip it for trivial changes, bug fixes, or well-understood tasks where framing and premortem analysis add no value. The pipeline is designed for ambiguous ideas where problem-solution separation and risk challenge matter.