nw-new
Guided wizard to start a new feature. Asks what you want to build, recommends the right starting wave, and launches it.
Best use case
nw-new is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Guided wizard to start a new feature. Asks what you want to build, recommends the right starting wave, and launches it.
Teams using nw-new should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/nw-new/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How nw-new Compares
| Feature / Agent | nw-new | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Guided wizard to start a new feature. Asks what you want to build, recommends the right starting wave, and launches it.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# NW-NEW: Start a New Feature
**Wave**: CROSS_WAVE (entry point)
**Agent**: Main Instance (self — wizard)
**Command**: `/nw-new`
## Overview
Conversational wizard that asks the user to describe their feature|classifies it|recommends a starting wave|launches it. Eliminates need to understand the 6-wave pipeline before using nWave.
You (the main Claude instance) run this wizard directly. No subagent delegation.
## Behavior Flow
### Step 1: Feature Description Intake
Ask the user to describe what they want to build. If provided as argument, use that.
If vague (fewer than 3 meaningful words or unclassifiable):
- Ask: **What system** is being changed?
- Ask: **What problem** are you solving?
- Ask: **Who benefits** from this change?
- Provide example: "Add rate limiting to prevent API abuse"
Do NOT proceed until you have a clear, actionable description.
### Step 2: Feature ID Derivation
Derive feature ID per rules in `~/.claude/nWave/skills/common/wizard-shared-rules.md` (section: Feature ID Derivation).
Examples: "Add rate limiting to the API gateway" -> `rate-limiting-api-gateway` | "OAuth2 upgrade" -> `oauth2-upgrade` | "Implement a real-time notification system with WebSocket support for mobile and desktop clients" -> `real-time-notification-system-websocket`
Show derived ID via AskUserQuestion. Allow override with custom value.
### Step 3: Name Conflict Check
Check if `docs/feature/{feature-id}/` exists. If so, offer via AskUserQuestion:
1. **Continue that project** — switch to `/nw-continue`
2. **Start fresh with different name** — ask for distinguishing name
3. **Archive and restart** — move to `docs/feature/{feature-id}-archived-{date}/`
### Step 4: Clarifying Questions
Use AskUserQuestion:
**Q1: New or existing behavior?**
- New functionality that doesn't exist yet
- Changing/improving existing functionality
- Fixing a bug or regression
**Q2: Requirements readiness?**
- Clear requirements in my head but nothing written
- Rough idea, need to explore further
- Haven't validated whether problem is worth solving
### Step 5: Feature Classification
Based on description and answers, classify:
- **User-facing** — UI/UX visible to end users
- **Backend** — APIs, services, data processing
- **Infrastructure** — DevOps, CI/CD, tooling
- **Cross-cutting** — Spans multiple layers (auth, logging, etc.)
Show classification for user confirmation.
### Step 6: Greenfield vs Brownfield Detection
Scan filesystem:
- Check if `src/` or equivalent has code
- Check if `docs/feature/` has prior feature directories
- Check for existing test directories
No source code and no prior features -> **greenfield** | Otherwise -> **brownfield**
### Step 7: Wave Recommendation
Decision tree:
```
IF "fixing a bug":
-> /nw-root-why ("Investigate the root cause first")
IF "haven't validated the problem":
-> /nw-discover ("Validate the problem space before building")
IF "rough idea, need to explore":
-> /nw-discuss ("Define requirements and acceptance criteria")
IF "clear requirements, nothing written":
-> /nw-discuss ("Formalize requirements into user stories")
IF existing DISCUSS artifacts found:
-> /nw-design ("Requirements exist, design the architecture")
IF existing DESIGN artifacts found:
-> /nw-distill ("Architecture exists, create acceptance tests")
IF all prior waves complete:
-> /nw-deliver ("Ready for implementation")
DEFAULT:
-> /nw-discuss ("Start by defining what to build")
```
Show recommendation with rationale via AskUserQuestion: recommended wave command|why this wave (one sentence)|what it produces.
### Step 8: Launch
After user confirms, create project directory:
```bash
mkdir -p docs/feature/{feature-id}
```
Invoke recommended wave command by reading its task file and following instructions, passing feature ID as argument.
## Error Handling
| Error | Response |
|-------|----------|
| Vague description (< 3 meaningful words) | Ask follow-up questions with example |
| Name conflict with existing project | Offer continue/rename/archive options |
| User cannot classify feature type | Default to "cross-cutting", note uncertainty |
| No clear wave recommendation | Default to DISCUSS with explanation |
## Success Criteria
- [ ] User described feature in plain language
- [ ] Project ID derived and confirmed by user
- [ ] No name conflicts (or resolved)
- [ ] Feature classified by type
- [ ] Starting wave recommended with rationale
- [ ] User confirmed recommendation
- [ ] Wave command launched with correct feature ID
## Examples
### Example 1: Greenfield backend feature
```
/nw-new "Add rate limiting to the API gateway"
```
Derives `rate-limiting-api-gateway`, detects no prior artifacts (greenfield), asks clarifying questions. User says "new functionality, clear requirements." Recommends DISCUSS, launches `/nw-discuss "rate-limiting-api-gateway"`.
### Example 2: Bug fix
```
/nw-new "Fix authentication timeout errors"
```
Detects "fix" in description. User confirms bug. Recommends `/nw-root-why "authentication timeout errors"`.
### Example 3: Unclear problem
```
/nw-new "Build a customer feedback system"
```
User says they haven't validated whether customers want this. Recommends DISCOVER, launches `/nw-discover "customer-feedback-system"`.Related Skills
nw-ux-web-patterns
Web UI design patterns for product owners. Load when designing web application interfaces, writing web-specific acceptance criteria, or evaluating responsive designs.
nw-ux-tui-patterns
Terminal UI and CLI design patterns for product owners. Load when designing command-line tools, interactive terminal applications, or writing CLI-specific acceptance criteria.
nw-ux-principles
Core UX principles for product owners. Load when evaluating interface designs, writing acceptance criteria with UX requirements, or reviewing wireframes and mockups.
nw-ux-emotional-design
Emotional design and delight patterns for product owners. Load when designing onboarding flows, empty states, first-run experiences, or evaluating the emotional quality of an interface.
nw-ux-desktop-patterns
Desktop application UI patterns for product owners. Load when designing native or cross-platform desktop applications, writing desktop-specific acceptance criteria, or evaluating panel layouts and keyboard workflows.
nw-user-story-mapping
User story mapping for backlog management and outcome-based prioritization. Load during Phase 2.5 (User Story Mapping) to produce story-map.md and prioritization.md.
nw-tr-review-criteria
Review dimensions and scoring for root cause analysis quality assessment
nw-tlaplus-verification
TLA+ formal verification for design correctness and PBT pipeline integration
nw-test-refactoring-catalog
Detailed refactoring mechanics with step-by-step procedures, and test code smell catalog with detection patterns and before/after examples
nw-test-organization-conventions
Test directory structure patterns by architecture style, language conventions, naming rules, and fixture placement. Decision tree for selecting test organization strategy.
nw-test-design-mandates
Four design mandates for acceptance tests - hexagonal boundary enforcement, business language abstraction, user journey completeness, walking skeleton strategy, and pure function extraction
nw-tdd-review-enforcement
Test design mandate enforcement, test budget validation, 5-phase TDD validation, and external validity checks for the software crafter reviewer