- name
SKILL.md
스킬 파일은 게시자의 저장소에 그대로 있습니다.
복사한 명령을 터미널에 붙여넣습니다. 이 SKILL.md가 해당 에이전트에 설치됩니다.
npx skills add google/elephant-goldfish-model --skill egm-brainstorm -a cursor -y복사한 명령을 터미널에 붙여넣습니다. 이 SKILL.md가 해당 에이전트에 설치됩니다.
npx skills add google/elephant-goldfish-model --skill egm-brainstorm -a claude-code -y복사한 명령을 터미널에 붙여넣습니다. 이 SKILL.md가 해당 에이전트에 설치됩니다.
npx skills add google/elephant-goldfish-model --skill egm-brainstorm -a codex -y복사한 명령을 터미널에 붙여넣습니다. 이 SKILL.md가 해당 에이전트에 설치됩니다.
npx skills add google/elephant-goldfish-model --skill egm-brainstorm -a grok -y복사한 메시지를 Grok Bot 채팅에 보냅니다. Bot이 GitHub에서 이 SKILL.md를 가져와 모든 Bot이 공유하는 스킬에 추가합니다.
Install this skill: https://github.com/google/elephant-goldfish-model/tree/HEAD/skills/egm-brainstorm게시자 제공
When running in Codex or ChatGPT Work, first read Codex integration.
In Claude Code or Cowork, read ${CLAUDE_PLUGIN_ROOT}/docs/claude.md first.
This skill acts as the upstream conversational brainstorming engine for the
Elephant-Goldfish Model (EGM). It turns "half-baked" or raw concepts into
hypotheses by combining interactive clarifying questions with an automated
Goldfish review. The outcome is an iteratively refined RFC summary
(concepts_brief.md) that leads directly into /egm-draft or review with
peers.
A Goldfish runs in a fresh context with no conversation history. Spawn each
subagent 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
frontmatter name (for example egm-zoom-out) is the subagent type to request
where your harness registers named subagents. Otherwise spawn a general-purpose
subagent and tell it to read that persona file first. Pass the prompt verbatim
and wait for the report. If your harness cannot nest subagents,
use direct dispatch instead of the synthesizer. See docs/harnesses.md.
If your harness has no subagent tool, stop and tell the user: a review in the same context is not a Goldfish review.
./concepts_brief.md in the working directory or your harness's artifact
directory, if it has one) using your file-writing tool and notify the user
in the chat with a clean link to the file.ask_question)
or supplying pre-canned multiple-choice candidate answers during open-ended
questioning.ask_question, if your harness has one, or plain chat) MUST contain
strictly one question (len(questions) == 1), be the sole tool call in the
turn, and provide clear, action-oriented options without (Recommended)
prefixes.Check for Concept Foundation & Author Identity: Verify if the user provided an initial
feature idea or concept prompt. If missing, prompt the user to describe what
they want to brainstorm. Resolve the brief's Author from git config user.name,
then GIT_AUTHOR_NAME; if neither is set, ask in chat.
Iterative Problem Drilling (Multi-Turn Chat): Do NOT rush into
launching subagents after a single response. Continue asking targeted,
open-ended clarifying questions across multiple chat turns as needed until
the problem statement, constraints, and target behavior are thoroughly
defined. Do NOT use structured question tools (ask_question) and do NOT
provide candidate multiple-choice options during problem exploration. Ask
open-ended questions directly in chat:
Readiness Checkpoint Gate (Single-Select): Once a clear foundation is
established, summarize the anchored working hypothesis in 2-3 sentences.
Present an explicit single-select confirmation gate (using a structured
question tool such as ask_question if your harness has one, or plain
chat):
{
"questions": [
{
"question": "Anchored feature hypothesis: [2-3 sentence summary]. How would you like to proceed?",
"options": [
"Review with Goldfishes",
"Clarify additional constraints or assumptions in chat"
],
"is_multi_select": false
}
]
}
Review with Goldfishes: The user confirms readiness.
