Nw New logo

Nw New

Organization
nWave-ai
nw-new

Guided wizard to start a new feature. Asks what you want to build, recommends the right starting wave, and launches it.

Overview

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

Use it in TypingMind

Enable Nw New 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 New 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 New 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.

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

ErrorResponse
Vague description (< 3 meaningful words)Ask follow-up questions with example
Name conflict with existing projectOffer continue/rename/archive options
User cannot classify feature typeDefault to "cross-cutting", note uncertainty
No clear wave recommendationDefault 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".

Frequently asked questions

What does the Nw New AI skill do?

Guided wizard to start a new feature. Asks what you want to build, recommends the right starting wave, and launches it.

Why use Nw New on TypingMind?

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

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

Which AI models can use Nw New?

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 New?

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

Is the Nw New 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 👇