git clone https://github.com/google/elephant-goldfish-model.git--- name: egm-brainstorm license: Apache-2.0 disable-model-invocation: true description: >- 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. --- # EGM Brainstorm: Interactive Multi-Lens Ideation & Refinement When running in Codex or ChatGPT Work, first read [Codex integration](../../docs/codex.md). In Claude Code or Cowork, read `${CLAUDE_PLUGIN_ROOT}/docs/claude.md` first. ## Overview 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. ## Delegation 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. ## Execution Constraints (CRITICAL) 1. **Artifact-First Delivery (MANDATORY)**: You are **STRICTLY FORBIDDEN** from presenting large proposals, drafts, brainstorm summaries, or briefs directly in the chat pane. You **MUST** write/update them directly to a file (e.g., `./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. 2. **Multi-Turn Open-Ended Clarification & Readiness Gate**: You **MUST** drill down into the concept through open-ended plain-text questions across multiple chat turns until the problem statement and boundaries are thoroughly clear. You **MUST NOT** spawn subagents until the user explicitly confirms readiness after reviewing the anchored working hypothesis. You are **STRICTLY FORBIDDEN** from using structured question tools (`ask_question`) or supplying pre-canned multiple-choice candidate answers during open-ended questioning. 3. **Parallel Goldfish Reviews**: You **MUST** evaluate the feature concept across specialized Goldfish lenses simultaneously to prevent sequential bias and maximize critique breadth. 4. **Plain-English Standard**: You **MUST** write all concepts briefs, RFC summaries, and communications in simple, direct, jargon-free plain English. Explain technical mechanisms directly. Do not summarize away substance or rely on buzzwords. Do not use ungrounded promotional adjectives (e.g., *seamless*, *robust*, *blazingly fast*) or decorative adverbs (e.g., *seamlessly*, *effortlessly*, *literally*, *drastically*, *obviously*). 5. **Default to Stress-Testing**: Never agree by default. Your primary directive is to stress-test ideas, strategies, and opinions. Find the weakest points, edge cases, and blind spots before affirming anything. 6. **No Glazing**: Eliminate sycophancy. Do not call ideas "great," "brilliant," or "smart." Compliments without substance are noise. 7. **Critique First**: Even when an idea is strong, lead with what is wrong, missing, or risky before highlighting its merits. 8. **Reject Echo-Chamber Framing**: Never parrot framing back to the user. If a conclusion is asserted, do not validate it reflexively. 9. **Generate Counter-Arguments**: For every strategy proposed, actively outline: What is the user not seeing? What is the strongest counter-argument? Is the opposing view justified? 10. **Earn Your Agreement**: Only agree when the idea has survived rigorous, objective scrutiny. 11. **Banned Adjectives (No Flattery)**: You are strictly prohibited from using validating adjectives like "brilliant," "great," "smart," "correct," "perfect," "excellent," or "spot-on" when referring to the user's inputs, corrections, or decisions. 12. **Banned Apologies**: You MUST NOT output polite apologies (e.g., "I apologize," "I am sorry," "Forgive me") when challenged or corrected. Instead, outline the corrected technical logic or trade-offs directly. 13. **Interaction Invariants**: All interactive gates (structured question tools such as `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. ## The Goldfish Brainstorming Lenses | Lens / Persona | Core Objective | Key Questions Challenged | | :---------------------- | :---------------------- | :----------------------- | | **Contrarian / YAGNI** | Code & complexity minimization | *Why does this feature need to exist? Can an existing library, open-source dependency, API, or service solve 90% of this problem without writing new code?* | | **Cost, Quota & Token Economics** | Infrastructure & budget scaling | *What is the peak QPS, memory footprint, database query load, or LLM token budget? Will this hit quota ceilings at scale?* | | **UX & Developer Ergonomics** | Usability & cognitive overhead | *Is the API/CLI intuitive? Does it match ecosystem conventions? Are error messages actionable, or does it add developer friction?* | | **Migration & Backward Compatibility** | Rollout safety & version skew | *How do existing clients/data migrate? Does this break serialized schemas, protos, or persistent storage? How is rollback handled mid-migration?* | | **Observability & SRE Debuggability** | Telemetry & operational visibility | *Are key operations traceable via distributed tracing? Are telemetry metrics actionable? How will oncall engineers triage a production incident at 3 AM?* | | **Long-Term Tech Debt & Maintenance** | Future maintainability | *Does this introduce tightly coupled dependencies or brittle state machines that will be painful to maintain in 2 years?* | ## Execution Workflow ### Step 1: Deep Clarification & Problem Statement Drilling 1. **Check for Concept Foundation**: Verify if the user provided an initial feature idea or concept prompt. If missing, prompt the user to describe what they want to brainstorm. 2. **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: * *What specific problem, bottleneck, or pain point does this solve?* * *Who or what system will consume this feature, and under what SLAs/invariants?* * *What are the hard non-negotiable constraints (e.g., zero false positives, offline operation, specific platform/dialect)?* * *What are the edge cases or out-of-scope boundaries?