Index of every page on this site: llms.txt
All skills
google avatar

/egm-brainstorm

@70406c4
by googlegoogle/elephant-goldfish-model22k stars
1,589
Run it yourself

Interactive ideation and brainstorming skill for the Elephant & Goldfish Model (EGM). Helps turn half-baked concepts into structured hypotheses via clarifying questions, review, and iterative refinement. Produces an RFC summary for human review or more detailed design with egm-draft.

Requires /egm-draft
Use this Skill: https://skilld.dev/gh/google/elephant-goldfish-model/egm-brainstorm

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

TEST.md

≈243 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Test Plan: EGM Brainstorm Skill

Frontmatter and link checks run in pytest tests/unit (see TESTING.md).

Protocol Verification Checklist

When evaluating or exploring egm-brainstorm interactively in chat, verify:

  • Step 1 (Open-Ended Clarification & Gate): Drills down into half-baked concepts using open-ended chat questions (without structured question tools or multiple-choice lists) and enforces a user readiness checkpoint gate before subagent invocation.
  • Step 2 (Upstream Multi-Lens Ideation): Evaluates feature concepts across the 7 specialized Goldfish perspective lenses (Contrarian/YAGNI, Cost/Quota Economics, UX Ergonomics, Migration & Compatibility, Observability & SRE, Tech Debt & Maintenance, Inventive Catalyst).
  • Step 3 & 4 (Concepts Brief Deliverable & Handoff): Compiles and saves the synthesized concepts_brief.md artifact for user review and handoff to /egm-draft.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts13d3 checks · Risk SAFE
  • Gen Agent Trust Hub14d

    This skill focuses on structured brainstorming and ideation using multi-lens reviews. It includes standard instructional constraints and typical integration points for AI agent environments. No security issues were identified.

  • Socket13d

    No alerts

  • Snyk14d

    Risk: LOW · No issues

Signed by skilld at 70406c4. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 3 days ago.

Activeupdated 2 weeks ago
disable-model-invocation
true

README badge

README badge for google/elephant-goldfish-model/egm-brainstorm