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.
npx skills add https://github.com/nWave-ai/nWave --skill nw-buddy-command-catalog
| Command | Wave | Agent | When to Use |
|---------|------|-------|-------------|
| /nw-discover | DISCOVER | product-discoverer (Scout) | Validate problem exists, customer interviews, opportunity mapping |
| /nw-diverge | DIVERGE | diverger (Flux) | Evaluate multiple solution approaches before committing |
| /nw-discuss | DISCUSS | product-owner (Luna) | Define user stories, journeys, acceptance criteria |
| /nw-design | DESIGN | system-designer, ddd-architect, solution-architect | Route to the right architect — system (scalability), domain (DDD), or application (components) |
| /nw-devops | DEVOPS | platform-architect | CI/CD, infrastructure, observability, deployment strategy |
| /nw-distill | DISTILL | acceptance-designer | Create executable acceptance tests (Given-When-Then) |
| /nw-deliver | DELIVER | software-crafter | Full implementation: roadmap -> execute -> finalize |
| Command | Purpose | When to Use |
|---------|---------|-------------|
| /nw-new | Guided wizard for new features | Starting something new — asks what you're building, recommends starting wave |
| /nw-continue | Resume in-progress feature | Returning to a feature — detects progress, starts at next wave |
| /nw-fast-forward | Run remaining waves without pausing | When you trust the agents to proceed without review between waves |
| Command | Purpose | When to Use |
|---------|---------|-------------|
| /nw-execute | Run single roadmap step | Implementing one step at a time (learning mode) |
| /nw-roadmap | Create implementation plan | Planning steps before execution |
| /nw-review | Expert review of artifacts | Quality check on roadmap, code, or step output |
| /nw-mutation-test | Test suite effectiveness | After implementation — verifies tests catch real bugs |
| /nw-finalize | Archive completed feature | After all steps pass — creates evolution document |
| Command | Agent | When to Use |
|---------|-------|-------------|
| /nw-research | researcher (Nova) | Investigate technologies, patterns, decisions needing evidence |
| /nw-document | documentarist + researcher | Create DIVIO-compliant documentation (tutorial, how-to, reference, explanation) |
| /nw-diagram | solution-architect | Generate C4 architecture diagrams (Mermaid/PlantUML) |
| /nw-refactor | software-crafter | Systematic refactoring using RPP levels L1-L6 |
| /nw-bugfix | troubleshooter + crafter | Root cause analysis -> regression test -> fix via TDD |
| /nw-root-why | troubleshooter | Root cause analysis (5 Whys) without fix |
| /nw-hotspot | (self) | Git change frequency analysis — find most-changed files |
| /nw-rigor | (self) | Set quality-vs-token profile (lean/standard/thorough/exhaustive) |
| /nw-forge | agent-builder (Zeus) | Create new specialized agents |
| /nw-mikado | software-crafter | Complex refactoring roadmaps with visual tracking (experimental) |
| /nw-buddy | buddy (Guide) | Ask any question about nWave — methodology, commands, project state |
> For the full authoritative command reference, read docs/reference/commands/index.md.
| User Says | Recommend |
|-----------|-----------|
| "I want to build something new" | /nw-new (wizard) or /nw-discover (if problem unclear) |
| "I'm not sure which approach to take" | /nw-diverge |
| "I need user stories for this feature" | /nw-discuss |
| "How should I architect this?" | /nw-design |
| "I need to set up CI/CD" | /nw-devops |
| "I need acceptance tests" | /nw-distill |
| "I'm ready to implement" | /nw-deliver |
| "I want to continue my feature" | /nw-continue |
| "I need to research X" | /nw-research |
| "I need documentation" | /nw-document |
| "Something is broken" | /nw-bugfix or /nw-root-why |
| "My code needs cleanup" | /nw-refactor |
| "How good are my tests?" | /nw-mutation-test |
Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.
Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances
Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.
Build and distribute Expo development clients locally or via TestFlight
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.
Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.
Take nwave-ai/nw-buddy-command-catalog from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.