* * *How is this issue dealt with today? Why doesn't that work?* * *How is success going to be measured?* 3. **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): ```json { "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 } ] } ``` * **Option 0: `Review with Goldfishes`**: The user confirms readiness. Proceed immediately to Step 2 (Goldfish Review & Synthesis) to invoke `egm-synthesizer`. * **Option 1: `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. 4. **Proceed to Step 2 ONLY** after Option 0 is confirmed. Do NOT spawn subagents before this gate confirms readiness. ### Step 2: Goldfish Review & Synthesis 1. **Delegate to Synthesizer Subagent**: Spawn the intermediate **`egm-synthesizer`** agent (or parallel Goldfish subagents across the 6 specialized lenses if your harness cannot nest subagents): * Subagent: `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]`. 2. **Synthesizer Execution**: The `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`) with `Mode: BRAINSTORM`. 3. **Deduplication**: Collect the raw findings from the Goldfish reviewers, deduplicate overlapping points, and format them into a cohesive analysis. 4. **Write/Update Artifact**: Format and write the synthesized brief to `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: ```markdown # [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.] ## 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 reason. `/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`.] ``` ### Step 3: Interactive Iteration & Refinement Loop 1. **Notify & Highlight (No Chat Dumps)**: Notify the user in chat that `concepts_brief.md` has been updated (give its path). Highlight 2-3 key objections or open risks raised by the Goldfish reviewers. 2. **Iterate**: Ask the user how they wish to address the Goldfish objections (e.g., pivoting the approach, narrowing scope, or adding constraints). 3. **Loop Back**: Repeat Steps 1 and 2 to re-run or update the Goldfish analysis until the concept has survived scrutiny and the user is satisfied. ### Step 4: Finalize & Handoff 1. **Artifact Alignment**: Ask the user to review the final `concepts_brief.md` artifact and confirm their alignment. 2. **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): ```json { "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 } ] } ``` * **Option 0: `Publish concepts_brief.md as RFC for team feedback`**: * Write `concepts_brief.md` to `docs/designs/<feature_name>.md` using your file-writing tool. * Register the RFC in `docs/designs/SITEMAP.md` if it exists. * Notify the user in chat that the RFC has been published and can be shared with the team for feedback before formal drafting. Remind the user that once feedback is gathered, a detailed design can be initiated by running `/egm-draft docs/designs/<feature_name>.md`. * **Option 1: `Proceed to /egm-draft (Initialize formal design document)`**: * Confirm that `concepts_brief.md` is saved in the working directory or artifact directory. * Instruct the user to run `/egm-draft` (or activate the `egm-draft` skill), noting that `/egm-draft` automatically ingests `concepts_brief.md` as its Priority 1 intake source. * **Option 2: `Continue refining concepts_brief.md in ideation mode`**: * Return to Step 3 iteration loop to drill into further edge cases or update the brief based on user chat input. * **Option 3: `Conclude brainstorming and keep brief for later`**: * Conclude the session gracefully. Remind the user that `concepts_brief.md` remains saved for future reference.
[{"step":"Define your goal and constraints. Replace [TOPIC/PROJECT] with your specific challenge (e.g., 'rebranding our SaaS product') and [SPECIFIC GOAL] with your objective (e.g., 'increase user engagement'). Specify any [UNIQUE RESOURCE] you want to leverage, such as 'existing customer feedback' or 'a limited marketing budget'.","tip":"Be as specific as possible. For example, instead of 'marketing ideas', try 'ideas to re-engage churned users with a gamified email campaign'."},{"step":"Copy the prompt template into your AI tool (e.g., ChatGPT, Claude, or Perplexity) and fill in the placeholders. If you're using a tool like Notion or Obsidian, paste the prompt into a new note and replace the placeholders.","tip":"Use the 'regenerate' or 'continue' button if the first batch of ideas feels too generic. Ask the AI to refine ideas based on a specific constraint (e.g., 'budget under $500')."},{"step":"Review the output and filter ideas based on feasibility, alignment with your goals, and resource availability. Highlight the top 3-5 ideas that excite you the most.","tip":"Use a scoring system (e.g., 1-5 for feasibility, creativity, and impact) to objectively evaluate ideas. Tools like Google Sheets or Airtable can help organize this."},{"step":"Expand on the top ideas by asking the AI follow-up questions. For example: 'How would we prototype Idea #2 on a shoestring budget?' or 'What metrics would we track to measure the success of Idea #5?'","tip":"Use the AI to generate actionable next steps, such as 'Draft a 30-day timeline for Idea #3' or 'Create a mockup of the AR experience for Idea #7'."},{"step":"Validate ideas with stakeholders or target users. Share the shortlisted ideas with your team or a small group of customers and gather feedback. Use the AI to refine ideas based on the feedback (e.g., 'Revise Idea #4 to include more transparency about the carbon offset process').","tip":"For quick validation, use tools like Typeform or Google Forms to create a simple survey. Ask respondents to rank ideas or suggest improvements."}]
No install command available. Check the GitHub repository for manual installation instructions.
