ux-jtbd

What this skill does

<!-- VERSION: 1.0.0 | DATE: 2026-03-04 | SOURCE: PROJ-022-user-experience-skill/PLAN.md | PARENT: /user-experience skill -->

# JTBD Sub-Skill

> **Version:** 1.0.0
> **Framework:** Jerry User-Experience / Jobs-to-Be-Done
> **Constitutional Compliance:** Jerry Constitution v1.0
> **Parent Skill:** `/user-experience` (`skills/user-experience/SKILL.md`)
> **Project:** PROJ-022 User Experience Skill | Wave 1 (Zero-Dependency)

## Document Sections

| Section | Purpose |
|---------|---------|
| [Document Audience](#document-audience-triple-lens) | Triple-Lens audience guide |
| [Purpose](#purpose) | What `/ux-jtbd` does and key capabilities |
| [When to Use This Sub-Skill](#when-to-use-this-sub-skill) | Activation triggers, routing path, and scope boundaries |
| [Available Agents](#available-agents) | Single agent roster with role, model, and output location |
| [Invoking an Agent](#invoking-an-agent) | Three invocation methods and H-26(c) registration exception |
| [P-003 Compliance](#p-003-compliance) | Worker agent hierarchy position |
| [Methodology](#methodology) | JTBD methodology adapted for AI-augmented research |
| [MCP Integration](#mcp-integration) | MCP dependencies and degraded mode behavior |
| [Output Specification](#output-specification) | Output format, location, and confidence classification |
| [Cross-Framework Integration](#cross-framework-integration) | How JTBD output feeds into other sub-skills |
| [Synthesis Hypothesis Validation](#synthesis-hypothesis-validation) | Confidence gates for AI-synthesized job statements |
| [Constitutional Compliance](#constitutional-compliance) | Governing principles |
| [Quick Reference](#quick-reference) | Common workflows and invocation examples |
| [References](#references) | Full repo-relative paths to all referenced files |

## Document Audience (Triple-Lens)

This SKILL.md serves multiple audiences:

| Level | Audience | Sections to Focus On |
|-------|----------|---------------------|
| **L0 (Stakeholder)** | Product managers, team leads | [Purpose](#purpose), [When to Use This Sub-Skill](#when-to-use-this-sub-skill), [Quick Reference](#quick-reference) |
| **L1 (Developer)** | Engineers invoking the sub-skill | [Methodology](#methodology), [Output Specification](#output-specification), [Available Agents](#available-agents) |
| **L2 (Architect)** | Workflow designers, skill maintainers | [Cross-Framework Integration](#cross-framework-integration), [P-003 Compliance](#p-003-compliance), [Synthesis Hypothesis Validation](#synthesis-hypothesis-validation) |

---

## Purpose

The `/ux-jtbd` sub-skill provides AI-augmented Jobs-to-Be-Done research and analysis for tiny teams (1-5 people) who lack the resources for traditional primary user research. It synthesizes job statements, switch forces, and outcome expectations from secondary research sources, producing structured artifacts that feed into downstream UX sub-skills.

JTBD shifts the team's thinking from "what features should we build?" to "what jobs are users trying to accomplish?" -- enabling demand-side innovation strategy even when direct user access is limited.

### Key Capabilities

- **Job Statement Synthesis** -- Produces structured job statements in the canonical format: "When [situation], I want to [motivation], so I can [expected outcome]"
- **Switch Interview Analysis** -- Applies Moesta/Spiek four forces framework (push, pull, anxiety, habit) to understand why users switch to or abandon products
- **Outcome-Driven Innovation** -- Applies Ulwick's ODI approach to identify underserved and overserved outcomes for innovation opportunity scoring
- **Job Mapping** -- Decomposes complex user jobs into sequential job steps with associated outcome expectations
- **Hiring Criteria Identification** -- Determines the criteria users apply when "hiring" a product for a specific job
- **Competitive Job Analysis** -- Maps how competing products address the same user jobs to identify differentiation opportunities

