Agent skill

Nw Diverge

Generates 3-5 divergent design directions through JTBD analysis, competitive research, structured brainstorming, and taste evaluation before convergence.

MITAuto-check passedAgent Workflows

Install Nw Diverge

skills CLI

$ npx skills add nWave-ai/nWave --skill nw-diverge -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install nWave-ai/nWave nw-diverge --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/nWave-ai/nWave.git skills-src && mkdir -p .claude/skills && cp -r skills-src/nWave/skills/nw-diverge .claude/skills/nw-diverge && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "nw-diverge" agent skill from https://github.com/nWave-ai/nWave/tree/main/nWave/skills/nw-diverge into .claude/skills/nw-diverge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nw-diverge", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/nWave-ai/nWave/tree/main/nWave/skills/nw-diverge

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add nWave-ai/nWave --skill nw-diverge -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install nWave-ai/nWave nw-diverge --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/nWave-ai/nWave.git skills-src && mkdir -p .agents/skills && cp -r skills-src/nWave/skills/nw-diverge .agents/skills/nw-diverge && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "nw-diverge" agent skill from https://github.com/nWave-ai/nWave/tree/main/nWave/skills/nw-diverge into .agents/skills/nw-diverge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nw-diverge", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add nWave-ai/nWave --skill nw-diverge -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install nWave-ai/nWave nw-diverge --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/nWave-ai/nWave.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/nWave/skills/nw-diverge .cursor/skills/nw-diverge && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "nw-diverge" agent skill from https://github.com/nWave-ai/nWave/tree/main/nWave/skills/nw-diverge into .cursor/skills/nw-diverge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nw-diverge", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/nWave-ai/nWave.git --path nWave/skills/nw-diverge

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add nWave-ai/nWave --skill nw-diverge -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install nWave-ai/nWave nw-diverge --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/nWave-ai/nWave.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/nWave/skills/nw-diverge .gemini/skills/nw-diverge && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "nw-diverge" agent skill from https://github.com/nWave-ai/nWave/tree/main/nWave/skills/nw-diverge into .gemini/skills/nw-diverge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nw-diverge", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install nWave-ai/nWave nw-diverge

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add nWave-ai/nWave --skill nw-diverge -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/nWave-ai/nWave.git skills-src && mkdir -p .github/skills && cp -r skills-src/nWave/skills/nw-diverge .github/skills/nw-diverge && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "nw-diverge" agent skill from https://github.com/nWave-ai/nWave/tree/main/nWave/skills/nw-diverge into .github/skills/nw-diverge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nw-diverge", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add nWave-ai/nWave --skill nw-diverge -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install nWave-ai/nWave nw-diverge --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/nWave-ai/nWave.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/nWave/skills/nw-diverge .opencode/skills/nw-diverge && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "nw-diverge" agent skill from https://github.com/nWave-ai/nWave/tree/main/nWave/skills/nw-diverge into .opencode/skills/nw-diverge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nw-diverge", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: nw-diverge
GitHub stars: 616
Token cost: ~2.2k tokens
SKILL.md length: 829 words
Files: 1
Skills in repo: 14
Repo updated: Sep 16, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Generates 3-5 divergent design directions through JTBD analysis, competitive research, structured brainstorming, and taste evaluation before convergence.

Works in 4 steps: New product -- no prior solution exists,… → Brownfield feature -- existing product,… → Pivot / redesign -- existing feature… → …
The team has a validated problem but hasnt chosen a solution approach
SKILL.md covers Overview, Interactive Decision Points, Prior Wave Consultation and Agent Invocation, plus 6 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Nw Diverge is an agent skill from nWave-ai/nWave. Generates 3-5 divergent design directions through JTBD analysis, competitive research, structured brainstorming, and taste evaluation before convergence. Use when the team has a validated problem but hasn't chosen a solution approach.

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Brainstorming and User stories. The repository describes itself as: AI agents that guide you from idea to working code, with you in control at every step. The licence is MIT.

When your agent uses it

The team has a validated problem but hasnt chosen a solution approach
Tasks that involve Brainstorming
Tasks that involve User stories

Example prompts

“Use the nw-diverge skill to generate 3-5 divergent design directions through JTBD analysis, competitive research, structured brainstorming, and…”
“/nw-diverge”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

New product -- no prior solution exists, full divergence needed
Brownfield feature -- existing product, exploring approach alternatives
Pivot / redesign -- existing feature being reconsidered from scratch
Other -- user provides custom context

What it can do on your machine

Read from SKILL.md and the folder at commit da401a8. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Nw Diverge loads about 2.2k tokens when it runs. Until then it costs about 61 tokens; SKILL.md has 829 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~61
When it runs · the whole SKILL.md, loaded when a task matches: ~2.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from nWave-ai/nWave at commit da401a8, republished under its MIT licence (© nWave-ai). 829 words, ~2,172 tokens.