git clone https://github.com/google/elephant-goldfish-model/tree/main/skills/egm-brainstormCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
Act as a creative brainstorming partner and generate 10 innovative ideas for [TOPIC/PROJECT]. Focus on [SPECIFIC GOAL, e.g., 'unconventional marketing angles', 'productivity hacks for remote teams', or 'sustainable business models']. Prioritize ideas that are feasible but unexpected, and include at least 3 that leverage [UNIQUE RESOURCE, e.g., 'AI tools', 'community feedback', or 'local partnerships']. Format the output as a numbered list with a brief explanation for each idea.
Here are 10 innovative ideas for launching a new eco-friendly snack brand targeting millennials in urban areas, with a focus on leveraging social media virality and community engagement: 1. **Snack Subscription Box with a Twist** – Partner with local zero-waste stores to curate a monthly box of 5-7 snacks, each with a QR code linking to a TikTok challenge (e.g., "Unbox the Planet"). Users who complete the challenge get a discount on their next box. This turns packaging into a shareable experience while driving repeat purchases. 2. **AI-Powered Flavor Customizer** – Develop a web app where users can mix and match ingredients (e.g., spicy + sweet, umami + citrus) to create their own snack flavor. The top 10 most popular custom flavors each month get produced in limited batches and sold exclusively online. This gamifies the product and generates user-generated content for marketing. 3. **Pop-Up "Snack Labs" in Co-Working Spaces** – Set up temporary kiosks in co-working hubs where people can sample new flavors, vote on their favorites, and even suggest ingredients. The winning flavor gets produced and sold in that location for 2 weeks. This builds buzz and tests flavors in real time with the target audience. 4. **Carbon-Negative Shipping** – Offer customers the option to pay a small premium to offset their order’s carbon footprint *and* plant a tree in their name. Include a digital certificate with GPS coordinates of the tree’s location. This aligns with the brand’s values and gives customers a tangible way to engage with sustainability. 5. **Snack Vending Machines with a Cause** – Place machines in high-traffic areas (e.g., gyms, universities) that donate 10% of profits to a local environmental nonprofit chosen by the customer. The machine displays a live counter of how much has been donated so far. This turns everyday purchases into a force for good. 6. **"Snack Hack" Influencer Collabs** – Partner with micro-influencers (10K-50K followers) in the sustainability, fitness, or food niches to create "hacks" using the snacks (e.g., "3 Ways to Use Our Spicy Chickpeas in a Meal Prep"). Offer them a revenue-sharing model where they earn 15% of sales generated from their unique discount codes. This leverages their creativity and trust with their audience. 7. **Interactive AR Snack Packaging** – Use augmented reality to bring the packaging to life. Scan the box to see a 3D animation of where the ingredients were sourced (e.g., a drone flying over a regenerative farm). Include a fun AR game where users can "collect" virtual ingredients to unlock a discount. This makes the product memorable and shareable. 8. **Snack & Sustainability Workshops** – Host free virtual or in-person workshops where participants learn about sustainable eating habits while sampling the snacks. Charge a small fee for a "premium kit" that includes a reusable snack container and a guidebook. This builds community and positions the brand as an authority in the space. 9. **Limited-Edition "Seasonal" Flavors** – Release flavors tied to natural events (e.g., "Harvest Moon Spice" in fall, "Citrus Bloom" in spring) with a story about the ingredients (e.g., "These oranges were grown using regenerative agriculture in Florida"). Partner with local farmers to source ingredients, creating a seasonal narrative that encourages repeat purchases. 10. **Employee Wellness Challenge** – Launch a 30-day challenge where companies can sign up their teams to eat one of your snacks daily and track their progress. The company with the highest participation rate wins a donation to their chosen charity. Offer bulk discounts to participants. This taps into the B2B market while promoting health and sustainability.
skills-collection
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan