brainstorming

Brainstorming Ideas Into Designs

Help turn ideas into fully formed designs and specs through natural collaborative dialogue.

Use this skill when the human has chosen a design-first workflow, explicitly asked to brainstorm or plan, or the task clearly needs structured design work.

Do NOT use it for tiny, targeted, or clearly-scoped requests when the human wants direct execution.

If the task is in the gray area and the human has not chosen a workflow yet, offer a choice between direct execution and the full Softpowers flow first.

Once this skill is active, do NOT invoke any implementation skill, write any code, scaffold any project, or take any implementation action until you have presented a design and the user has approved it.

Anti-Pattern: Forcing Design Work After the Human Chose Direct Execution

This skill is for work where design alignment is useful or requested. A typo fix, a narrow one-file change, or another clearly-scoped task does not need formal brainstorming if the human prefers direct execution.

But once the human chooses this skill or asks for the full flow, do the design properly. Don't half-brainstorm your way into code.

Checklist

You MUST create a task for each of these items and complete them in order:

1. Explore project context: check files, docs, recent commits
2. Offer visual companion (if topic will involve visual questions): this is its own message, not combined with a clarifying question. See the Visual Companion section below.
3. Ask clarifying questions: one at a time, understand purpose/constraints/success criteria
4. Propose 2-3 approaches: with trade-offs and your recommendation
5. Present design: in sections scaled to their complexity, get user approval after each section
6. Ask output choice: Ask the user to choose the final spec output: Simple Markdown or Enriched HTML
7. Write markdown spec draft: save the spec body to a unique temporary markdown path such as SPEC_DRAFT="$(mktemp /tmp/softpowers-spec-XXXXXX.md)"
8. Spec self-review: quick inline check for placeholders, contradictions, ambiguity, scope (see below)
9. Spec review loop: dispatch the spec reviewer subagent on the markdown draft, fix issues until approved
10. Save final spec: run printenv PROJECTS_DOCS_PATH, resolve {repoName} explicitly, save the spec to the selected .md or .html path, validate enriched HTML output, then commit only in the repo that actually owns that path
11. User reviews written spec: ask user to review the saved spec file before proceeding
12. Transition to implementation: invoke writing-plans skill to create implementation plan

Process Flow

digraph brainstorming {
    "Explore project context" [shape=box];
    "Visual questions ahead?" [shape=diamond];
    "Offer Visual Companion\n(own message, no other content)" [shape=box];
    "Ask clarifying questions" [shape=box];
    "Propose 2-3 approaches" [shape=box];
    "Present design sections" [shape=box];
    "User approves design?" [shape=diamond];
    "Ask final output:\nSimple Markdown or Enriched HTML" [shape=box];
    "Write markdown spec draft" [shape=box];
    "Spec self-review\n(fix inline)" [shape=box];
    "Spec reviewer approves\nmarkdown draft?" [shape=diamond];
    "Save Markdown or\ngenerate + validate HTML" [shape=box];
    "User reviews spec?" [shape=diamond];
    "Invoke writing-plans skill" [shape=doublecircle];

    "Explore project context" -> "Visual questions ahead?";
    "Visual questions ahead?" -> "Offer Visual Companion\n(own message, no other content)" [label="yes"];
    "Visual questions ahead?" -> "Ask clarifying questions" [label="no"];
    "Offer Visual Companion\n(own message, no other content)" -> "Ask clarifying questions";
    "Ask clarifying questions" -> "Propose 2-3 approaches";
    "Propose 2-3 approaches" -> "Present design sections";
    "Present design sections" -> "User approves design?";
    "User approves design?" -> "Present design sections" [label="no, revise"];
    "User approves design?" -> "Ask final output:\nSimple Markdown or Enriched HTML" [label="yes"];
    "Ask final output:\nSimple Markdown or Enriched HTML" -> "Write markdown spec draft";
    "Write markdown spec draft" -> "Spec self-review\n(fix inline)";
    "Spec self-review\n(fix inline)" -> "Spec reviewer approves\nmarkdown draft?";
    "Spec reviewer approves\nmarkdown draft?" -> "Write markdown spec draft" [label="no, fix draft"];
    "Spec reviewer approves\nmarkdown draft?" -> "Save Markdown or\ngenerate + validate HTML" [label="yes"];
    "Save Markdown or\ngenerate + validate HTML" -> "User reviews spec?";
    "User reviews spec?" -> "Write markdown spec draft" [label="changes requested"];
    "User reviews spec?" -> "Invoke writing-plans skill" [label="approved"];
}

The terminal state is invoking writing-plans. Do NOT invoke frontend-design, mcp-builder, or any other implementation skill. The ONLY skill you invoke after brainstorming is writing-plans.

