New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Nw Command Design Patterns

by nWave-ai in nWave-ai/nWave

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

MITAuto-check passedDevelopment

Install Nw Command Design Patterns

skills CLI
$ npx skills add nWave-ai/nWave --skill nw-command-design-patterns -a claude-code

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

GitHub CLI
$ gh skill install nWave-ai/nWave nw-command-design-patterns --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-command-design-patterns .claude/skills/nw-command-design-patterns && 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/

Facts

Skill name
nw-command-design-patterns
GitHub stars
617
Token cost
~2.4k tokens
SKILL.md length
741 words
Files
1
Skills in repo
106
Repo updated
First seen
Licence
MIT

At a glance

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

  • Works in 3 steps: Command-to-Command: Orchestrator… → Command-to-Agent: Domain knowledge… → Command-to-Self: develop.md embeds other…
  • Tasks that involve Design patterns
  • SKILL.md covers The Forge Model (Gold Standard), Command Categories, Declarative Command Template and Size Targets and Evidence, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Nw Command Design Patterns is an agent skill from nWave-ai/nWave. Best practices for command definition files - size targets, declarative template, anti-patterns, and canonical examples based on research evidence

Its SKILL.md is about 2.4k 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 Development, covering Design patterns. 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

  • Tasks that involve Design patterns

Example prompts

  • “/nw-command-design-patterns”

Workflow steps

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

  1. Command-to-Command: Orchestrator briefings, agent registries, parameter parsing repeated in 5-12 files (~620 lines waste)
  2. Command-to-Agent: Domain knowledge belonging in agents (~1,300 lines waste). Examples: TDD phases in execute.md, DIVIO templates in…
  3. Command-to-Self: develop.md embeds other commands inline (~1,000 lines)

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 and yaml).

    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 Command Design Patterns loads about 2.4k tokens when it runs. Until then it costs about 43 tokens; SKILL.md has 741 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~43
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k

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). 741 words, ~2,388 tokens.

Download SKILL.mdSave it as .claude/skills/nw-command-design-patterns/SKILL.md (or your agent's skills folder).
name
nw-command-design-patterns
description
Best practices for command definition files - size targets, declarative template, anti-patterns, and canonical examples based on research evidence
user-invocable
false
disable-model-invocation
true

Command Design Patterns

The Forge Model (Gold Standard)

forge.md at 40 lines is the reference dispatcher. Contains: header (wave, agent, overview) | Agent invocation (name + command + config) | Success criteria (checklist) | Next wave handoff | Expected outputs. Every dispatcher should aspire to this pattern.

Command Categories

CategoryDescriptionSize TargetExamples
SimpleDirect action, minimal delegation40-80 linesforge, start, version, git
DispatcherDelegates to one agent with context40-150 linesresearch, review, execute
OrchestratorCoordinates multiple agents/phases100-300 linesdevelop, document

Declarative Command Template

Commands declare WHAT, not HOW. The agent knows how to do its job.

markdown
# DW-{NAME}: {Title}

**Wave**: {WAVE_NAME}
**Agent**: {persona} ({agent-id})

## Overview

One paragraph: what this command does and when to use it.

## Context Files Required

- {path} - {why needed}

## Agent Invocation

@{agent-id}

Execute \*{command} for {parameters}.

**Context Files:**
- {files the orchestrator reads and passes}

**Configuration:**
- {key}: {value} # {comment}

## Success Criteria

- [ ] {measurable outcome}
- [ ] {quality gate}

## Next Wave

**Handoff To**: {next wave or workflow step}
**Deliverables**: {what this command produces}

# Expected outputs:
# - {file paths}

Size Targets and Evidence

Research (Chroma Research, Anthropic context engineering): focused prompts (~300 tokens) outperform full prompts (~113k tokens) | Claude shows most pronounced performance gap | Information buried mid-prompt gets deprioritized ("Lost in the Middle") | Opus 4.6 is proactive/self-directing; verbose instructions cause overtriggering

Targets: Dispatchers 40-150 lines | Orchestrators 100-300 lines | Current average 437 lines; target under 150

The Duplication Triangle

Commands duplicate content in three directions, all waste tokens:

  1. Command-to-Command: Orchestrator briefings, agent registries, parameter parsing repeated in 5-12 files (~620 lines waste)
  2. Command-to-Agent: Domain knowledge belonging in agents (~1,300 lines waste). Examples: TDD phases in execute.md, DIVIO templates in document.md, refactoring hierarchies in refactor.md
  3. Command-to-Self: develop.md embeds other commands inline (~1,000 lines)

Fix: Extract shared content to preamble skill. Move domain knowledge to agents. Have orchestrators reference sub-commands.