Download SKILL.mdSave it as .claude/skills/nw-diverge/SKILL.md (or your agent's skills folder).

name: nw-diverge
description: Generates 3-5 divergent design directions through JTBD analysis, competitive research, structured brainstorming, and taste evaluation before convergence. Use when the team has a validated problem but hasn't chosen a solution approach.
user-invocable: true
argument-hint: [feature-id] - Optional: --work-type=[new-product|brownfield|pivot]

NW-DIVERGE: Structured Divergent Thinking Before Convergence

Wave: DIVERGE (between DISCOVER and DISCUSS, optional) | Agent: Flux (nw-diverger) | Command: /nw-diverge

Overview

Execute DIVERGE wave through Flux's 4-phase workflow: JTBD analysis|competitive research|structured brainstorming|taste-filtered evaluation. Transforms a validated problem into 3-5 concrete, taste-scored design directions so DISCUSS can converge on one with confidence.

DIVERGE is optional. Brownfield features with a clear direction may skip it (see skip checklist in design spec). New products and pivot decisions benefit most from structured divergence.

Interactive Decision Points

Decision 1: Work Type

Question: What type of work is this? Options:

New product -- no prior solution exists, full divergence needed
Brownfield feature -- existing product, exploring approach alternatives
Pivot / redesign -- existing feature being reconsidered from scratch
Other -- user provides custom context

Decision 2: Research Depth

Question: How deep should competitive research go? Options:

Lightweight -- 3 competitors, known market
Comprehensive -- 5+ competitors including non-obvious alternatives
Deep-dive -- cross-category research, adjacent markets, academic references

Prior Wave Consultation

Before beginning DIVERGE work, read SSOT and prior wave artifacts:

SSOT (if docs/product/ exists):
- docs/product/jobs.yaml -- validated jobs and opportunity scores
- docs/product/vision.md -- product vision and strategic context
Project context: docs/project-brief.md | docs/stakeholders.yaml (if available)
DISCOVER artifacts: Read docs/feature/{feature-id}/discover/ (if present)
- wave-decisions.md -- validated assumptions and key decisions
- problem-validation.md -- customer evidence grounding the problem

Migration gate: If docs/product/ does not exist but docs/feature/ has existing features, STOP. Guide the user to docs/guides/migrating-to-ssot-model/README.md and complete the migration first. If greenfield, DIVERGE will bootstrap docs/product/jobs.yaml with the validated job.

READING ENFORCEMENT: You MUST read every file listed in Prior Wave Consultation above using the Read tool before proceeding. After reading, output a confirmation checklist. Do NOT skip files that exist -- skipping causes options disconnected from evidence.

Agent Invocation

@nw-diverger

Execute *diverge for {feature-id}.

Context Files: see Prior Wave Consultation above + project context files.

Configuration:

work_type: {Decision 1}
research_depth: {Decision 2}
output_directory: docs/feature/{feature-id}/

SKILL_LOADING: Before starting work, load your skill files using the Read tool from ~/.claude/skills/nw-{skill-name}/SKILL.md. Skills encode your methodology -- without them you operate with generic knowledge only.

At the start of execution, create these tasks using TaskCreate and follow them in order:

JTBD Analysis — Load jtbd-analysis skill. Extract and elevate the job from the raw request or DISCOVER evidence. Produce job statements (functional + emotional + social) and ODI outcome statements. Gate: job at strategic or physical level (not tactical), minimum 3 ODI outcome statements produced.
Competitive Research — Invoke nw-researcher sub-agent for evidence-grounded competitive research. Map how existing products serve the validated job. Identify non-obvious alternatives. Gate: 3+ real competitors named, at least one non-obvious alternative, evidence quality confirmed.
Brainstorming — Load brainstorming skill. Frame HMW question, apply SCAMPER lenses, generate structurally diverse options. Gate: 6 options generated with diversity confirmed (mechanism, assumption, and cost structure differ across options).
Taste Evaluation — Load taste-evaluation skill. Apply DVF filter, score surviving options on 4 taste criteria with locked weights, produce weighted ranking and recommendation with dissenting case. Gate: all surviving options scored on all 4 criteria, recommendation traceable to scoring matrix, dissenting case documented.
Peer Review — Invoke nw-diverger-reviewer (Prism) to validate all 5 dimensions. Revise if needed (max 2 iterations). Gate: reviewer approval confirmed, handoff accepted by nw-product-owner.

