From discover
Define structural design foundation — information architecture, user flows, content model, brand direction, and AI interaction model — from validated opportunities and hypotheses
npx claudepluginhub shinpr/claude-code-workflows --plugin discoverThis skill uses the workspace's default tool permissions.
**Context**: Create or update structural design artifacts in `docs/product/design/` that provide shared context for prototype generation and downstream UI specification. Blueprint bridges the gap between "what problems to solve" (discovery) and "what the product looks and works like" (prototypes).
Orchestrates interactive workflows to transform fuzzy product/feature ideas into structured development briefs. Adaptive phases handle complexity; generates HTML/CSS visual prototypes.
Orchestrates interactive product/feature design from fuzzy ideas to structured briefs via adaptive phases, collaborative refinement, and HTML/CSS visual prototypes. Use before coding.
Guides pre-design discovery for features, components, or UI: explores problem, users, intent, constraints. Quick mode for POCs; full process for products.
Share bugs, ideas, or general feedback.
Context: Create or update structural design artifacts in docs/product/design/ that provide shared context for prototype generation and downstream UI specification. Blueprint bridges the gap between "what problems to solve" (discovery) and "what the product looks and works like" (prototypes).
Execution Protocol:
[STOP — BLOCKING] marker — present findings and CANNOT proceed until user explicitly confirmsInput (validated opportunities / discovery outputs / strategic update)
↓
1. Context Assessment → Determine scope and mode (create vs. update)
↓
2. MVP Scope Definition → Feature prioritization from validated hypotheses
↓
3. Information Architecture → Page structure, navigation, multi-sided layout [Stop: User confirms IA]
↓
4. Content Model → Entity types, relationships, states
↓
5. Core User Flows → 5-10 primary flows across personas [Stop: User confirms structure]
↓
6. Brand Direction → Visual tone, color/typography direction, reference products
↓
7. AI Interaction Model → Interaction patterns, capability boundaries, guardrails (if applicable) [Stop: User confirms design direction]
↓
Output: docs/product/design/ artifacts
Input: $ARGUMENTS
Read project context to determine scope:
| File | Extract |
|---|---|
docs/product/vision.md | Product vision, design vision, outcomes, NSM, strategic priorities |
docs/product/design-principles.md | Trade-off resolutions that constrain all design decisions |
docs/product/personas/ | All persona files — roles, JTBD, pains, behavioral patterns |
docs/discovery/INDEX.md | Opportunity and hypothesis status overview |
docs/discovery/opportunities/ | Validated opportunities with impact assessment |
docs/discovery/hypotheses/ | Hypothesis status, confidence scores, learnings |
docs/discovery/journeys/ | Journey maps (if available) |
docs/product/learnings.md | Tier 1 learnings from reflection cycles |
Gate: Vision, design principles, and at least one persona file must exist. At least one Opportunity must be identified (draft status is sufficient — validation is not required). If missing → inform user which prerequisite files are needed before proceeding.
| Situation | Mode | Action |
|---|---|---|
No docs/product/design/ exists | Create | Full blueprint definition |
| Blueprint exists, new Opportunities discovered | Update | Extend IA, flows, content model for new scope |
Blueprint exists, new learnings in docs/product/learnings.md | Update | Revise based on new learnings |
| Existing codebase | Create/Update | Invoke codebase-analyzer for current architecture understanding |
Synthesize validated opportunities and hypotheses into a feature scope:
references/mvp-definition.md for MoSCoW/RICE frameworksRecord the scope in the IA artifact header (Step 3).
Use blueprint-standards skill references/ia-template.md to structure the IA:
[STOP — BLOCKING] Present IA to user for confirmation:
CANNOT proceed to Step 4 until user explicitly confirms the IA structure.
Use blueprint-standards skill references/content-model-template.md to define the data structure:
Use blueprint-standards skill references/flow-template.md to define 5-10 primary flows:
Prioritize flows that:
[STOP — BLOCKING] Present content model and user flows to user for confirmation:
CANNOT proceed to Step 6 until user explicitly confirms the structural design.
Use blueprint-standards skill references/brand-direction-template.md to define visual direction:
auto-derived in the templateReference the competitive landscape research (if available in research/) for visual benchmarking.
Note: Design experts can refine Visual Tokens after blueprint completion using
recipe-refine-visuals. The refinement updates the samebrand-direction.mdfile.
Skip this step if the product has no AI-powered features.
Use blueprint-standards skill references/ai-interaction-model-template.md to define:
[STOP — BLOCKING] Present brand direction and AI interaction model to user for confirmation:
CANNOT write files until user explicitly confirms the design direction.
After user approval, write all artifacts to docs/product/design/:
docs/product/design/information-architecture.mddocs/product/design/content-model.mddocs/product/design/brand-direction.mddocs/product/design/ai-interaction-model.md (if applicable)docs/product/design/flows/flow-{name}.md (one file per flow)| Agent | When | Why (context separation benefit) |
|---|---|---|
| codebase-analyzer (via Agent tool, subagent_type: "discover:codebase-analyzer") | Existing codebase exists | Objective assessment of current architecture, routes, and components without hypothesis bias |
Included: Information architecture, user flows, content model, brand direction, AI interaction model, MVP scope synthesis Not included: Opportunity discovery, hypothesis validation, pixel-level design specifications (UI Spec scope), component APIs and final production token values (UI Spec scope), PRD creation
docs/product/design/