Anti-Patterns

Anti-patternImpactFix
Procedural overloadStep-by-step for capable agents wastes tokens, "lost in the middle"Declare goal + constraints, let agent apply methodology
Duplicated briefingsSame orchestrator constraints in every command (30-80 lines each)Extract to shared preamble, reference once
Embedded domain knowledgeRefactoring hierarchies, review criteria, TDD cycles in commandsMove to agent definitions or skills
Aggressive language"CRITICAL/MANDATORY/MUST" causes overtriggering in Opus 4.6Direct statements without emphasis markers
Example overload50+ lines of JSON examples2-3 canonical examples suffice
Inline validation logicPrompt template validation in command textPlatform/hook responsibility
Dead codeDeprecated formats, aspirational metrics, old signaturesRemove; version control preserves history
Verbose JSON state examples200+ lines of unused JSONShow actual format (pipe-delimited), 3 examples max

When Commands Should Contain Logic vs Delegate

Contain in command (declarative):

  1. Which agent to invoke
  2. What context files to read/pass
  3. Success criteria and quality gates
  4. Next wave handoff

Delegate to agent:

  1. Methodology (TDD phases, review criteria, refactoring levels)
  2. Domain-specific templates/schemas
  3. Tool-specific config (cosmic-ray, pytest)
  4. Quality assessment rubrics

Rule: if content describes HOW the agent does its work, it belongs in agent definition or skill, not command.

Canonical Examples

Example 1: Minimal Dispatcher (forge.md pattern, ~40 lines)
markdown
# 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
- [ ] 11-point validation checklist 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)
markdown
# 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:

markdown
# 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.

Show full SKILL.md (304 more words)Show less

Compression Guidelines

When optimizing command files for token efficiency:

Safe to compress:

  1. Prose descriptions → pipe-delimited
  2. Verbose explanations → imperative voice
  3. Filler words ("in order to", "it is important to") → remove
  4. Related bullet items → single line with | separators

Never compress:

  1. ### Example N: section headers — keep verbatim (eval tools and agents depend on these)
  2. AskUserQuestion decision tree options — these are runtime menu items, not documentation
  3. **Question**: lines in decision points — runtime behavior
  4. Code blocks and YAML — preserve verbatim
  5. YAML frontmatter — preserve exactly

Compression evidence: Pipe-delimited compression achieves 15-30% token reduction on prose-heavy files. Code-heavy files (PBT skills, code examples) yield <5%. Average across framework: ~7.4% overall.

Orchestrator skill loading section: Commands dispatching sub-agents must include SKILL_LOADING in the Task prompt reminding the agent to read its skills at ~/.claude/skills/nw-{skill-name}/SKILL.md. Without this, sub-agents operate without domain knowledge (the skills: frontmatter is decorative).

Command Installation Format (v2.8+)

Since v2.8.0, commands are installed as skills, not as separate command files. The installer reads from nWave/skills/nw-{command-name}/SKILL.md, NOT from nWave/tasks/nw/{command-name}.md. The legacy tasks/nw/*.md path is still supported but is NOT auto-installed.

When creating a new command, produce THREE files:

  1. nWave/skills/nw-{name}/SKILL.md — the installable command skill. Frontmatter MUST include:

    yaml
    ---
name: nw-{name}
description: "One-line description for slash command menu"
user-invocable: true
argument-hint: "[args] - Example: \"example usage\""
---

    Body: the full command definition (same content as the declarative template above).

  2. nWave/tasks/nw/{name}.md — legacy task file (kept for backward compat + reference). Same content, simpler frontmatter (just description + argument-hint).

  3. nWave/skills/nw-{name}-methodology/SKILL.md (optional) — deep methodology knowledge for the agent. Frontmatter:

    yaml
    ---
name: nw-{name}-methodology
description: "Methodology knowledge for {name}"
user-invocable: false
disable-model-invocation: true
---

The skill file (nWave/skills/nw-{name}/SKILL.md) is the PRIMARY deliverable. Without it, the command won't appear in the /nw- menu after installation. The task file is secondary.

Also update nWave/framework-catalog.yaml with the command entry under the appropriate wave section.

© nWave-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in nWave/skills/nw-command-design-patterns of nWave-ai/nWave.

Open the folder on GitHubat commit da401a8

Compare with similar skills

Nw Command Design Patterns 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 Command Design Patterns compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Nw Command Design Patterns this skillnWave-ai/nWave617—~2.4kAutomated safety check: PassMIT
Vercel Composition Patternssupabase/supabase111k59 repos~726Automated safety check: PassMIT
Swiftui View RefactorDimillian/Skills4k5 repos~2kAutomated safety check: PassMIT
RTK Rust Design Patternsrtk-ai/rtk83k—~1.9kAutomated safety check: PassApache-2.0
Effect Client WrapperUsefulSoftwareCo/executor4.1k1 repos~1.4kAutomated safety check: PassMIT
Architecture PatternsKartikLabhshetwar/better-shot2.4k2 repos~1.4kAutomated safety check: PassCustom licence

Similar skills

  • Vercel Composition Patterns

    supabase/supabase

    Official

    React composition patterns that scale. An agent skill from supabase/supabase.

