discover

Analyzes existing codebase objectively for facts about implementation, user behavior patterns, and technical architecture. Use when existing code needs to be understood without hypothesis bias. Invoked by recipe-discover, recipe-validate, and recipe-persona.

Decomposes hypotheses into testable assumptions, selects test methods, and designs bias-free validation. Use PROACTIVELY during recipe-validate to ensure validation design seeks disconfirming evidence. Context separation is critical for this agent.

Analyzes hypothesis groups to extract cross-cutting patterns, contradictions, and distilled learnings. Use during recipe-reflect for Tier 2/Tier 1 knowledge promotion. Context separation prevents individual hypothesis bias from distorting pattern recognition.

Reviews PRD for quality, completeness, and internal consistency against prd-standards. Use PROACTIVELY after PRD creation in recipe-define. Eliminates author's self-review bias through context separation.

Generates self-contained HTML prototypes for hypothesis validation. Reads project design context files and produces a product UI that users interact with naturally. Context separation ensures prototypes reflect product vision. Invoked by recipe-validate for Usability risk validation.

Defines structural design artifact formats — information architecture, user flows, content model, brand direction, and AI interaction model. Use when creating or reviewing structural design documents that precede prototype generation.

Provides Business Model Canvas, Value Proposition Canvas, and TAM/SAM/SOM market analysis frameworks. Use when assessing Viability risk, sizing markets, mapping value propositions, conducting competitive analysis, or identifying market gaps.

Integrates design principles, WCAG 2.2 AA accessibility, persona context, and state design into product decisions. Use when reviewing UX decisions, checking accessibility, applying design principles, or ensuring state coverage in acceptance criteria.

Manages hypothesis lifecycle, enforces validation criteria, time budgets, and confidence scoring rules. Use when creating hypotheses, updating confidence scores, setting validation criteria, handling timeouts, or recording validation results.

Defines PRD structure, user story format with 4 Risks assessment, EARS-format acceptance criteria, and delivery readiness thresholds. Use when writing PRDs, drafting user stories, defining acceptance criteria, or reviewing PRD quality and completeness.

Defines 4 Risks confidence thresholds, OST hierarchy levels, Knowledge Pyramid tiers, and state design requirements. Use when evaluating user stories, setting confidence scores, referencing OST levels, scoping MVP, or determining validation sufficiency.

Generates self-contained HTML prototypes with design context from project files. Read design principles, personas, and hypothesis files, then produce a working prototype for Usability and Value risk validation. Use when creating prototypes or validating through tangible artifacts.

Define structural design foundation — information architecture, user flows, content model, brand direction, and AI interaction model — from validated opportunities and hypotheses

Orchestrate PRD creation from validated hypotheses — standard PRD output with 4 Risks confidence and hypothesis traceability

Orchestrate Opportunity discovery and hypothesis generation through business and user perspectives

Create or update personas with demographic, contextual, JTBD, and behavioral data

Optional side-workflow for design experts to refine auto-derived Visual Tokens in brand-direction.md with professional judgment

Orchestrate structured reflection — update target artifacts with learnings, distill knowledge across hypotheses, and maintain INDEX.md

Orchestrate hypothesis validation through type-appropriate methods — prototypes, code analysis, market research, and expert review

Define or update product vision, strategy, outcomes, and NSM