Nw Leanux Methodology logo

Nw Leanux Methodology

Organization
nWave-ai
nw-leanux-methodology

LeanUX backlog management methodology - user story template, story sizing, story states, task types, Definition of Ready/Done, anti-pattern detection and remediation

Overview

PublishernWave-ai
RepositorynWave
Skill namenw-leanux-methodology
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 Leanux Methodology 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-leanux-methodology
  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-leanux-methodology .claude/skills/nw-leanux-methodology
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Nw Leanux Methodology 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 Leanux Methodology 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 Leanux Methodology 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.

LeanUX Backlog Management Methodology

"A backlog is not a todo list. It's a collection of validated hypotheses waiting to become working software."

Story States

StateMeaningEntry Criteria
DraftIdea captured, not validatedHas problem statement
ReadyValidated, has UAT, ready to buildAll DoR items complete
In ProgressActively being builtUAT test written (RED)
In ReviewCode complete, awaiting reviewAll tests green
DoneMerged, deployed, validatedUAT passes in production
BlockedCannot proceedBlocker documented

Story Sizing Criteria

Right-Sized

Completable in 1-3 days | 3-7 UAT scenarios | Delivers demonstrable value | Explainable in 2 minutes

Oversized Indicators

7 UAT scenarios | >3 days effort | Multiple distinct user outcomes | Cannot demonstrate in single session

Splitting Strategy

Split by user outcome, not technical layer. Each resulting story delivers independently demonstrable value.

Example: "User Management" (20 scenarios) splits into:

  • "Quick Login" (5 scenarios) -- returning customer on trusted device
  • "New Registration" (4 scenarios) -- first-time customer sign-up
  • "Password Recovery" (3 scenarios) -- customer who forgot credentials
  • "Profile Settings" (4 scenarios) -- customer updating preferences

Definition of Ready (DoR) - Hard Gate

Stories pass ALL 8 items before proceeding to DESIGN wave.

Checklist with Pass/Fail Examples

1. Problem statement clear and in domain language

  • Pass: "Maria wastes 30 seconds typing credentials on every visit"
  • Fail: "Users need authentication"

2. User/persona identified with specific characteristics

  • Pass: "Returning customer (2+ orders) on trusted personal device"
  • Fail: "User" or "Customer"

3. At least 3 domain examples with real data

  • Pass: "Maria on her MacBook, last login 5 days ago, goes directly to dashboard"
  • Fail: "User logs in successfully"

4. UAT scenarios in Given/When/Then (3-7 scenarios)

  • Pass: "Given Maria authenticated 5 days ago on 'MacBook-Home'..."
  • Fail: "Test login functionality"

5. Acceptance criteria derived from UAT

  • Pass: "Sessions older than 30 days require re-authentication"
  • Fail: "System should work correctly"

6. Story right-sized (1-3 days, 3-7 scenarios)

  • Pass: "2 days effort, 5 scenarios, single demo-able feature"
  • Fail: "Epic with 20 scenarios"

7. Technical notes identify constraints

  • Pass: "Requires JWT token storage, GDPR cookie consent"
  • Fail: "No technical considerations"

8. Dependencies resolved or tracked

  • Pass: "Depends on US-041 (completed) and Auth service API (available)"
  • Fail: "Unspecified external dependencies"

Validation Output Format

markdown
## Definition of Ready Validation

### Story: {story-id}

| DoR Item | Status | Evidence/Issue |
|----------|--------|----------------|
| Problem statement clear | PASS/FAIL | {evidence or issue} |
| User/persona identified | PASS/FAIL | {evidence or issue} |
| 3+ domain examples | PASS/FAIL | {evidence or issue} |
| UAT scenarios (3-7) | PASS/FAIL | {evidence or issue} |
| AC derived from UAT | PASS/FAIL | {evidence or issue} |
| Right-sized | PASS/FAIL | {evidence or issue} |
| Technical notes | PASS/FAIL | {evidence or issue} |
| Dependencies tracked | PASS/FAIL | {evidence or issue} |

### DoR Status: PASSED / BLOCKED

Failure Recovery

When DoR fails:

  1. Display specific failures with remediation guidance
  2. Do not proceed to peer review or handoff
  3. Return to user with action items
  4. Re-validate after fixes applied

Definition of Done (DoD) - Completion Criteria

DoD validation owned by acceptance-designer during DISTILL->DELIVER transition. Product-owner defines checklist, acceptance-designer enforces.