    111k GitHub starsUsed in 59 repos~726 tokens
    DevelopmentAuto-check passed

  • Swiftui View Refactor

    Dimillian/Skills

    Refactor and review SwiftUI view files with strong defaults for small dedicated subviews, MV-over-MVVM data flow, stable view trees, explicit dependency injection, and correct Observation usage.

    4k GitHub starsUsed in 5 repos~2k tokens
    DevelopmentAuto-check passed

  • RTK Rust Design Patterns

    rtk-ai/rtk

    Describes seven Rust design patterns for the RTK CLI filter modules, with when to use each, RTK examples, and notes on when a pattern is overkill.

    83k GitHub stars~1.9k tokensUpdated today
    DevelopmentAuto-check passed

  • Effect Client Wrapper

    UsefulSoftwareCo/executor

    Pattern for wrapping third-party SDK clients (Stripe, Resend, AWS, etc.) with Effect.

    4.1k GitHub starsUsed in 1 repo~1.4k tokens
    DevelopmentAuto-check passed

  • Architecture Patterns

    KartikLabhshetwar/better-shot

    Deep dive into software architecture for macOS. An agent skill from KartikLabhshetwar/better-shot.

    2.4k GitHub starsUsed in 2 repos~1.4k tokens
    DevelopmentAuto-check passed

  • GitVersion .NET Development

    GitTools/GitVersion

    Gives repository-specific .NET guidance for GitVersion: build and test commands, central package management, project layout and coding conventions.

    3.1k GitHub stars~1.7k tokensUpdated today
    DevelopmentAuto-check passed

More from nWave-ai/nWave

All 106 skills in this repo

  • Nw Deliver Orchestration

    nWave-ai/nWave

    DELIVER wave orchestration workflow -- 9 phases from baseline to finalization.

    617 GitHub stars~974 tokensUpdated 21 days ago
    Auto-check passed

  • Nw Diagram

    nWave-ai/nWave

    Generates C4 architecture diagrams (context, container, component) in Mermaid or PlantUML.

    617 GitHub stars~640 tokensUpdated 21 days ago
    Auto-check passed

  • Nw Diverge

    nWave-ai/nWave

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

    617 GitHub stars~2.2k tokensUpdated 21 days ago
    Auto-check passed

  • Nw Document

    nWave-ai/nWave

    Creates evidence-based documentation following DIVIO/Diataxis principles.

    617 GitHub stars~1.4k tokensUpdated 21 days ago
    Auto-check passed

  • Nw Execute

    nWave-ai/nWave

    A skill your agent uses when a DELIVER roadmap already exists and you need to dispatch exactly one identified step through its TDD cycle.

    617 GitHub stars~3k tokensUpdated 21 days ago
    Auto-check passed

  • Nw Refactor

    nWave-ai/nWave

    Applies the Refactoring Priority Premise (RPP) levels L1-L6 for systematic code refactoring.

    617 GitHub stars~1.2k tokensUpdated 21 days ago
    Auto-check passed

Categories

Questions about Nw Command Design Patterns

What does Nw Command Design Patterns do?

Best practices for command definition files - size targets, declarative template, anti-patterns, and canonical examples based on research evidence. Nw Command Design Patterns is an agent skill from nWave-ai/nWave.

When should I use Nw Command Design Patterns?

Nw Command Design Patterns fits situations like: tasks that involve Design patterns.

How do I install Nw Command Design Patterns in Claude Code?

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

How do I install Nw Command Design Patterns in Codex?

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

Can I use Nw Command Design Patterns 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-command-design-patterns -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-command-design-patterns, .gemini/skills/nw-command-design-patterns, .github/skills/nw-command-design-patterns and .opencode/skills/nw-command-design-patterns in your project.

What does Nw Command Design Patterns need to run?

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

Does Nw Command Design Patterns 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 Command Design Patterns 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 Command Design Patterns use?

Nw Command Design Patterns 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 Command Design Patterns use?

About 2.4k tokens (SKILL.md is roughly 9.6k 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 Command Design Patterns?

Skills that share tags, products or a category with Nw Command Design Patterns: Vercel Composition Patterns (supabase/supabase, 111k stars), Swiftui View Refactor (Dimillian/Skills, 4k stars), RTK Rust Design Patterns (rtk-ai/rtk, 83k stars) and Effect Client Wrapper (UsefulSoftwareCo/executor, 4.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Nw Command Design Patterns?

nWave-ai (a GitHub organization) maintains it in nWave-ai/nWave, which has 617 GitHub stars. The repository holds 106 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.