Show full SKILL.md (302 more words)Show less

Success Criteria

Job extracted at strategic or physical level (not tactical, not a feature description)
Minimum 3 ODI outcome statements produced
3+ real competitors researched, at least one non-obvious alternative
6 structurally diverse options generated (different mechanism, assumption, cost)
All surviving options scored on all 4 taste criteria with locked weights
Recommendation traceable to scoring matrix (no "feels right" overrides)
Dissenting case documented for second-place option
Peer review approved by nw-diverger-reviewer
Handoff accepted by nw-product-owner (DISCUSS wave)

Next Wave

Handoff To: nw-product-owner (DISCUSS wave) Deliverables: recommendation.md with explicit decision statement + supporting DIVERGE artifacts

Wave Decisions Summary

Before completing DIVERGE, produce (or append to) docs/feature/{feature-id}/wave-decisions.md:

markdown

# DIVERGE Decisions -- {feature-id}

## Key Decisions
- [D1] {decision}: {rationale} (see: {source-file})

## Job Summary
- Validated job: {job statement at strategic/physical level}
- ODI outcomes: {count} outcome statements

## Options Evaluated
- {count} options generated, {count} survived DVF filter
- Recommended: {option name} -- {one-line rationale}
- Dissent: {second-place option} -- {why it might be better under different assumptions}

## SSOT Updates
- jobs.yaml: {created|updated} with job JOB-{NNN}

SSOT Update

After producing feature-level artifacts, update the product-level SSOT:

Jobs SSOT: Create or update docs/product/jobs.yaml with the validated job from Phase 1. Add changelog entry referencing this feature-id.
If docs/product/ does not exist, create the directory. This is the SSOT bootstrap.

SSOT files use schema_version and changelog fields. See canonical schema in the design spec.

Expected Outputs

Feature delta (in `docs/feature/{feature-id}/`)

  recommendation.md             (top 3 options, dissenting case, decision for DISCUSS)
  wave-decisions.md             (DIVERGE section appended)

Internal artifacts (in `docs/feature/{feature-id}/diverge/`)

  job-analysis.md               (validated job + ODI outcome statements)
  competitive-research.md       (prior art, competitor analysis, non-obvious alternatives)
  options-raw.md                (all generated options, unfiltered, no evaluation)
  taste-evaluation.md           (DVF filter, locked weights, scoring matrix)
  review.yaml                   (peer review result from nw-diverger-reviewer)

SSOT updates (in `docs/product/`)

  jobs.yaml                     (created or updated with validated job + changelog entry)

Examples

Example 1: New product divergence

/nw-diverge notification-system

DISCOVER artifacts present with validated problem. Flux reads problem-validation.md, extracts job ("minimize likelihood of developers missing critical failure signals"), researches 5 notification tools including non-obvious alternatives (ambient light signals, IDE annotations), generates 6 structurally diverse options, scores with taste evaluation, recommends proactive push with Slack integration. Updates jobs.yaml with validated job.

Example 2: Brownfield feature without DISCOVER

/nw-diverge rate-limiting

No DISCOVER artifacts. Flux works from project-brief.md and direct conversation. Extracts job via 5 Whys from "we need rate limiting" to strategic level. Creates docs/product/jobs.yaml (SSOT bootstrap). Proceeds through all 4 phases.

Example 3: Skip validation (DIVERGE not needed)

/nw-diverge --skip auth-bugfix

Skip checklist evaluated: clear direction exists (bugfix), no competing approaches, self-evident path. DIVERGE skipped. User directed to /nw-discuss or /nw-distill depending on work type.

Files

Just SKILL.md in nWave/skills/nw-diverge of nWave-ai/nWave.

Open the folder on GitHubat commit da401a8

Compare with similar skills

Nw Diverge next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Nw Diverge compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Nw Diverge this skillnWave-ai/nWave	616	—	~2.2k	Automated safety check: Pass	MIT	25 days ago
Spec Workflowhashgraph-online/awesome-codex-plugins	1.3k	—	~2.1k	Automated safety check: Pass	Apache-2.0	yesterday
Specifygenkovich/sdd	171	—	~3.6k	Automated safety check: Pass	MIT	1 mo ago
Synthesis Buildacogood/diffmode_free	163	—	~5.3k	Automated safety check: Pass	Apache-2.0	2 mo ago
Idea Refinementaddyosmani/agent-skills	105k	6 repos	~2k	Automated safety check: Pass	MIT	yesterday
CE BrainstormEveryInc/compound-engineering-plugin	25k	—	~1.9k	Automated safety check: Pass	MIT	today

