ux-lean-ux

What this skill does

<!-- VERSION: 1.2.0 | DATE: 2026-03-04 | SOURCE: skills/user-experience/SKILL.md | PARENT: /user-experience skill | REVISION: Iter3 quality gate fixes -- ICE attribution correction, H-26 reference normalization, on_receive/on_send inline enumeration, agent table stub marker fix -->

# Lean UX Sub-Skill

> **Version:** 1.2.0
> **Framework:** Jerry User-Experience -- Lean UX
> **Constitutional Compliance:** Jerry Constitution v1.0
> **Parent Skill:** `/user-experience` (`skills/user-experience/SKILL.md`)
> **Wave:** 2 (Data-Ready)
> **Project:** PROJ-022 User Experience Skill | GitHub Issue [#138](https://github.com/geekatron/jerry/issues/138)

## Document Sections

| Section | Purpose |
|---------|---------|
| [Document Audience](#document-audience-triple-lens) | Triple-Lens audience guide |
| [Purpose](#purpose) | Sub-skill overview and key capabilities |
| [When to Use This Sub-Skill](#when-to-use-this-sub-skill) | Activation triggers and scope boundaries |
| [Available Agents](#available-agents) | Single agent with role, model, and output location |
| [P-003 Compliance](#p-003-compliance) | Worker agent hierarchy position |
| [Invoking the Agent](#invoking-the-agent) | Invocation via ux-orchestrator |
| [Methodology](#methodology) | Lean UX Build-Measure-Learn cycles, hypothesis format, ICE prioritization, assumption mapping, experiment types with selection guide |
| [MCP Dependencies](#mcp-dependencies) | Miro REQ with text-based fallback; Figma ENH; Context7 for Lean UX docs |
| [Output Specification](#output-specification) | Output location, L0/L1/L2 structure, required sections |
| [Routing](#routing) | Keywords and lifecycle-stage routing integration |
| [Cross-Framework Integration](#cross-framework-integration) | Handoff from Design Sprint and to HEART Metrics |
| [Synthesis Hypothesis Confidence](#synthesis-hypothesis-confidence) | Confidence classifications for Lean UX outputs |
| [Constitutional Compliance](#constitutional-compliance) | Governing principles and AI-augmented analysis limitations |
| [Registration](#registration) | H-26 parent-routed registration model and AGENTS.md confirmation |
| [Deployment Status](#deployment-status) | Wave 2 stub agent status and implementation timeline |
| [Quick Reference](#quick-reference) | Common workflows and agent selection hints |
| [References](#references) | Full repo-relative paths, requirements traceability, external citations |

## Document Audience (Triple-Lens)

This SKILL.md serves multiple audiences:

| Level | Audience | Sections to Focus On |
|-------|----------|---------------------|
| **L0 (Stakeholder)** | Product managers, designers | [Purpose](#purpose), [When to Use This Sub-Skill](#when-to-use-this-sub-skill), [Quick Reference](#quick-reference) |
| **L1 (Developer)** | Engineers invoking the agent | [Invoking the Agent](#invoking-the-agent), [Methodology](#methodology), [Output Specification](#output-specification) |
| **L2 (Architect)** | Workflow designers, skill maintainers | [Cross-Framework Integration](#cross-framework-integration), [MCP Dependencies](#mcp-dependencies), [Synthesis Hypothesis Confidence](#synthesis-hypothesis-confidence) |

---

## Purpose

The Lean UX sub-skill provides structured, hypothesis-driven design facilitation using Jeff Gothelf and Josh Seiden's Lean UX methodology (3rd edition, 2021). It targets tiny teams (1-5 people) who need to move beyond opinion-based design decisions toward evidence-based iteration through Build-Measure-Learn cycles.

This sub-skill is part of Wave 2 (Data-Ready), meaning it requires Wave 1 completion (at least 1 heuristic evaluation completed AND 1 JTBD job statement used in a product decision) before deployment. It bridges the gap between design evaluation (Wave 1) and quantitative measurement (Wave 2: HEART Metrics) by providing a structured experimentation framework.

