01 Brainstorm

Brainstorm

Clarifies and refines a feature request through structured iterative questioning until no ambiguity remains. Auto-triggers on prompts indicating uncertainty or need for clarification.

Available actions

Default flow

Sequential skill: 01 → 02 → 03 → 04 → 05. Loop 02 → 03 until no ambiguity (router checks 03 output for needs_more).

Transversal rules

• Never assume technical solutions upfront.
• Use bullet points for clarity.
• DO NOT IMPLEMENT ANYTHING.
• Wait for user response after questions or approval prompts.

References

• @references/ambiguity-detection.md: How to identify and resolve unclear requirements.

Assets

• @assets/question-templates.md: Reusable probing question categories.

External data

• None.

01 - Capture Request

Detail the initial feature request in bullet points (no technical aspects).

Inputs

• user_intent : the user's prompt or request text.

Outputs

Bullet-point list of features/requirements.

- Feature 1
- Feature 2

Depends on

• None

Process

1. Parse user_intent into non-technical bullet points. 2. Output the structured list.

Test

• Output is a list of bullet points without technical details.

02 - Ask Probing Questions

Generate questions to challenge assumptions, edge cases, and missing context.

Inputs

• captured_request : original bullet points request.

Outputs

List of 3-5 probing questions.

- Question 1?
- Question 2?

Depends on

• 01-capture-request

Process

1. Analyze captured_request for gaps (assumptions, edges, context). 2. Generate targeted questions using assets/question-templates.md. 3. Output questions for user response.

Test

• Questions address potential ambiguities in the request.

03 - Integrate Answers

Update the request with user responses and determine if more clarification is needed.

Inputs

• captured_request : original bullet points request.
• user_answers : responses to questions.

Outputs

Updated request and flag for more questions.

{
  "updated_request": ["- Updated feature 1", "- Updated feature 2"],
  "needs_more": true
}

Depends on

• 02-ask-probing-questions

Process

1. Merge user_answers into captured_request bullets. 2. Assess if ambiguity remains; set needs_more. 3. Output updated request and flag.

Test

• Updated request incorporates answers; needs_more accurately reflects clarity.

04 - Refine and Validate

Finalize the request and validate for remaining ambiguity.

Inputs

• updated_request : user request with clarification answers

Outputs

Refined request and validation result.

{
  "refined_request": "Consolidated description",
  "is_clear": true,
  "issues": []
}

Depends on

• 03-integrate-answers

Process

1. Consolidate updated_request into coherent description. 2. Check for ambiguity using references/ambiguity-detection.md. 3. Output refined request, clarity flag, and any issues.

Test

• Refined request is clear and consolidated; is_clear is accurate.

05 - Confirm Approval

Present the final refined request and wait for user approval.

Inputs

• refined_request from previous action.

Outputs

Approval prompt displayed.

Does this refined request look correct? (Yes/No)

Depends on

• 04-refine-and-validate

Process

1. Display refined_request clearly. 2. Output approval prompt and wait for response.

Test

• Prompt is displayed with the refined request.

Question Templates

Reusable categories for probing questions:

• Who are the primary users? (e.g., customers, employees)
• What platforms or environments? (web, mobile, desktop)
• What are the key assumptions?
• What edge cases should be considered?
• What constraints or limitations exist?
• How does this integrate with existing systems?

← aidd-framework / aidd-refine

01 - Brainstorm

Interactive brainstorming session that clarifies and refines a vague request through iterative questioning, until no ambiguity remains and the user explicitly approves the result.

When to use

• The user surfaces an unclear requirement, a half-formed idea, or a fuzzy

feature description.

• A request feels under-specified and the next step (plan, code, test) would

rest on assumptions.

• The user explicitly asks to brainstorm, refine, or clarify a request.

When NOT to use

• The technical spec is already clear and actionable.
• The user only needs implementation details on a settled requirement.
• The request is concrete enough that planning or coding can start directly.

How to invoke

Use skill aidd-refine:01-brainstorm

The skill walks 5 atomic actions:

1. capture-request - restate the initial intent as bullet points. 2. ask-probing-questions - challenge assumptions with targeted questions. 3. integrate-answers - fold the user's answers back into the request. 4. refine-and-validate - finalize and scan for residual ambiguity. 5. confirm-approval - wait for explicit user sign-off.

The router loops 02 → 03 until the validator marks the request unambiguous.

Outputs

• A refined, bullet-pointed request the user has explicitly approved.
• No code, no plan, no files. Intent only.

Prerequisites

• A user-supplied request, even if vague.
• Willingness to answer clarifying questions before moving forward.

Technical details

See `SKILL.md` for the action contract, `actions/` for each step, `references/ambiguity-detection.md` for the ambiguity heuristics, and `assets/question-templates.md` for the reusable question categories.

Ambiguity Detection

Signs of unclear requirements:

• Vague terms like "users", "fast", "easy".
• Missing context (who, what, when, where, why).
• Assumptions not stated.
• No edge cases mentioned.
• Incomplete integration details.

How to resolve:

• Ask specific questions.
• Use examples.
• Break down into smaller parts.
• Validate with user confirmation.