Nw Jtbd Core logo

Nw Jtbd Core

Organization
nWave-ai
nw-jtbd-core

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

Overview

PublishernWave-ai
RepositorynWave
Skill namenw-jtbd-core
Stars
616
Forks
65
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by nWave-ai on GitHub. Read the source before you install it.

Installation

Install the Nw Jtbd Core AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/nWave-ai/nWave/tree/main/nWave/skills/nw-jtbd-core
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/nWave-ai/nWave.git /tmp/nWave
mkdir -p .claude/skills
cp -r /tmp/nWave/nWave/skills/nw-jtbd-core .claude/skills/nw-jtbd-core
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Nw Jtbd Core in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Nw Jtbd Core on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Nw Jtbd Core is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

JTBD Core Theory

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.

The Three Job Dimensions

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.

  • "Deploy a new feature to production without downtime"
  • "Identify the root cause of a performance regression"

Emotional: How the customer wants to feel (or avoid feeling). Internal, personal, often unarticulated.

  • "Feel confident that my changes will not break production"
  • "Feel in control of the project timeline despite changing requirements"

Social: How the customer wants to be perceived. Identity, status, professional reputation.

  • "Be seen as a technically competent lead who makes sound decisions"
  • "Demonstrate to stakeholders that the team delivers measurable value"

Discovery Questions by Dimension

DimensionQuestions
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 Story Format

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].

Writing Tips

  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)

Worked Example

markdown
## 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

Job Stories vs User Stories

AspectUser StoryJob Story
FormatAs a [persona], I want to [action], so that [benefit]When [situation], I want to [motivation], so I can [outcome]
FocusWho the user isWhat situation triggers the need
AnchoringIdentity/roleContext/circumstance
GroupingUsers grouped by roleUsers grouped by situation
Design driverPersona characteristicsCausality and context

When to Use Each

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.

The Translation Pipeline

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)

Example Translation

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:

  • Test coverage for payment processing module is at least 90%
  • Coverage report highlights any critical paths with less than 80% coverage
  • Deployment is blocked if any critical path has zero test coverage

The 8-Step Universal Job Map

All jobs follow this universal structure (Ulwick). Walk all 8 steps to surface requirements that feature-driven thinking misses.

StepDescriptionDiscovery Question
1. DefineDetermine goals, plan approach, assess resources"What information do users need before starting?"
2. LocateGather necessary inputs, materials, information"Where do users find the data/resources they need?"
3. PrepareSet up environment, organize inputs"What setup or configuration is required?"
4. ConfirmVerify readiness, validate inputs"How do users confirm they have everything?"
5. ExecutePerform the core task"What is the primary action sequence?"
6. MonitorCheck progress, verify results"How do users know if things are working?"
7. ModifyAdjust, handle exceptions, course-correct"What do users do when something goes wrong?"
8. ConcludeFinalize, clean up, assess outcome"How do users wrap up and assess success?"

Worked Example: "Deploy Application to Production"

  1. Define: Determine version to deploy, review change log, assess risk level
  2. Locate: Find correct build artifact, gather deployment config, locate rollback scripts
  3. Prepare: Set up deployment pipeline, configure environment variables, notify stakeholders
  4. Confirm: Run pre-deployment checks, verify build integrity, confirm deployment window
  5. Execute: Trigger deployment, apply database migrations, update routing
  6. Monitor: Watch health checks, verify service responses, check error rates
  7. Modify: Roll back if errors exceed threshold, scale resources, apply hotfix
  8. Conclude: Update deployment log, notify team, archive deployment artifact

Steps 1-4 (Define through Confirm) are where most missing requirements hide. Teams jump straight to Execute without considering the full journey.

Outcome Statements

Express customer needs as measurable, solution-free metrics. Used in opportunity scoring (see jtbd-opportunity-scoring skill).

[Direction] + the [metric] + [object of control] + [contextual clarifier]

Direction: "Minimize" or "Maximize". Metric: time, likelihood, number, or frequency.

Examples

  • "Minimize the time it takes to determine which features are most important"
  • "Minimize the likelihood of overlooking a critical edge case"
  • "Maximize the likelihood that acceptance criteria cover all relevant scenarios"
  • "Minimize the number of iterations needed to reach shared understanding"

Quality Checks for Outcome Statements

  • Solution-free: no reference to specific technology
  • Measurable: can be rated on importance and satisfaction scales
  • Controllable: customer can assess whether the outcome improved
  • Unambiguous: interpreted the same way by all stakeholders

The Four Forces of Progress

For a switch to happen, Push + Pull must exceed Anxiety + Habit. Teams often focus only on Pull (making product attractive) while ignoring Anxiety and Habit reduction.

        PROGRESS (switching happens)
             ^
             |
Push of  ----+---- Pull of New
Current       |     Solution
Situation     |
             |
        NO PROGRESS (staying put)
             ^
             |
Anxiety  ----+---- Habit of
of New        |     Present
Solution      |
  1. Push (demand-generating): Frustration with current solution
  2. Pull (demand-generating): Attractiveness of the alternative
  3. Anxiety (demand-reducing): Fear, risk, learning curve of new solution
  4. Habit (demand-reducing): Familiarity, comfort, sunk costs with current solution

Forces Template

markdown
## Forces Analysis: [Feature/Decision]

### Demand-Generating
- **Push**: [Current frustrations driving change]
- **Pull**: [Attractions of the new solution]

### Demand-Reducing
- **Anxiety**: [Fears about the new approach]
- **Habit**: [Inertia of the current approach]

### Assessment
- Switch likelihood: [High/Medium/Low]
- Key blocker: [Strongest demand-reducing force]
- Key enabler: [Strongest demand-generating force]
- Design implication: [What the product must do to tip the balance]

Cross-References

  • For interview techniques to discover jobs: load jtbd-interviews skill
  • For prioritization using opportunity scoring: load jtbd-opportunity-scoring skill
  • For translating jobs to BDD scenarios: load jtbd-bdd-integration skill
  • For persona-level JTBD analysis: load persona-jtbd-analysis skill
  • For workflow selection by job type: load jtbd-workflow-selection skill

Frequently asked questions

What does the Nw Jtbd Core AI skill do?

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

Why use Nw Jtbd Core on TypingMind?

Because you install it once and use it with any model. Nw Jtbd Core is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Nw Jtbd Core in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/nWave-ai/nWave/tree/main/nWave/skills/nw-jtbd-core. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Nw Jtbd Core?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Nw Jtbd Core?

As many as you like. As long as a model supports skills, you can use Nw Jtbd Core with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Nw Jtbd Core AI skill free?

Yes. It is published on GitHub by nWave-ai under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