nWave-ai/nWave

AT Completeness Check gates acceptance-test sets against a canonical 7-category taxonomy and 15-item checklist. Use it to spot missing boundary, state, lifecycle, flag, negative, and environment cases.

Acceptance Test Critique Dimensions reviews acceptance tests for coverage, GWT structure, business-language wording, observable assertions, and traceability. Use it when peer-reviewing scenarios or walking skeletons before handoff.

Agent Creation Workflow guides agent design from requirements analysis through validation and refinement. Use it when creating a new agent or modifying an existing one with clear responsibilities, tools, and quality gates.

Agent Quality Critique Dimensions provides checks for Claude Code agent definitions, including template compliance, safety, examples, loading, and priority. Use it when reviewing an agent file for correctness and fit.

Agent Quality Critique Dimensions provides review criteria for Claude Code agent definitions, including template compliance, safety, examples, and loading behavior. Use it when validating an agent before release or refactor.

Agent Testing Framework defines a 5-layer approach for validating agent outputs, handoffs, and adversarial cases. It is used to check prompt injection resistance and other security constraints in Claude Code agents.

Architectural Styles Tradeoffs helps choose between common software architecture styles using decision trees, comparison matrices, and combination patterns. Use it when selecting or evaluating an architecture for a system.

Architecture Patterns covers architecture styles, DDD, quality attributes, and trade-off evaluation for solution design. Use it when choosing patterns, defining boundaries, or assessing risks in a system architecture.

Authoritative Sources defines domain-specific trusted databases, search strategies, and freshness rules for research. Use it when choosing sources for architecture, security, frameworks, or DevOps topics.

BDD Methodology defines acceptance test design with Given-When-Then scenarios, scenario-writing rules, and pytest-bdd implementation. Use it to write living documentation and avoid common BDD anti-patterns.

BDD Requirements Discovery guides collaborative discovery of requirements through Example Mapping, Three Amigos conversations, and concrete examples. Use it to turn business rules into Given-When-Then scenarios and uncover edge cases.

CI/CD And Deployment covers pipeline design, quality gates, deployment strategies, and GitHub Actions patterns. Use it when planning build, test, release, or rollback workflows.

Canary detects whether auto-injection is active by exposing a known marker for verification. Use it to confirm skill-loading behavior during testing.

Collaboration And Handoffs defines cross-agent handoff protocols, workflow transitions, and commit message formats for TDD, Mikado, and refactoring work. Use it to pass implementation context between roles and keep progress traceable.

Collapse Detection identifies documentation type-mixing patterns such as tutorial creep, how-to bloat, and reference narrative. Use it to flag docs that combine multiple user intents and to guide splitting or remediation.

Command Design Patterns defines best practices for Claude Code command files, including size targets, declarative structure, and common anti-patterns. Use it when designing or reviewing dispatchers and orchestrators.

Command Optimization Workflow converts oversized command files into lean declarative definitions by removing duplicated boilerplate, moving domain knowledge to agents, and restructuring around a standard template. Use it when a Claude Code command needs to be shortened and made easier to maintain.

NW Buddy answers questions about nWave methodology, project state, commands, migration, and troubleshooting using the project’s own docs and files. It is read-only and meant for contextual help.

NW Continue scans docs/feature/ for active projects, detects the current wave, and shows what to resume next. Use it when returning to an in-progress feature after time away.

Nw Buddy Command Catalog explains every /nw-* command, when to use it, and which agent it invokes. Use it to choose the right command for a feature, task, or troubleshooting step.

Nw Bug Fix guides a defect through root-cause analysis, user review, and a regression test plus minimal fix. Use it for known bugs that need a confirmed diagnosis before implementation.

Project Reading helps a buddy agent inspect a codebase in a defined order and answer questions with file-and-line citations. Use it when you need grounded project facts, architecture context, or current state without guessing.

SSOT Knowledge tells a buddy agent which file is authoritative for versions, backlog, architecture, config, and runtime behavior. Use it when repo sources disagree or when you need to avoid answering from stale docs.

Structured Brainstorming guides divergent ideation with HMW framing, SCAMPER, and Crazy 8s. It is used when you need many distinct options before any evaluation or ranking begins.

Wave Methodology Knowledge maps the nWave process from DISCOVER through DELIVER, including each wave’s purpose, inputs, outputs, and primary agent. Use it to route questions about where work is in the process and what comes next.