Checklist:

  • All UAT scenarios pass (green) | All supporting tests pass (unit, integration, component)
  • Code refactored, no obvious debt | Code reviewed and approved
  • Merged to main branch | Deployed to staging/production
  • Story can be demoed to user

Anti-Pattern Detection and Remediation

Implement-X

  • Signal: Task starts with "Implement X" or "Add X"
  • Problem: No user context, technical focus, vague completion
  • Bad: "Implement user authentication"
  • Good: "Returning Customer Quick Login -- Maria wastes 30 seconds..."
  • Fix: Start with user pain point, rewrite as problem statement

Generic Data

  • Signal: Examples use "user123", "test@test.com"
  • Problem: Lacks real-world context, harder to validate
  • Bad: "Given user123 logs in with password123"
  • Good: "Given Maria Santos (maria.santos@email.com) on her MacBook"
  • Fix: Replace all generic data with real names and realistic values

Technical Acceptance Criteria

  • Signal: AC describes implementation ("Use JWT tokens")
  • Problem: Prescribes solution, not testable outcome
  • Bad: "Use JWT tokens for session management"
  • Good: "Session persists for 30 days on trusted device"
  • Fix: Focus on observable user outcome, move tech choices to DESIGN

Oversized Stories

  • Signal: >7 scenarios or >3 days effort
  • Problem: Too large to track, deliver, or demo meaningfully
  • Bad: "Complete user management (20 scenarios)"
  • Good: "Quick Login (5 scenarios), Password Reset (4 scenarios)"
  • Fix: Split into focused stories by user outcome

No Examples

  • Signal: Abstract requirements without concrete examples
  • Problem: Ambiguous, untestable, different interpretations
  • Bad: "Users should be able to manage their settings"
  • Good: "Maria changes notification frequency from daily to weekly"
  • Fix: Add 3+ concrete narratives with real data

Tests After Code

  • Signal: Tests written after implementation
  • Problem: Technical debt, test coverage gaps
  • Fix: UAT scenarios defined in DISCUSS wave, tests written RED first in DELIVER wave

UAT-First Development Flow

Flow from Ready story to Done story follows double-loop TDD:

  1. Write UAT test from scenario: Translate first Gherkin scenario to executable test. Run -> RED (correct).
  2. Build outside-in: What does UAT need? Integration -> RED -> code -> GREEN. What does integration need? Unit -> RED -> code -> GREEN.
  3. Refactor: All tests green, safe to refactor.
  4. Next scenario: Repeat for each UAT scenario. All scenarios green -> Story is DONE.

Story Prioritization

MoSCoW Classification

CategoryMeaningGuideline
Must HaveRequired for MVPWithout this, release has no value
Should HaveImportant for full product valueSignificant value, workaround exists
Could HaveNice-to-have for enhanced experienceDesirable if time/budget allows
Won't HaveDeferred to future releasesAcknowledged, explicitly out of scope

Assign MoSCoW during Phase 2 (CRAFT) when multiple stories emerge from same requirements conversation.

Value/Effort Matrix

Low EffortHigh Effort
High ValueQuick wins -- do firstStrategic investments -- plan carefully
Low ValueFill-ins -- do if time allowsEliminate or defer

Quick wins build momentum and stakeholder confidence. Strategic investments need baseline measurement and roadmap planning (see jtbd-workflow-selection skill).

Risk Identification Checklist

During Phase 4 (HANDOFF), include brief risk assessment. Categorize:

Business Risks: market changes | regulatory changes | stakeholder availability | budget/timeline constraints Technical Risks: integration complexity | technology uncertainty | data migration | performance/security unknowns Project Risks: resource availability | scope creep potential | communication challenges | testing coverage gaps

For each risk: probability (low/medium/high) | impact (low/medium/high) | mitigation approach (avoid, mitigate, transfer, accept). Detailed risk management belongs to downstream waves -- product-owner surfaces risks, does not manage them.

Wave Handoff Package

When handing off to DESIGN wave (solution-architect), include:

  • Structured requirements document with business context
  • User stories with detailed acceptance criteria
  • Stakeholder analysis and engagement plan
  • Business rules and domain model
  • Risk assessment with categorized risks (see checklist above)
  • Non-functional requirements and quality attributes
  • DoR validation results (all PASSED)
  • Peer review approval

Frequently asked questions

What does the Nw Leanux Methodology AI skill do?

LeanUX backlog management methodology - user story template, story sizing, story states, task types, Definition of Ready/Done, anti-pattern detection and remediation

Why use Nw Leanux Methodology on TypingMind?

Because you install it once and use it with any model. Nw Leanux Methodology 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 Leanux Methodology in TypingMind?

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

Which AI models can use Nw Leanux Methodology?

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 Leanux Methodology?

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

Is the Nw Leanux Methodology 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 👇