Product design skills

silver-ideate

Generate meaningfully distinct concepts and testable hypotheses grounded in the current problem frame and canonical constraints, then support explicit human selection. Use for divergent product design exploration and hypothesis generation.

Category
Discovery
Status
Experimental
Use when
  • generate distinct concept alternatives for this problem
  • produce testable hypotheses from a problem frame
  • diverge before committing to a design direction
  • pause for explicit concept selection
  • propose alternatives that differ in mechanism, not just visuals
Works on
  • a problem frame (required)
  • optional findings, design principles, and constraints
Produces
  • multiple concepts with distinct mechanisms, assumptions, and tradeoffs, each paired with a falsifiable hypothesis and its cheapest useful test, awaiting explicit human selection with rejected tradeoffs recorded
Requires
node
Works with
Claude Code, Codex, Cursor, OpenCode, Amp, Gemini CLI, GitHub Copilot, VS Code, Claude.ai
Tags
opportunity-mapping, assumption-mapping, product-discovery, hypothesis
Source
thejparsenault/silver-design-framework by JP Arsenault · MIT
Related skills
silver-synthesizesilver-evaluatedesign-negotiationux-research-workflowproduct-discovery

Instructions from SKILL.md

Ideate concepts

Workflow

  1. Pin the current problem frame, evidence, principles, and constraints.
  2. Generate alternatives with distinct mechanisms, assumptions, and tradeoffs.
  3. Express a falsifiable hypothesis and cheapest useful test for each.
  4. Pause for explicit selection; record the choice and rejected tradeoffs.

Run the guarded file operation through the CLI when durable outputs are ready:

.silver/bin/silver invoke --scaffold ideate .
.silver/bin/silver invoke ideate <request.json> .

The scaffold prefills timestamps, provenance, pinned context, required checks, and expected_integrity. Replace every silver-scaffold-placeholder before invoking; the CLI refuses a request that still contains one.

Done

  • Satisfy: concepts-distinct, hypotheses-testable, selection-explicit.
  • Evaluate quality: Alternatives differ in mechanism or product bet, not merely surface treatment.
  • Emit a valid silver/skill-result/v2 record separating execution, acceptance, and downstream readiness.
  • Recommend follow-up skills; never start them automatically.

Boundaries

  • Do not select a direction on the user's behalf when human review is required.
  • Do not evade design-system constraints through visual novelty.

Supporting files

4 more files in this skill's folder. Markdown opens as a page, other text files open as source, and anything else downloads as it is.

Next to SKILL.md2
agents/1
scripts/1

On this page