/discuss

description: "Conducts Jobs-to-be-Done analysis, UX journey design, and requirements gathering through interactive discovery. Use when starting feature analysis, defining user stories, or creating acceptance criteria."
argument-hint: "[feature-name] - Optional: --phase=[jtbd|journey|requirements] --interactive=[high|moderate] --output-format=[md|yaml]"

NW-DISCUSS: Jobs-to-be-Done Analysis, UX Journey Design, and Requirements Gathering

**Wave**: DISCUSS (wave 2 of 6) | **Agent**: Luna (nw-product-owner) | **Command**: `/nw-discuss`

Overview

Execute DISCUSS wave through Luna's integrated workflow: JTBD analysis|UX journey discovery|emotional arc design|shared artifact tracking|requirements gathering|user story creation|acceptance criteria definition. Luna uncovers jobs users accomplish, maps to journeys and requirements, handles complete lifecycle from user motivations through DoR-validated stories ready for DESIGN. Establishes ATDD foundation.

For greenfield projects (no src/ code, no docs/feature/ history), Luna proposes Walking Skeleton as Feature 0.

Interactive Decision Points

Decision 1: Feature Type

**Question**: What type of feature is this? **Options**: 1. User-facing -- UI/UX functionality visible to end users 2. Backend -- APIs, services, data processing 3. Infrastructure -- DevOps, CI/CD, tooling 4. Cross-cutting -- Spans multiple layers (auth, logging, etc.) 5. Other -- user provides custom input

Decision 2: Walking Skeleton

**Question**: Should we start with a walking skeleton? **Options**: 1. Yes -- recommended for greenfield projects 2. Depends -- brownfield; Luna evaluates existing structure first 3. No -- feature is isolated enough to skip

Decision 3: UX Research Depth

**Question**: Priority for UX research depth? **Options**: 1. Lightweight -- quick journey map, focus on happy path 2. Comprehensive -- full experience mapping with emotional arcs 3. Deep-dive -- extensive user research, multiple personas, edge cases

Prior Wave Consultation

Before beginning DISCUSS work, read SSOT and prior wave artifacts:

1. **SSOT** (if `docs/product/` exists):

• `docs/product/journeys/{name}.yaml` — existing journey to extend (if applicable)
• `docs/product/jobs.yaml` — validated jobs and opportunity scores
• `docs/product/vision.md` — product vision

2. **Project context**: `docs/project-brief.md` | `docs/stakeholders.yaml` 3. **DISCOVER artifacts**: Read `docs/feature/{feature-id}/discover/` (if present) 4. **DIVERGE artifacts**: Read `docs/feature/{feature-id}/diverge/` (if present)

• `recommendation.md` is the primary input — the selected design direction and job statement
• `job-analysis.md` — validated JTBD job statements and ODI outcome statements — use directly, do not re-run JTBD analysis

DISCUSS is the convergence wave — it takes the direction from DIVERGE (or a direct decision) and transforms it into UX journeys and testable requirements.

If `docs/product/` does not exist, this is the first feature using the SSOT model. DISCUSS will create it (see SSOT Update below).

**READING ENFORCEMENT**: You MUST read every file listed in Prior Wave Consultation above using the Read tool before proceeding. After reading, output a confirmation checklist (`✓ {file}` for each read, `⊘ {file} (not found)` for missing). Do NOT skip files that exist — skipping causes requirements disconnected from evidence.

After reading, check whether any DISCUSS decisions would contradict DISCOVER evidence. Flag contradictions and resolve with user before proceeding. Example: DISCOVER found "users don't want automation" but DISCUSS story assumes "automated workflow" — this must be resolved.

Document Update (Back-Propagation)

When DISCUSS decisions change assumptions established in DISCOVER: 1. Document the change in a `## Changed Assumptions` section at the end of the affected DISCUSS artifact 2. Reference the original DISCOVER document and quote the original assumption 3. State the new assumption and the rationale for the change 4. Do NOT modify DISCOVER documents directly — they represent historical evidence

Agent Invocation

@nw-product-owner

IF DIVERGE artifacts present (`docs/feature/{feature-id}/diverge/recommendation.md` exists): Read `recommendation.md` and `job-analysis.md` to ground journey design|execute *journey for {feature-id} informed by DIVERGE direction|then *story-map|then *gather-requirements with outcome KPIs. ELSE: Execute *journey for {feature-id}|then *story-map|then *gather-requirements with outcome KPIs.

Context files: see Prior Wave Consultation above + project context files.

**Configuration:**

• format: visual | yaml | gherkin | all (default: all)
• research_depth: {Decision 3} | interactive: high | output_format: markdown
• elicitation_depth: comprehensive | feature_type: {Decision 1}
• walking_skeleton: {Decision 2}
• output_directory: docs/feature/{feature-id}/discuss/

**Phase 1 -- Job Grounding (from DIVERGE artifacts):**

If DIVERGE artifacts are present, read `recommendation.md` and `job-analysis.md` before any journey work. Extract: the selected design direction|the validated job statement|ODI outcome statements. These ground all subsequent journey and story work — every story must trace to the job from DIVERGE.

If no DIVERGE artifacts: journey design proceeds without a pre-validated job. Note this as a risk in `wave-decisions.md`.

**Phase 2 -- Journey Design:**

Luna runs deep discovery (mental model|emotional arc|shared artifacts|error paths) informed by JTBD, produces visual journey + YAML schema + Gherkin scenarios. Each journey maps to one or more identified jobs.

| Artifact | Path | |----------|------| | Visual Journey | `docs/feature/{feature-id}/discuss/journey-{name}-visual.md` | | Journey Schema | `docs/feature/{feature-id}/discuss/journey-{name}.yaml` (includes Gherkin per step — DISTILL extracts at wave start) | | Artifact Registry | `docs/feature/{feature-id}/discuss/shared-artifacts-r