Nw Fast Forward logo

Nw Fast Forward

Organization
nWave-ai
nw-fast-forward

Fast-forwards through remaining waves end-to-end without stopping for review between waves.

Overview

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

Use it in TypingMind

Enable Nw Fast Forward 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 Fast Forward 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 Fast Forward 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-FAST-FORWARD: Fast-Forward

Wave: CROSS_WAVE (entry point) | Agent: Main Instance (self — orchestrator) | Command: /nw-fast-forward

Overview

Chains remaining waves end-to-end after single user confirmation. Detects current progress (like /nw-continue), shows planned sequence, runs each wave automatically — DISCUSS > DESIGN > DEVOPS > DISTILL > DELIVER — without stopping between waves.

You (main Claude instance) run this orchestration directly. Each wave invoked by reading its task file.

DISCOVER skipped by default — requires interactive customer interview data that cannot be auto-generated. Use --from=discover to include.

Behavior Flow

Step 1: Input Parsing

Accept: feature description (new project)|--from flag with optional feature ID|no arguments (auto-detect from docs/feature/)

Step 2: Project Resolution

New project (description provided): Derive feature ID per ~/.claude/nWave/skills/common/wizard-shared-rules.md (Feature ID Derivation). Show derived ID, allow override via AskUserQuestion. Create docs/feature/{feature-id}/.

Existing project (no description): Scan docs/feature/ (same as /nw-continue Step 1-2). If multiple, ask user to select.

Step 3: Detect Current Progress

Check wave artifacts using Wave Detection Rules in ~/.claude/nWave/skills/common/wizard-shared-rules.md.

Step 4: Determine Wave Sequence

Default order (DISCOVER skipped): DISCUSS > DESIGN > DEVOPS > DISTILL > DELIVER

With --from flag: Validate prerequisite artifacts exist. If missing: "Cannot start from {wave} — {missing} artifacts missing. Run /nw-continue to fill the gap." Start from specified wave.

Without --from: Find first incomplete wave, start from there.

Step 5: Show Plan and Confirm

Feature: {feature-id}

  Fast-forward plan:
    1. DISCUSS  — Define requirements and user stories
    2. DESIGN   — Architecture and technology selection
    3. DEVOPS   — Platform and infrastructure readiness
    4. DISTILL  — Acceptance tests (Given-When-Then)
    5. DELIVER  — TDD implementation

  This will run all 5 waves without stopping for review.

If some waves complete, show as skipped:

  Fast-forward plan:
    ✓ DISCUSS  — complete
    ✓ DESIGN   — complete
    1. DEVOPS   — Platform and infrastructure readiness
    2. DISTILL  — Acceptance tests (Given-When-Then)
    3. DELIVER  — TDD implementation

  3 waves will execute without stopping.

One-time confirmation via AskUserQuestion.

Step 6: Sequential Execution

For each wave:

  1. Read task file (nWave/tasks/nw/{wave}.md)
  2. Follow instructions — invoke appropriate agent via Task tool
  3. Wait for completion
  4. Verify output artifacts exist (wave detection rules)
  5. Missing artifacts after wave = failure
  6. Proceed to next wave

Between waves show brief status:

✓ DISCUSS complete — user-stories.md, story-map.md created
  Starting DESIGN...

Step 7: Failure Handling

If any wave fails:

  1. Stop immediately — do not proceed
  2. Show error:
    ✗ {WAVE} failed
      Error: [details]
      Progress saved. Run /nw-continue to resume from {WAVE}.
  3. Suggest /nw-continue for manual resume
  4. Do NOT retry automatically

Step 8: Completion

✓ Fast-forward complete for {feature-id}

  DISCUSS   ● complete
  DESIGN    ● complete
  DEVOPS    ● complete
  DISTILL   ● complete
  DELIVER   ● complete

  All acceptance tests pass. Feature is ready.

Error Handling

ErrorResponse
No description and no existing projectsSuggest /nw-new
--from with missing prerequisitesList missing artifacts, refuse
Wave failure mid-pipelineStop, show error, suggest /nw-continue
Artifact verification fails after waveTreat as wave failure
Name conflict on new projectSame as /nw-new conflict handling

Success Criteria

  • Project resolved (new or existing)
  • Current progress detected accurately
  • Planned wave sequence shown to user
  • User confirmed one-time before execution
  • Each wave executed in sequence
  • Output artifacts verified between waves
  • Failure stops pipeline with clear error and /nw-continue suggestion
  • Completion summary shown

Examples

Example 1: Full fast-forward from scratch

/nw-fast-forward "Upgrade authentication to OAuth2"

Wizard derives oauth2-upgrade, detects no prior artifacts, shows plan: DISCUSS > DESIGN > DEVOPS > DISTILL > DELIVER. User confirms. All 5 waves execute in sequence.

Example 2: Fast-forward from mid-pipeline

/nw-fast-forward

Wizard finds notification-service with DISCUSS complete. Shows plan: DESIGN > DEVOPS > DISTILL > DELIVER. User confirms. 4 waves execute.

Example 3: Fast-forward with --from flag

/nw-fast-forward --from=distill rate-limiting

Wizard validates DESIGN artifacts exist for rate-limiting. Shows plan: DISTILL > DELIVER. User confirms. 2 waves execute.

Example 4: Fast-forward with failure

/nw-fast-forward "Add payment processing"

DISCUSS succeeds, DESIGN succeeds, DEVOPS fails. Pipeline stops. Shows error and suggests /nw-continue to resume from DEVOPS.

Frequently asked questions

What does the Nw Fast Forward AI skill do?

Fast-forwards through remaining waves end-to-end without stopping for review between waves.

Why use Nw Fast Forward on TypingMind?

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

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

Which AI models can use Nw Fast Forward?

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 Fast Forward?

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

Is the Nw Fast Forward 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 👇