### Key Capabilities

- **Hypothesis-Driven Design** -- Structures design decisions as testable hypotheses using the Lean UX format: "We believe [outcome] for [users] if [change] because [evidence]"
- **Assumption Mapping** -- Prioritizes unknowns using the 4-quadrant framework (Known/Unknown x High Risk/Low Risk) to focus experimentation on the highest-risk unknowns first
- **MVP Experiment Design** -- Designs minimum viable experiments (A/B tests, fake door tests, concierge MVP, Wizard of Oz, paper prototypes) with measurable success criteria
- **Validated Learning Documentation** -- Tracks hypothesis outcomes (confirmed/invalidated) with supporting evidence, building an organizational learning log
- **Hypothesis Backlog Management** -- Maintains a prioritized backlog of hypotheses with validation status, enabling systematic iteration across Build-Measure-Learn cycles
- **Build-Measure-Learn Cycle Tracking** -- Coordinates full cycles from hypothesis formulation through experiment execution to learning documentation

> **Source:** Key capabilities derived from parent SKILL.md [skills/user-experience/SKILL.md § Key Capabilities] ("Lean UX Facilitation -- Hypothesis-driven build-measure-learn cycles (Wave 2)") and [skills/user-experience/SKILL.md § Available Agents] ("Lean UX hypothesis and experiment facilitation").

---

## When to Use This Sub-Skill

Activate when:

- Designing or validating a hypothesis about a design change and its expected outcome
- Mapping and prioritizing assumptions about user behavior, value proposition, or implementation feasibility
- Designing an MVP experiment to test a specific hypothesis with measurable outcomes
- Documenting validated learning from completed experiments (hypothesis confirmed or invalidated)
- Managing a backlog of hypotheses through multiple Build-Measure-Learn iterations
- Iterating on an existing design during the "During design" lifecycle stage with a hypothesis-testing approach
- Transitioning from a Design Sprint (Wave 5) into structured iteration cycles

Do NOT use for:

- Evaluating an existing interface against usability heuristics -- use `/ux-heuristic-eval` (Nielsen's 10) instead. Lean UX focuses on forward-looking hypothesis testing, not backward-looking evaluation of existing designs.
- Measuring quantitative UX health metrics -- use `/ux-heart-metrics` (Google GSM) instead. Lean UX produces hypothesis validation status; HEART Metrics produces ongoing measurement baselines.
- Understanding user motivations and jobs -- use `/ux-jtbd` (Jobs-to-Be-Done) instead. Lean UX consumes job statements from JTBD; it does not perform user motivation research.
- Diagnosing why users fail to take a specific action -- use `/ux-behavior-design` (Fogg B=MAP) instead. Lean UX tests hypotheses about changes; behavior design diagnoses existing behavioral bottlenecks.
- Running a full rapid prototyping sprint -- use `/ux-design-sprint` (Design Sprint 2.0) instead. Lean UX operates on individual hypotheses; Design Sprint produces validated prototypes through a multi-day structured process.
- Accessibility compliance auditing -- use `/ux-inclusive-design` (WCAG 2.2) instead.
- Security-focused interface review -- use `/eng-team` instead.
- General research without UX hypothesis focus -- use `/problem-solving` instead.

> **Source:** Routing logic derived from [skills/user-experience/SKILL.md § Lifecycle-Stage Routing] ("During design: Iterating on existing design -> /ux-lean-ux OR /ux-heuristic-eval") and [skills/user-experience/rules/ux-routing-rules.md § Stage Routing Table], [skills/user-experience/rules/ux-routing-rules.md § Common Intent Resolution].

---

## Available Agents

| Agent | Role | Tier | Mode | Model | Output Location |
|-------|------|------|------|-------|-----------------|
| `ux-lean-ux-facilitator` | Lean UX hypothesis and experiment facilitation specialist | T4 | Systematic | Sonnet | `projects/${JERRY_PROJECT}/engagements/{engagement-id}/ux-lean-ux-facilitator-{topic-slug}.md` |

**STUB:** The agent definition file (`skills/ux-lean-ux/agents/ux-lean-ux-facilitator.md`) currently contain