/diverge
Generates 3-5 divergent design directions through JTBD analysis, competitive research, structured brainstorming, and taste evaluation before convergence.
> /plugin marketplace add nWave-ai/nWave > /plugin install nw@nwave-marketplace
How it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/diverge
Context preview
What this command does when you run it.
Generates 3-5 divergent design directions through JTBD analysis, competitive research, structured brainstorming, and taste evaluation before convergence.
Command definition
diverge.mddescription: "Generates 3-5 divergent design directions through JTBD analysis, competitive research, structured brainstorming, and taste evaluation before convergence."
argument-hint: "[feature-id] - Optional: --work-type=[new-product|brownfield|pivot]"
NW-DIVERGER: Structured Divergent Thinking Before Convergence
**Wave**: DIVERGE (between DISCOVER and DISCUSS, optional) | **Agent**: Flux (nw-diverger) | **Command**: `/nw-diverger`
Overview
Execute DIVERGE wave through Flux's 4-phase workflow: JTBD analysis|competitive research|structured brainstorming|taste-filtered evaluation. Transforms a validated problem into 3-5 concrete, taste-scored design directions so DISCUSS can converge on one with confidence.
DIVERGE is optional. Brownfield features with a clear direction may skip it (see skip checklist in design spec). New products and pivot decisions benefit most from structured divergence.
Interactive Decision Points
Decision 1: Work Type
**Question**: What type of work is this? **Options**: 1. New product -- no prior solution exists, full divergence needed 2. Brownfield feature -- existing product, exploring approach alternatives 3. Pivot / redesign -- existing feature being reconsidered from scratch 4. Other -- user provides custom context
Decision 2: Research Depth
**Question**: How deep should competitive research go? **Options**: 1. Lightweight -- 3 competitors, known market 2. Comprehensive -- 5+ competitors including non-obvious alternatives 3. Deep-dive -- cross-category research, adjacent markets, academic references
Prior Wave Consultation
Before beginning DIVERGE work, read SSOT and prior wave artifacts:
1. **SSOT** (if `docs/product/` exists):
- `docs/product/jobs.yaml` -- validated jobs and opportunity scores
- `docs/product/vision.md` -- product vision and strategic context
2. **Project context**: `docs/project-brief.md` | `docs/stakeholders.yaml` (if available) 3. **DISCOVER artifacts**: Read `docs/feature/{feature-id}/discover/` (if present)
- `wave-decisions.md` -- validated assumptions and key decisions
- `problem-validation.md` -- customer evidence grounding the problem
If `docs/product/` does not exist, this is the first wave using the SSOT model. DIVERGE will create it (bootstrap `docs/product/jobs.yaml` with the validated job).
**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. Do NOT skip files that exist -- skipping causes options disconnected from evidence.
Agent Invocation
@nw-diverger
Execute \*diverge for {feature-id}.
**Context Files:** see Prior Wave Consultation above + project context files.
**Configuration:**
- work_type: {Decision 1}
- research_depth: {Decision 2}
- output_directory: docs/feature/{feature-id}/
**SKILL_LOADING**: Before starting work, load your skill files using the Read tool from `~/.claude/skills/nw-{skill-name}/SKILL.md`. Skills encode your methodology -- without them you operate with generic knowledge only.
**Phase 1 -- JTBD Analysis:** Flux loads `jtbd-analysis` skill. Extracts and elevates the job from the raw request or DISCOVER evidence. Produces job statements (functional + emotional + social) and ODI outcome statements. Gate G1 validates job level and ODI minimum.
**Phase 2 -- Competitive Research:** Flux invokes `nw-researcher` sub-agent for evidence-grounded competitive research. Maps how existing products serve the validated job. Identifies non-obvious alternatives. Gate G2 validates real products named and evidence quality.
**Phase 3 -- Brainstorming:** Flux loads `brainstorming` skill. Frames HMW question, applies SCAMPER lenses, generates structurally diverse options. Gate G3 validates diversity (mechanism|assumption|cost differ).
**Phase 4 -- Taste Evaluation:** Flux loads `taste-evaluation` skill. Applies DVF filter, scores surviving options on 4 taste criteria with locked weights, produces weighted ranking and recommendation with dissenting case. Gate G4 validates completeness and traceability.
