ux-behavior-design

What this skill does

<!-- VERSION: 1.5.0 | DATE: 2026-03-04 | SOURCE: skills/user-experience/SKILL.md | PARENT: /user-experience skill | REVISION: iter6 — fix inline citation at line 364 from Chapter 3 to Chapters 14-15 for behavior statement format, resolving contradiction with References table -->

# Behavior Design Sub-Skill

> **Version:** 1.5.0
> **Framework:** Jerry User-Experience -- Behavior Design
> **Constitutional Compliance:** Jerry Constitution v1.0
> **Parent Skill:** `/user-experience` (`skills/user-experience/SKILL.md`)
> **Wave:** 4 (Advanced Analytics)
> **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) | Fogg B=MAP framework, factor analysis, bottleneck identification, intervention design, 5-phase execution procedure |
| [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 heuristic evaluation and to HEART metrics |
| [Synthesis Hypothesis Confidence](#synthesis-hypothesis-confidence) | Confidence classifications for Behavior Design outputs |
| [Quality Gate Integration](#quality-gate-integration) | S-014 scoring and H-13 threshold enforcement |
| [Degraded Mode Behavior](#degraded-mode-behavior) | Operation without real-time behavioral data |
| [Wave Architecture](#wave-architecture) | Wave 4 entry criteria, bypass conditions |
| [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 4 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), [Synthesis Hypothesis Confidence](#synthesis-hypothesis-confidence), [Degraded Mode Behavior](#degraded-mode-behavior) |

---

## Purpose

The Behavior Design sub-skill provides structured behavioral bottleneck diagnosis using BJ Fogg's Behavior Model, commonly expressed as B=MAP: Behavior happens when Motivation, Ability, and a Prompt converge at the same moment (Fogg, 2009; Fogg, 2020). It targets tiny teams (1-5 people) who observe users failing to complete desired actions and need a systematic framework to identify which behavioral factor is the limiting constraint.

This sub-skill is part of Wave 4 (Advanced Analytics), requiring Wave 3 completion before deployment. It bridges design system construction (Wave 3) and process-intensive activities (Wave 5) by providing behavioral insight that explains why well-designed interfaces still fail to drive target user actions.

### Key Capabilities

- **B=MAP Factor Assessment** -- Systematically evaluates each of the three behavioral factors (Motivation, Ability, Prompt) for a target behavior, determining whether each factor is above or below the action threshold (Fogg, 2020)
- **Motivation Analysis** -- Analyzes intrinsic motivators (sensation, anticipation, belonging), extrinsic motivators (rewards, punishments, social proof), and social drivers (competition, collaboration, recognition) that influence user willingness to act
- **Ability Analysis** -- Evaluates the six Fogg simplicity factors (Time, Money, Physical Effort, Brain Cycles, Social Deviance, Non-Routine) to identify friction points that make the target behavior too difficult (Fogg, 2009)
- **Prompt Analysis** -- Classifies prompts into three types (Facilitator, Signal, Spark) and assesses whether the right prompt type is deployed at the right moment for the user's motivation-ability state (Fogg, 2009)
- **Bottleneck Identification** -- Determines which single factor (or combination) is the primary constraint preventing the target behavior, using a structured elimination algorithm
- **Intervention Design** -- Recommends targeted interventions that address the diagnosed bottleneck: motivation interventions for low-motivation bottlenecks, simplification for low-ability bottlenecks, or prompt redesign for missing/mistimed prompts

---

## When to Use This Sub-Skill

Activate when:

- Users are not completing a specific desired action and the team needs to understand why
- Diagnosing whether user inaction stems from insufficient motivation, excessive difficulty, or absent/mistimed prompts
- Analyzing post-launch behavioral data showing low conversion, abandonment, or incomplete task flows
- Designing behavior change interventions targeted at a specific bottleneck factor
- Investigating why a well-designed interface fails to drive the intended user action
- Providing behavioral root-cause analysis for urgent UX problems (CRISIS mode step 2)
- Evaluating whether a proposed feature change addresses the correct behavioral bottleneck
- Preparing behavioral diagnosis to feed into HEART metrics measurement

Do NOT use for:

- Evaluating an existing interface against usability heuristics -- use `/ux-heuristic-eval` (Nielsen's 10) instead. Use heuristic evaluation first, then Behavior Design to trace severe issues to behavioral root causes.
- Building or auditing a component library -- use `/ux-atomic-design` (Atomic Design) instead.
- Accessibility compliance auditing -- use `/ux-inclusive-design` (WCAG 2.2) instead.
- Measuring quantitative UX health metrics -- use `/ux-heart-metrics` (Google GSM) instead. Use Behavior Design first to diagnose, then HEART to measure improvement.
- Understanding user motivations at the job level -- use `/ux-jtbd` (Jobs-to-Be-Done) instead. JTBD identifies what users want; Behavior Design diagnoses why they fail to complete a specific action.
- Testing hypotheses about design changes -- use `/ux-lean-ux` (Lean UX) instead.
- Running a full rapid prototyping sprint -- use `/ux-design-sprint` (Design Sprint 2.0) instead.
- Prioritizing features by user satisfaction impact -- use `/ux-kano-model` (Kano) instead.
- Security-focused interface review -- use `/eng-team` instead.
- General research without behavioral UX focus -- use `/problem-solving` instead.

---

## Available Agents

| Agent | Role | Tier | Mode | Model | Output Location |
|-------|------|------|------|-------|-----------------|
| `ux-behavior-diagnostician` | Fogg B=MAP behavior bottleneck diagnostician | T2 | Convergent | Sonnet | `projects/${JERRY_PROJECT}/engagements/{engagement-id}/ux-behavior-diagnostician-{topic-slug}.md` |

**STUB:** The agent definition file (`skills/ux-behavior-design/agents/ux-behavior-diagnostician.md`) is pending Wave 4 Phase 2