Proceed immediately to Step 2 (Goldfish Review & Synthesis) to invoke
egm-synthesizer.Clarify additional constraints or assumptions in chat:
The user wishes to refine the problem statement or provides write-in
notes. Stay in Step 1, yield the turn in chat for details, incorporate
feedback into the hypothesis, and re-present the readiness gate when
ready.Proceed to Step 2 ONLY after Option 0 is confirmed. Do NOT spawn subagents before this gate confirms readiness.
egm-synthesizer agent (or parallel Goldfish subagents across the 7
specialized lenses if your harness cannot nest subagents):
egm-synthesizer (agents/synthesizer.md)Prompt: >- Conduct multi-lens brainstorm for feature concept:
[AnchoredFeatureHypothesis]. Mode: BRAINSTORM. Reviewers:
[egm-design, egm-codebase-details, egm-zoom-out, egm-comprehension, egm-implementation-readiness, egm-structural, egm-inventive-catalyst].egm-synthesizer subagent launches the
parallel Goldfish reviewers across the specialized lenses (egm-design,
egm-codebase-details, egm-zoom-out, egm-comprehension,
egm-implementation-readiness, egm-structural,
egm-inventive-catalyst) with Mode: BRAINSTORM.concepts_brief.md in the working directory (or your harness's artifact
directory, if it has one) using your file-writing tool.The concepts_brief.md artifact follows this structure:
# [Feature Name]
* **Author:** [Author Name or GitHub Handle]
* **Date:** [YYYY-MM-DD]
## Overview
[High-level summary of the feature, target user, and core value proposition written in plain English.]
## Analysis
[Cohesive analysis found by review lenses written in plain English, covering inventive contradictions, suggested catalog patterns, secondary trade-offs, and the Ideal Final Result.]
## Goals vs. Non-Goals
* **In-Scope Goals:** [Explicitly defined scope items]
* **Out-of-Scope Non-Goals:** [Features intentionally excluded]
## Alternatives Weighed
[Each option rejected during ideation, with the technical reason (e.g. "Rejected by author: <reason>"). Do not attribute a rejection to a maintainer without linking their issue, discussion, or PR. `/egm-draft` copies
these into Alternatives Considered and has no other source for them.]
## Key Decisions & Staging for Next Steps
[Key decisions resolved during ideation to be carried forward into `/egm-draft`.]
concepts_brief.md has been updated (give its path). Highlight 2-3 key
objections or open risks raised by the Goldfish reviewers.Artifact Alignment: Ask the user to review the final concepts_brief.md
artifact and confirm their alignment.
Step 4 Handoff Gate Modal (Single-Select): Once approved, present the
standardized handoff choices (using a structured question tool such as
ask_question if your harness has one, or plain chat):
{
"questions": [
{
"question": "Brainstorming complete. concepts_brief.md is finalized. Select next step:",
"options": [
"Publish concepts_brief.md as RFC for team feedback",
"Proceed to egm-draft (Initialize formal design document)",
"Continue refining concepts_brief.md in ideation mode",
"Conclude brainstorming and keep brief for later"
],
"is_multi_select": false
}
]
}
Publish concepts_brief.md as RFC for team feedback:
concepts_brief.md to docs/designs/<feature_name>.md using
your file-writing tool.docs/designs/SITEMAP.md if it exists.egm-draft skill on
docs/designs/<feature_name>.md with the host's command form (for
example /egm:egm-draft docs/designs/<feature_name>.md in Claude
Code and agy CLI, or the skill picker in Codex).Proceed to egm-draft (Initialize formal design document):
concepts_brief.md is saved in the working directory
or artifact directory.egm-draft skill with the host's
command form (for example /egm:egm-draft in Claude Code and agy
CLI, or the skill picker in Codex), noting that it automatically
ingests concepts_brief.md as its Priority 1 intake source.Continue refining concepts_brief.md in ideation mode:
Conclude brainstorming and keep brief for later:
concepts_brief.md remains saved for future reference.>-
---name: egm-brainstormdescription: >----# skills/egm-brainstorm/SKILL.mdFAQ
게시자에게서 skills/egm-brainstorm/SKILL.md를 다운로드하거나 경로를 복사해 저장소를 엽니다. PlugMCP는 스킬을 목록에 올릴 뿐 파일을 호스팅하지 않습니다.
게시자가 https://github.com/google/elephant-goldfish-model에서 관리합니다.
Claude, Cursor, Codex, Grok Build는 게시자의 저장소에서 추가한 SKILL.md를 읽을 수 있습니다. Grok Bot은 채팅에서 스킬의 GitHub 폴더 링크를 보내면 설치합니다.