**Peer Review:** After Phase 4 gates pass, Flux invokes `nw-diverger-reviewer` (Prism) to validate all 5 dimensions. Max 2 revision iterations before handoff.
Progress Tracking
The invoked agent MUST create a task list from its workflow phases at the start of execution using TaskCreate. Each phase becomes a task with the gate condition as completion criterion. Mark tasks in_progress when starting each phase and completed when the gate passes. This gives the user real-time visibility into progress.
Success Criteria
- [ ] Job extracted at strategic or physical level (not tactical, not a feature description)
- [ ] Minimum 3 ODI outcome statements produced
- [ ] 3+ real competitors researched, at least one non-obvious alternative
- [ ] 6 structurally diverse options generated (different mechanism, assumption, cost)
- [ ] All surviving options scored on all 4 taste criteria with locked weights
- [ ] Recommendation traceable to scoring matrix (no "feels right" overrides)
- [ ] Dissenting case documented for second-place option
- [ ] Peer review approved by nw-diverger-reviewer
- [ ] Handoff accepted by nw-product-owner (DISCUSS wave)
Next Wave
**Handoff To**: nw-product-owner (DISCUSS wave) **Deliverables**: `recommendation.md` with explicit decision statement + supporting DIVERGE artifacts
Wave Decisions Summary
Before completing DIVERGE, produce (or append to) `docs/feature/{feature-id}/wave-decisions.md`:
# DIVERGE Decisions -- {feature-id}
## Key Decisions
- [D1] {decision}: {rationale} (see: {source-file})
## Job Summary
- Validated job: {job statement at strategic/physical level}
- ODI outcomes: {count} outcome statements
## Options Evaluated
- {count} options generated, {count} survived DVF filter
- Recommended: {option name} -- {one-line rationale}
- Dissent: {second-place option} -- {why it might be betRead more
description: "Generates 3-5 divergent design directions through JTBD analysis, competitive research, structured brainstorming, and taste evaluation before convergence." argument-hint: "[feature-id] - Optional: --work-type=[new-product|brownfield|pivot]"
NW-DIVERGER: Structured Divergent Thinking Before Convergence
**Wave**: DIVERGE (between DISCOVER and DISCUSS, optional) | **Agent**: Flux (nw-diverger) | **Command**: `/nw-diverger`
Overview
Execute DIVERGE wave through Flux's 4-phase workflow: JTBD analysis|competitive research|structured brainstorming|taste-filtered evaluation. Transforms a validated problem into 3-5 concrete, taste-scored design directions so DISCUSS can converge on one with confidence.
DIVERGE is optional. Brownfield features with a clear direction may skip it (see skip checklist in design spec). New products and pivot decisions benefit most from structured divergence.
Interactive Decision Points
Decision 1: Work Type
**Question**: What type of work is this? **Options**: 1. New product -- no prior solution exists, full divergence needed 2. Brownfield feature -- existing product, exploring approach alternatives 3. Pivot / redesign -- existing feature being reconsidered from scratch 4. Other -- user provides custom context
Decision 2: Research Depth
**Question**: How deep should competitive research go? **Options**: 1. Lightweight -- 3 competitors, known market 2. Comprehensive -- 5+ competitors including non-obvious alternatives 3. Deep-dive -- cross-category research, adjacent markets, academic references
Prior Wave Consultation
Before beginning DIVERGE work, read SSOT and prior wave artifacts:
1. **SSOT** (if `docs/product/` exists):
- `docs/product/jobs.yaml` -- validated jobs and opportunity scores
- `docs/product/vision.md` -- product vision and strategic context
2. **Project context**: `docs/project-brief.md` | `docs/stakeholders.yaml` (if available) 3. **DISCOVER artifacts**: Read `docs/feature/{feature-id}/discover/` (if present)
- `wave-decisions.md` -- validated assumptions and key decisions
- `problem-validation.md` -- customer evidence grounding the problem
If `docs/product/` does not exist, this is the first wave using the SSOT model. DIVERGE will create it (bootstrap `docs/product/jobs.yaml` with the validated job).
**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. Do NOT skip files that exist -- skipping causes options disconnected from evidence.
Agent Invocation
@nw-diverger
Execute \*diverge for {feature-id}.