The Process

Understanding the idea:

• Check out the current project state first (files, docs, recent commits)
• Before asking detailed questions, assess scope: if the request describes multiple independent subsystems (e.g., "build a platform with chat, file storage, billing, and analytics"), flag this immediately. Don't spend questions refining details of a project that needs to be decomposed first.
• If the project is too large for a single spec, help the user decompose into sub-projects: what are the independent pieces, how do they relate, what order should they be built? Then brainstorm the first sub-project through the normal design flow. Each sub-project gets its own spec → plan → implementation cycle.
• For appropriately-scoped projects, ask questions one at a time to refine the idea
• Prefer multiple choice questions when possible, but open-ended is fine too
• Only one question per message - if a topic needs more exploration, break it into multiple questions
• Focus on understanding: purpose, constraints, success criteria

Exploring approaches:

• Propose 2-3 different approaches with trade-offs
• Present options conversationally with your recommendation and reasoning
• Lead with your recommended option and explain why

Presenting the design:

• Once you believe you understand what you're building, present the design
• Scale each section to its complexity: a few sentences if straightforward, up to 200-300 words if nuanced
• Ask after each section whether it looks right so far
• Cover: architecture, components, data flow, error handling, testing
• Be ready to go back and clarify if something doesn't make sense

Design for isolation and clarity:

• Break the system into smaller units that each have one clear purpose, communicate through well-defined interfaces, and can be understood and tested independently
• For each unit, you should be able to answer: what does it do, how do you use it, and what does it depend on?
• Can someone understand what a unit does without reading its internals? Can you change the internals without breaking consumers? If not, the boundaries need work.
• Smaller, well-bounded units are also easier for you to work with - you reason better about code you can hold in context at once, and your edits are more reliable when files are focused. When a file grows large, that's often a signal that it's doing too much.

Working in existing codebases:

• Explore the current structure before proposing changes. Follow existing patterns.
• Where existing code has problems that affect the work (e.g., a file that's grown too large, unclear boundaries, tangled responsibilities), include targeted improvements as part of the design - the way a good developer improves code they're working in.
• Don't propose unrelated refactoring. Stay focused on what serves the current goal.

After the Design

Documentation:

• Ask the user to choose the final spec output: Simple Markdown or Enriched HTML. Ask before writing the final spec artifact; do not assume HTML.
• Before resolving the save path, run printenv PROJECTS_DOCS_PATH.
• Resolve {repoName} this way:
  • git repo available: use the git top-level directory basename
  • no git repo: use the current project directory basename
  • project not on disk yet / slug still ambiguous: ask the human once and use that slug
• The final spec path is:
  • If the user chooses Simple Markdown:
    • $PROJECTS_DOCS_PATH/{repoName}/specs/YYYY-MM-DD-<topic>-design.md when PROJECTS_DOCS_PATH is set
    • docs/softpowers/specs/YYYY-MM-DD-<topic>-design.md when it is unset
  • If the user chooses Enriched HTML:
    • $PROJECTS_DOCS_PATH/{repoName}/specs/YYYY-MM-DD-<topic>-design.html when PROJECTS_DOCS_PATH is set
    • docs/softpowers/specs/YYYY-MM-DD-<topic>-design.html when it is unset
• Prefer markdown-first authoring. Draft the spec body in markdown at a unique temporary path, for example:

SPEC_DRAFT="$(mktemp /tmp/softpowers-spec-XXXXXX.md)"

• Softpowers doc helpers live in the Softpowers package, not in the project you are designing. Resolve SOFTPOWERS_ROOT to the package root that contains this skills/ directory, then use absolute helper paths from there for every scripts/, templates/, examples/, and docs/softpowers/ reference.
• Do not run node scripts/create-spec-doc.mjs or node scripts/validate-spec-doc.mjs relative to the target project, and do not use find to hunt for those helpers. Resolve SOFTPOWERS_ROOT once from the skill/package path and reuse it.
• After your self-review and before creating the final spec artifact, dispatch a reviewer subagent using skills/brainstorming/spec-document-reviewer-prompt.md. Give the reviewer the selected output format and resolved final output path. The reviewer should read the markdown draft, return Approved or Issues Found, and you should fix the markdown draft until it is approved.
• If the user chooses Simple Markdown, copy the approved markdown draft to the resolved .md path. Do not run the HTML helper or validator for this output mode.
• If the user chooses Enriched HTML, generate the HTML shell and TOC with:

node "$SOFTPOWERS_ROOT/scripts/create-spec-doc.mjs" \
  --title "<Spec title>" \
  --slug <topic-slug> \
  --body "$SPEC_DRAFT"

