NWave nw-buddy-command-catalog
All /nw-* commands — what they do, when to use them, which agent they invoke. For the buddy agent to help users pick the right command.
install
source · Clone the upstream repo
git clone https://github.com/nWave-ai/nWave
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/nWave-ai/nWave "$T" && mkdir -p ~/.claude/skills && cp -r "$T/nWave/skills/nw-buddy-command-catalog" ~/.claude/skills/nwave-ai-nwave-nw-buddy-command-catalog && rm -rf "$T"
manifest:
nWave/skills/nw-buddy-command-catalog/SKILL.mdsource content
Command Catalog
Wave Commands (run in order per feature)
| Command | Wave | Agent | When to Use |
|---|---|---|---|
| DISCOVER | product-discoverer (Scout) | Validate problem exists, customer interviews, opportunity mapping |
| DIVERGE | diverger (Flux) | Evaluate multiple solution approaches before committing |
| DISCUSS | product-owner (Luna) | Define user stories, journeys, acceptance criteria |
| DESIGN | system-designer, ddd-architect, solution-architect | Route to the right architect — system (scalability), domain (DDD), or application (components) |
| DEVOPS | platform-architect | CI/CD, infrastructure, observability, deployment strategy |
| DISTILL | acceptance-designer | Create executable acceptance tests (Given-When-Then) |
| DELIVER | software-crafter | Full implementation: roadmap -> execute -> finalize |
Routing Commands
| Command | Purpose | When to Use |
|---|---|---|
| Guided wizard for new features | Starting something new — asks what you're building, recommends starting wave |
| Resume in-progress feature | Returning to a feature — detects progress, starts at next wave |
| Run remaining waves without pausing | When you trust the agents to proceed without review between waves |
DELIVER Inner Loop Commands (manual mode)
| Command | Purpose | When to Use |
|---|---|---|
| Run single roadmap step | Implementing one step at a time (learning mode) |
| Create implementation plan | Planning steps before execution |
| Expert review of artifacts | Quality check on roadmap, code, or step output |
| Test suite effectiveness | After implementation — verifies tests catch real bugs |
| Archive completed feature | After all steps pass — creates evolution document |
Cross-Wave Commands (any time)
| Command | Agent | When to Use |
|---|---|---|
| researcher (Nova) | Investigate technologies, patterns, decisions needing evidence |
| documentarist + researcher | Create DIVIO-compliant documentation (tutorial, how-to, reference, explanation) |
| solution-architect | Generate C4 architecture diagrams (Mermaid/PlantUML) |
| software-crafter | Systematic refactoring using RPP levels L1-L6 |
| troubleshooter + crafter | Root cause analysis -> regression test -> fix via TDD |
| troubleshooter | Root cause analysis (5 Whys) without fix |
| (self) | Git change frequency analysis — find most-changed files |
| (self) | Set quality-vs-token profile (lean/standard/thorough/exhaustive) |
| agent-builder (Zeus) | Create new specialized agents |
| software-crafter | Complex refactoring roadmaps with visual tracking (experimental) |
| buddy (Guide) | Ask any question about nWave — methodology, commands, project state |
For the full authoritative command reference, read
.docs/reference/commands/index.md
Common User Scenarios -> Command
| User Says | Recommend |
|---|---|
| "I want to build something new" | |
| "I'm not sure which approach to take" | |
| "I need user stories for this feature" | |
| "How should I architect this?" | |
| "I need to set up CI/CD" | |
| "I need acceptance tests" | |
| "I'm ready to implement" | |
| "I want to continue my feature" | |
| "I need to research X" | |
| "I need documentation" | |
| "Something is broken" | |
| "My code needs cleanup" | |
| "How good are my tests?" | |