Similar skills

Spec Workflow
hashgraph-online/awesome-codex-plugins
This skill should be used when the user asks to "create a spec", "write requirements", "design a feature", "plan implementation", "use EARS notation", "create user stories", "break down tasks"…
1.3k GitHub stars~2.1k tokensUpdated yesterday
Product & Project ManagementAuto-check passed
Specify
genkovich/sdd
A skill your agent uses to turn a raw feature idea into a reviewed spec.md — a lightweight Socratic interview front (capture the idea, deep-dive the problem) merged with a full product spec…
171 GitHub stars~3.6k tokensUpdated 1 mo ago
Product & Project ManagementAuto-check passed
Synthesis Build
acogood/diffmode_free
Synthesis BUILD stage — the FINAL stage of the Diffmode growth-tactics pipeline (fuses white-space ideation + founder-fit adaptation & merge — formerly two separate synthesis passes — into ONE…
163 GitHub stars~5.3k tokensUpdated 2 mo ago
Product & Project ManagementAuto-check passed
Idea Refinement
addyosmani/agent-skills
Guides a conversation that takes a vague idea through divergent and convergent thinking and ends in a markdown one-pager covering scope and assumptions.
105k GitHub starsUsed in 6 repos~2k tokens
Agent WorkflowsAuto-check passed
CE Brainstorm
EveryInc/compound-engineering-plugin
Turns a vague or ambitious feature idea into a requirements-only plan through dialogue with you, sized to the work, before any code is written.
25k GitHub stars~1.9k tokensUpdated today
Agent WorkflowsAuto-check passed
Extracting Requirements
prime-radiant-inc/iterative-development
Reads human-written spec documents and produces per-epic requirement files with proof obligations plus behavior scenarios with stable IDs, using parallel chunked extraction.
181 GitHub stars~2.7k tokensUpdated 4 mo ago
Agent WorkflowsAuto-check passed

Questions about Nw Diverge

What does Nw Diverge do?

Generates 3-5 divergent design directions through JTBD analysis, competitive research, structured brainstorming, and taste evaluation before convergence. Nw Diverge is an agent skill from nWave-ai/nWave. Generates 3-5 divergent design directions through JTBD analysis, competitive research, structured brainstorming, and taste evaluation before convergence.

When should I use Nw Diverge?

Nw Diverge fits situations like: the team has a validated problem but hasnt chosen a solution approach; tasks that involve Brainstorming; tasks that involve User stories.

How do I install Nw Diverge in Claude Code?

Run `npx skills add nWave-ai/nWave --skill nw-diverge -a claude-code`. Or copy the skill folder (nWave/skills/nw-diverge in nWave-ai/nWave) into .claude/skills/nw-diverge in your project. Claude Code loads it when a task matches its description.

How do I install Nw Diverge in Codex?

Run `npx skills add nWave-ai/nWave --skill nw-diverge -a codex`. Or copy the skill folder (nWave/skills/nw-diverge in nWave-ai/nWave) into .agents/skills/nw-diverge in your project. Codex loads it when a task matches its description.

Can I use Nw Diverge in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add nWave-ai/nWave --skill nw-diverge -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/nw-diverge, .gemini/skills/nw-diverge, .github/skills/nw-diverge and .opencode/skills/nw-diverge in your project.

What does Nw Diverge need to run?

SKILL.md names no scripts, command-line tools or credentials: Nw Diverge is instructions for the agent only.

Does Nw Diverge access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Nw Diverge safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Nw Diverge use?

Nw Diverge is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Nw Diverge use?

About 2.2k tokens (SKILL.md is roughly 8.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Nw Diverge?

Skills that share tags, products or a category with Nw Diverge: Spec Workflow (hashgraph-online/awesome-codex-plugins, 1.3k stars), Specify (genkovich/sdd, 171 stars), Synthesis Build (acogood/diffmode_free, 163 stars) and Idea Refinement (addyosmani/agent-skills, 105k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Nw Diverge?

nWave-ai (a GitHub organization) maintains it in nWave-ai/nWave, which has 616 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on September 16, 2026.

Source: nWave-ai/nWave on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Nw Diverge

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

NW-DIVERGE: Structured Divergent Thinking Before Convergence

Overview

Interactive Decision Points

Decision 1: Work Type

Decision 2: Research Depth

Prior Wave Consultation

Agent Invocation

Success Criteria

Next Wave

Wave Decisions Summary

SSOT Update

Expected Outputs

Feature delta (in docs/feature/{feature-id}/)

Internal artifacts (in docs/feature/{feature-id}/diverge/)

SSOT updates (in docs/product/)

Examples

Example 1: New product divergence

Example 2: Brownfield feature without DISCOVER

Example 3: Skip validation (DIVERGE not needed)

Files

Compare with similar skills

Similar skills

More from nWave-ai/nWave

Related

Questions about Nw Diverge

Feature delta (in `docs/feature/{feature-id}/`)

Internal artifacts (in `docs/feature/{feature-id}/diverge/`)

SSOT updates (in `docs/product/`)