### AI-Augmented Research Caveat

All JTBD outputs from this sub-skill are synthesized from secondary research (competitive analysis, domain literature, product documentation, analogous contexts) rather than primary user interviews. Synthesis outputs carry **MEDIUM confidence** by default. This means:

- Job statements reflect AI-synthesized patterns from training data, not validated user motivations
- Switch forces are inferred from secondary evidence, not observed in real switch interviews
- All outputs require validation against real user data before informing design decisions

See [Synthesis Hypothesis Validation](#synthesis-hypothesis-validation) for the full confidence gate protocol.

> **Deployment status:** Wave 1 sub-skill. The agent definition (`skills/ux-jtbd/agents/ux-jtbd-analyst.md`) is currently a stub with frontmatter and core identity sections. Full implementation (complete `<methodology>`, `<input>`, `<capabilities>`, `<output>` XML-tagged body sections) is a Wave 1 deliverable of PROJ-022. The methodology documented in this SKILL.md describes the target behavior the agent will execute once fully implemented.

---

## When to Use This Sub-Skill

### Activation Path

This sub-skill is invoked by the `ux-orchestrator` agent via the `/user-experience` parent skill's lifecycle-stage routing. It is NOT invoked directly by users.

**Routing path:** User request reaches `/user-experience` via trigger keywords. The `ux-orchestrator` routes to `/ux-jtbd` when the user's intent matches:

| Stage Category | User Intent | Route |
|---------------|-------------|-------|
| Before design | "Don't know what to build" | `/ux-jtbd` |
| Before design | "Decide what to build" (strategic, defining the problem) | `/ux-jtbd` |
| Any stage | Understand user motivations, map user jobs | `/ux-jtbd` |

Source: `skills/user-experience/rules/ux-routing-rules.md` [Stage Routing Table].

### Trigger Keywords

| Keyword | Specificity |
|---------|------------|
| jobs to be done | Primary |
| JTBD | Primary |
| switch interview | Primary |
| job mapping | Primary |
| user motivation | Primary |
| hiring criteria | Primary |
| user jobs | Primary |
| outcome expectations | Secondary |
| switch forces | Secondary |
| push/pull forces | Secondary |
| demand-side innovation | Secondary |

### Do NOT Use When

| Condition | Use Instead | Why |
|-----------|-------------|-----|
| Prioritizing known features by satisfaction impact | `/ux-kano-model` | Kano classifies known features; JTBD discovers underlying jobs |
| Evaluating an existing design against usability standards | `/ux-heuristic-eval` | Heuristic evaluation assesses design quality, not user motivations |
| Measuring UX metrics after launch | `/ux-heart-metrics` | HEART measures outcomes; JTBD identifies the jobs driving those outcomes |
| Diagnosing why users fail to complete an action | `/ux-behavior-design` | Behavior design (Fogg B=MAP) diagnoses behavioral bottlenecks; JTBD maps the underlying job |
| General research without UX focus | `/problem-solving` | JTBD methodology is UX-specific; general research uses ps-researcher |

---

## Available Agents

| Agent | Role | Tier | Mode | Model | Output Location |
|-------|------|------|------|-------|-----------------|
| `ux-jtbd-analyst` | JTBD research and analysis specialist | T4 | Divergent | Sonnet | `projects/${JERRY_PROJECT}/engagements/{engagement-id}/ux-jtbd-analyst-{topic-slug}.md` |

**Single-agent sub-skill.** The `ux-jtbd-analyst` handles the full JTBD methodology -- from context gathering through job statement synthesis. Complex multi-job engagements are decomposed into multiple invocations by the `ux-orchestrator`, each targeting a specific job domain.

**Tool tier:** T4 (External). The analyst uses WebSearch and WebFetch for secondary research (competitive analysis, domain literature, product reviews) and Context7 for JTBD framework documentation lookup. See `skills/ux-jtbd/agents/ux-jtbd-analyst.md` for the full agent definitio