**Context Files:** see Prior Wave Consultation above + project context files.
**Configuration:**
- work_type: {Decision 1}
- research_depth: {Decision 2}
- output_directory: docs/feature/{feature-id}/
**SKILL_LOADING**: Before starting work, load your skill files using the Read tool from `~/.claude/skills/nw-{skill-name}/SKILL.md`. Skills encode your methodology -- without them you operate with generic knowledge only.
**Phase 1 -- JTBD Analysis:** Flux loads `jtbd-analysis` skill. Extracts and elevates the job from the raw request or DISCOVER evidence. Produces job statements (functional + emotional + social) and ODI outcome statements. Gate G1 validates job level and ODI minimum.
**Phase 2 -- Competitive Research:** Flux invokes `nw-researcher` sub-agent for evidence-grounded competitive research. Maps how existing products serve the validated job. Identifies non-obvious alternatives. Gate G2 validates real products named and evidence quality.
**Phase 3 -- Brainstorming:** Flux loads `brainstorming` skill. Frames HMW question, applies SCAMPER lenses, generates structurally diverse options. Gate G3 validates diversity (mechanism|assumption|cost differ).
**Phase 4 -- Taste Evaluation:** Flux loads `taste-evaluation` skill. Applies DVF filter, scores surviving options on 4 taste criteria with locked weights, produces weighted ranking and recommendation with dissenting case. Gate G4 validates completeness and traceability.
**Peer Review:** After Phase 4 gates pass, Flux invokes `nw-diverger-reviewer` (Prism) to validate all 5 dimensions. Max 2 revision iterations before handoff.
Progress Tracking
The invoked agent MUST create a task list from its workflow phases at the start of execution using TaskCreate. Each phase becomes a task with the gate condition as completion criterion. Mark tasks in_progress when starting each phase and completed when the gate passes. This gives the user real-time visibility into progress.
Success Criteria
- [ ] Job extracted at strategic or physical level (not tactical, not a feature description)
- [ ] Minimum 3 ODI outcome statements produced
- [ ] 3+ real competitors researched, at least one non-obvious alternative
- [ ] 6 structurally diverse options generated (different mechanism, assumption, cost)
- [ ] All surviving options scored on all 4 taste criteria with locked weights
- [ ] Recommendation traceable to scoring matrix (no "feels right" overrides)
- [ ] Dissenting case documented for second-place option
- [ ] Peer review approved by nw-diverger-reviewer
- [ ] Handoff accepted by nw-product-owner (DISCUSS wave)
Next Wave
**Handoff To**: nw-product-owner (DISCUSS wave) **Deliverables**: `recommendation.md` with explicit decision statement + supporting DIVERGE artifacts
Wave Decisions Summary
Before completing DIVERGE, produce (or append to) `docs/feature/{feature-id}/wave-decisions.md`:
# DIVERGE Decisions -- {feature-id}
## Key Decisions
- [D1] {decision}: {rationale} (see: {source-file})
## Job Summary
- Validated job: {job statement at strategic/physical level}
- ODI outcomes: {count} outcome statements
## Options Evaluated
- {count} options generated, {count} survived DVF filter
- Recommended: {option name} -- {one-line rationale}
- Dissent: {second-place option} -- {why it might be betAI agents that guide you from idea to working code, with human judgment at every gate. nWave runs inside Claude Code. It breaks feature delivery into seven waves (discover, diverge, discuss, design, devops, distill, deliver).
Repo: nWave-ai/nWave
Other commands on nwave.
- /buddy
nWave concierge โ ask any question about methodology, project state, commands, migration, or troubleshooting. Read-only, contextual answers.
Open command - /bugfix
Bug fix workflow: root cause analysis โ user review โ regression test + fix via TDD
Open command - /continue
Detects current wave progress for a feature and resumes at the next step. Scans docs/feature/ for artifacts.
Open command - /deliver
Orchestrates the full DELIVER wave end-to-end (roadmap > execute-all > finalize). Use when all prior waves are complete and the feature is ready for implementation.
Open command - /design
Designs system architecture with C4 diagrams and technology selection. Use when defining component boundaries, choosing tech stacks, or creating architecture documents.
Open command - /devops
Designs CI/CD pipelines, infrastructure, observability, and deployment strategy. Use when preparing platform readiness for a feature.
Open command

