egm-brainstorm

1# EGM Brainstorm: Interactive Multi-Lens Ideation & Refinement
2 
3When running in Codex or ChatGPT Work, first read [Codex integration](../../docs/codex.md).
4In Claude Code or Cowork, read `${CLAUDE_PLUGIN_ROOT}/docs/claude.md` first.
5 
6## Overview
7 
8This skill acts as the upstream conversational brainstorming engine for the
9Elephant-Goldfish Model (EGM). It turns "half-baked" or raw concepts into
10hypotheses by combining **interactive clarifying questions** with an automated
11**Goldfish review**. The outcome is an iteratively refined RFC summary
12(`concepts_brief.md`) that leads directly into `/egm-draft` or review with
13peers.
14 
15## Delegation
16 
17A Goldfish runs in a fresh context with no conversation history. Spawn each
18subagent with your harness's subagent tool (Antigravity: `invoke_subagent`; Claude Code: `Agent`; Codex: `spawn_agent`). Each subagent is defined in `agents/<file>.md`, and its
19frontmatter `name` (for example `egm-zoom-out`) is the subagent type to request
20where your harness registers named subagents. Otherwise spawn a general-purpose
21subagent and tell it to read that persona file first. Pass the prompt verbatim
22and wait for the report. If your harness cannot nest subagents,
23use direct dispatch instead of the synthesizer. See `docs/harnesses.md`.
24If your harness has no subagent tool, stop and tell the user: a review in the same context is not a Goldfish review.
25 
26## Execution Constraints (CRITICAL)
27…