Skip to content

nWave-ai/nWave / nWave/skills/nw-command-design-patterns

nw-command-design-patterns

Unverified

Best practices for command definition files - size targets, declarative template, anti-patterns, and canonical examples based on research evidence

Command Design Patterns (composing core)

Kind: KNOWLEDGE (lean composing core). The command-design knowledge is decomposed into three one-trigger modules; this core holds the canonical examples and composes the modules by trigger. Load the module(s) for the question in play.

Composition

ModuleLoad when the question isPath
nw-command-design-patterns-classificationwhat CATEGORY / what SIZE / what SHAPE (declarative template, WHAT-vs-HOW logic placement)~/.claude/skills/nw-command-design-patterns-classification/SKILL.md
nw-command-design-patterns-reductionwhat is REDUCIBLE / what to REMOVE / how far to COMPRESS (duplication triangle, anti-patterns, compression rules)~/.claude/skills/nw-command-design-patterns-reduction/SKILL.md
nw-command-design-patterns-authoringI am creating a NEW command — which FILES / what FORMAT (v2.8+ three-file install contract)~/.claude/skills/nw-command-design-patterns-authoring/SKILL.md

The three triggers partition the space: classification (size an existing command), reduction (trim a bloated one), authoring (lay out a new one). No overlap, no gap.

Canonical Examples

Example 1: Minimal Dispatcher (forge.md pattern, ~40 lines)

# DW-FORGE: Create Agent (V2)

**Wave**: CROSS_WAVE
**Agent**: Zeus (nw-agent-builder)

## Overview

Create a new agent using the research-validated v2 approach.

## Agent Invocation

@nw-agent-builder

Execute \*forge to create {agent-name} agent.

**Configuration:**
- agent_type: specialist | reviewer | orchestrator

## Success Criteria

- [ ] Agent definition under 400 lines
- [ ] Every `nw-ab-validation-checklist` item passes
- [ ] 3-5 canonical examples included

## Next Wave

**Handoff To**: Agent installation and deployment
**Deliverables**: Agent specification file + Skill files

Example 2: Medium Dispatcher with Context (~80 lines)

# DW-RESEARCH: Evidence-Driven Research

**Wave**: CROSS_WAVE
**Agent**: Nova (nw-researcher)

## Overview

Execute systematic evidence-based research with source verification.

## Orchestration: Trusted Source Config

Read .nwave/trusted-source-domains.yaml at orchestration time, embed inline in prompt.

## Agent Invocation

@nw-researcher

Execute \*research on {topic} [--embed-for={agent-name}].

**Configuration:**
- research_depth: detailed
- output_directory: docs/research/

## Success Criteria

- [ ] All sources from trusted domains
- [ ] Cross-reference performed (3+ sources per major claim)
- [ ] Research file created in docs/research/

## Next Wave

**Handoff To**: Invoking workflow
**Deliverables**: Research document + optional embed file

Example 3: Orchestrator (~200 lines)

Coordinates multiple phases without embedding agent knowledge:

# DW-DOCUMENT: Documentation Creation

**Wave**: CROSS_WAVE
**Agent**: Orchestrator (self)

## Overview

Create DIVIO-compliant documentation through research and writing phases.

## Phases

1. Research phase: @nw-researcher gathers domain knowledge
2. Writing phase: @nw-documentarist creates documentation
3. Review phase: @nw-reviewer validates quality

## Phase 1: Research

@nw-researcher - Execute \*research on {topic}
[Orchestrator reads and passes relevant context files]

## Phase 2: Writing

@nw-documentarist - Create {doc-type} documentation
[Orchestrator passes research output as context]

## Phase 3: Review

@nw-reviewer - Review documentation against DIVIO standards
[Orchestrator passes documentation for review]

## Success Criteria
[Per-phase and overall criteria]

The orchestrator describes WHAT each phase does and WHO does it. The agents know HOW.

brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.Stars: 195kUpdated Claude CodeCodexVerifiedInstall
frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.Stars: 195kUpdated Claude CodeCodexVerifiedInstall
mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).Stars: 195kUpdated Claude CodeCodexVerifiedInstall
web-artifacts-builderanthropics/skillsSuite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.Stars: 195kUpdated Claude CodeCodexUnverifiedInstall