nw-ab-critique-dimensi…
Review dimensions for validating agent quality - template compliance, safety, testing, and priority validation
Core JTBD theory and job story format - job dimensions, job story template, job stories vs user stories, 8-step universal job map, outcome statements, and forces of progress
$ npx -y skills add nWave-ai/nWave --skill nw-jtbd-core --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/nw-jtbd-coreContext preview
The summary Claude sees to decide when to auto-load this skill.
Core JTBD theory and job story format - job dimensions, job story template, job stories vs user stories, 8-step universal job map, outcome statements, and forces of progress
name: nw-jtbd-core description: Core JTBD theory and job story format - job dimensions, job story template, job stories vs user stories, 8-step universal job map, outcome statements, and forces of progress user-invocable: false disable-model-invocation: true
Jobs-to-be-Done reframes product development around the progress customers seek rather than products they buy. Customers "hire" products to accomplish specific jobs. The job exists independently of any solution.
Every job has three dimensions. Capture all three during discovery -- functional jobs surface first, but emotional and social jobs drive switching decisions.
**Functional**: Practical task to accomplish. Measurable, concrete, articulated first.
**Emotional**: How the customer wants to feel (or avoid feeling). Internal, personal, often unarticulated.
**Social**: How the customer wants to be perceived. Identity, status, professional reputation.
| Dimension | Questions | |-----------|-----------| | Functional | "What were you trying to accomplish?" / "Walk me through what you did." | | Emotional | "How did that make you feel?" / "What were you worried about?" | | Social | "Who else was involved or affected?" / "What would others think?" |
Job stories emphasize situation and motivation rather than persona and action.
When [situation/context], I want to [motivation/capability], so I can [expected outcome/benefit].
1. **Refine situation with context**: "When I am nearly done with a document" beats "When I want to save a document" 2. **Focus on job, not task**: Job is the higher-level goal; task is one possible way to achieve it 3. **Specify motivation, not implementation**: "I want to be confident my work is saved" not "I want a save button" 4. **Leave design space open**: Job stories do not prescribe solutions 5. **Reveal the forces**: Story should hint at push (frustration), pull (desire), anxiety (risk), habit (comfort)
## Job Story: Confident Production Deployment **When** I am about to deploy a feature that touches payment processing, **I want to** validate that all critical paths are covered by tests, **so I can** deploy with confidence that revenue-generating flows will not break. ### Functional Job Verify test coverage for critical business paths before deployment. ### Emotional Job Feel confident and in control during high-stakes deployments. ### Social Job Be trusted by the team as someone who ships reliably without causing incidents. ### Forces Analysis - **Push**: Recent deployment broke checkout flow, causing revenue loss - **Pull**: Automated coverage report would eliminate manual checking - **Anxiety**: Will the coverage tool flag false negatives? - **Habit**: Currently eyeballing test files manually before each deploy
| Aspect | User Story | Job Story | |--------|-----------|-----------| | Format | As a [persona], I want to [action], so that [benefit] | When [situation], I want to [motivation], so I can [outcome] | | Focus | Who the user is | What situation triggers the need | | Anchoring | Identity/role | Context/circumstance | | Grouping | Users grouped by role | Users grouped by situation | | Design driver | Persona characteristics | Causality and context |
**Use job stories when**: defining product strategy | discovering new opportunities | early-stage requirements without established personas | same job applies across multiple roles
**Use user stories when**: detailed implementation planning with known personas | clear scope boundaries needed | tracking sprint backlog | stakeholders think in user profiles
**Use both together**: Job stories for strategic discovery, user stories for implementation. Job story reveals the *why*; user story captures the *what to build*.
Job Statement (strategic, solution-agnostic)
|
v
Job Story (contextual, situation-driven)
|
v
User Story (implementable, persona-driven)
|
v
Acceptance Criteria (testable conditions)
|
v
BDD Scenario (automatable Given-When-Then)**Job Statement**: "Help me manage deployment risk when releasing new features"
**Job Story**: "When I am about to deploy a feature that touches payment processing, I want to validate that all critical paths are covered by tests, so I can deploy with confidence."
**User Story**: "As a developer deploying to production, I want to see a test coverage report for critical paths before deployment, so that I can verify all revenue-critical flows are tested."
**Acceptance Criteria**:
All jobs follow this universal structure (Ulwick). Walk all 8 steps to surface requirements that feature-driven thinking misses.
| Step | Description | Discovery Question | |------|-------------|-------------------| | 1. **Define** | Determine goals, plan approach, assess resources | "What information do users need before starting?" | | 2. **Locate** | Gather necessary inputs, materials, information | "Where do users find the data/resources they need?" | | 3. **Prepare** | Set up environment, organize inputs | "What setup or configuration is required?" | | 4. **Confirm** | Verify readiness,
AI 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
Review dimensions for validating agent quality - template compliance, safety, testing, and priority validation
Review dimensions for validating agent quality - template compliance, safety, testing, and priority validation
Review dimensions for acceptance test quality - happy path bias, GWT compliance, business language purity, coverage completeness, walking skeleton…
Detailed 5-phase workflow for creating agents - from requirements analysis through validation and iterative refinement
5-layer testing approach for agent validation including adversarial testing, security validation, and prompt injection resistance
Architectural style selection decision matrices, trade-off analysis, structural enforcement rules, and combination patterns. Load when choosing or evaluating…