• If you already have section fragments as HTML and the user chose Enriched HTML, pass --body-format html instead. Those fragments must contain <section id="..."> blocks with <h2> headings.
• The helper fills $SOFTPOWERS_ROOT/templates/spec.template.html, builds the TOC, validates the finished document, and prints the final path clearly.
• If you must fill the template manually for Enriched HTML, keep the shell intact and replace:
  • {{DOC_TITLE}} — the spec name shown in <title> and <h1>
  • {{TOC_ITEMS}} — the full TOC block, typically <h3>Table of contents</h3><ol>...</ol>
  • {{OVERVIEW}} — the complete spec body (sections, code blocks, tables, etc.)
• For Enriched HTML, validate the saved spec with node "$SOFTPOWERS_ROOT/scripts/validate-spec-doc.mjs" <resolved-spec-path>. This is a blocking gate: if the validator exits non-zero or reports any errors, stop immediately, show the full validation output to the user, fix the reported issues, then re-run the validator before proceeding to the next step.
• If the user wants changes after reading the final spec, edit the markdown draft first, re-run the markdown review loop if the change is material, then re-save the Markdown output or regenerate and re-validate the HTML.
• Use elements-of-style:writing-clearly-and-concisely skill if available.
• Commit rule:
  • if the resolved spec path is inside the current project repo, commit it there
  • if it resolves outside the current project repo, do not also create a repo-local copy; report the external path clearly and only commit in that external docs repo when it exists and the workflow actually calls for a commit
• Canonical example source: examples/html-docs/canonical-spec.md
• Canonical generated example: docs/softpowers/specs/2026-05-13-canonical-html-spec-workflow-design.html

Spec Self-Review: After writing the markdown draft, look at it with fresh eyes:

1. Placeholder scan: Any "TBD", "TODO", incomplete sections, or vague requirements? Fix them.
2. Internal consistency: Do any sections contradict each other? Does the architecture match the feature descriptions?
3. Scope check: Is this focused enough for a single implementation plan, or does it need decomposition?
4. Ambiguity check: Could any requirement be interpreted two different ways? If so, pick one and make it explicit.

Fix any issues inline. No need to re-review: just fix and move on.

Spec Review Loop: The markdown draft must be reviewed before saving the selected final output.

1. Save the draft to a unique temporary path such as SPEC_DRAFT="$(mktemp /tmp/softpowers-spec-XXXXXX.md)".
2. Run the self-review checklist above and fix any issues in the markdown draft.
3. Dispatch a reviewer subagent using skills/brainstorming/spec-document-reviewer-prompt.md with the selected output format and resolved output path.
4. If the reviewer finds issues, fix the markdown draft and re-dispatch the reviewer.
5. Only after the reviewer approves should you save the Simple Markdown spec or generate and validate the Enriched HTML spec.

User Review Gate: After the markdown spec review loop passes and the selected final spec is saved, ask the user to review the written spec before proceeding:

"Spec written to <path>. Please review it and let me know if you want to make any changes before we start writing out the implementation plan."

Use <validation note> as and validated for Enriched HTML, and omit it for Simple Markdown. Wait for the user's response. If they request changes, make them and re-run the spec review loop. Only proceed once the user approves.

Implementation:

• Invoke the writing-plans skill to create a detailed implementation plan
• Do NOT invoke any other skill. writing-plans is the next step.

Key Principles

• One question at a time - Don't overwhelm with multiple questions
• Multiple choice preferred - Easier to answer than open-ended when possible
• YAGNI ruthlessly - Remove unnecessary features from all designs
• Explore alternatives - Always propose 2-3 approaches before settling
• Incremental validation - Present design, get approval before moving on
• Be flexible - Go back and clarify when something doesn't make sense

Visual Companion

A browser-based companion for showing mockups, diagrams, and visual options during brainstorming. Available as a tool: not a mode. Accepting the companion means it's available for questions that benefit from visual treatment; it does NOT mean every question goes through the browser.

Offering the companion: When you anticipate that upcoming questions will involve visual content (mockups, layouts, diagrams), offer it once for consent:

"Some of what we're working on might be easier to explain if I can show it to you in a web browser. I can put together mockups, diagrams, comparisons, and other visuals as we go. This feature is still new and can be token-intensive. Want to try it? (Requires opening a local URL)"

This offer MUST be its own message. Do not combine it with clarifying questions, context summaries, or any other content. The message should contain ONLY the offer above and nothing else. Wait for the user's response before continuing. If they decline, proceed with text-only brainstorming.

Per-question decision: Even after the user accepts, decide FOR EACH QUESTION whether to use the browser or the terminal. The test: would the user understand this better by seeing it than reading it?

• Use the browser for content that IS visual: mockups, wireframes, layout comparisons, architecture diagrams, side-by-side visual designs
• Use the terminal for content that is text: requirements questions, conceptual choices, tradeoff lists, A/B/C/D text options, scope decisions

A question about a UI topic is not automatically a visual question. "What does personality mean in this context?" is a conceptual question: use the terminal. "Which wizard layout works better?" is a visual question: use the browser.

If they agree to the companion, read the detailed guide before proceeding: skills/brainstorming/visual-companion.md