nw-forge
Creates new specialized agents using the 5-phase workflow (ANALYZE > DESIGN > CREATE > VALIDATE > REFINE). Use when building a new AI agent or validating an existing agent specification.
Best use case
nw-forge is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Creates new specialized agents using the 5-phase workflow (ANALYZE > DESIGN > CREATE > VALIDATE > REFINE). Use when building a new AI agent or validating an existing agent specification.
Teams using nw-forge should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/nw-forge/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How nw-forge Compares
| Feature / Agent | nw-forge | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Creates new specialized agents using the 5-phase workflow (ANALYZE > DESIGN > CREATE > VALIDATE > REFINE). Use when building a new AI agent or validating an existing agent specification.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# NW-FORGE: Create Agent (V2)
**Wave**: CROSS_WAVE
**Agent**: Zeus (nw-agent-builder)
## Overview
Create a new agent using research-validated v2 approach: focused core (200-400 lines) with Skills for domain knowledge.
1. **ANALYZE** — Identify single clear responsibility, check overlap with existing agents, classify type, determine minimum tools needed. Gate: responsibility defined, no overlap, classification chosen.
2. **DESIGN** — Select design pattern, define role and divergent principles, plan Skills extraction, draft frontmatter. Gate: pattern selected, principles drafted, frontmatter ready.
3. **CREATE** — Write agent `.md` using template. Workflow must be numbered task list. Create Skill files if domain knowledge exceeds 50 lines. Gate: agent file written, line count under 400.
4. **VALIDATE** — Run 14-point validation checklist. Check for anti-patterns. Verify workflow is numbered task list, not prose. Gate: all 14 items pass, zero anti-patterns.
5. **REFINE** — Address validation failures. Add instructions only for observed failure modes. Re-measure and re-validate. Gate: all items pass, line count reported.
## Agent Invocation
@nw-agent-builder
Execute \*forge to create {agent-name} agent.
**Configuration:**
- agent_type: specialist | reviewer | orchestrator
- design_pattern: react | reflection | router | planning | sequential | parallel | hierarchical
## Success Criteria
- [ ] Agent definition under 400 lines (`wc -l`)
- [ ] Official YAML frontmatter format (name, description, tools, maxTurns)
- [ ] 11-point validation checklist passes
- [ ] Only divergent behaviors specified (no Claude defaults)
- [ ] 3-5 canonical examples included
- [ ] Domain knowledge extracted to Skills if >50 lines
- [ ] No aggressive language (no CRITICAL/MANDATORY/ABSOLUTE)
- [ ] Safety via platform features (frontmatter/hooks), not prose
## Next Wave
**Handoff To**: Agent installation and deployment
**Deliverables**: Agent specification file + Skill files (if any)
## Expected Outputs
```
~/.claude/agents/nw/nw-{agent-name}.md
~/.claude/skills/nw-{skill-name}/SKILL.md*.md (if Skills needed)
```Related Skills
nw-ux-web-patterns
Web UI design patterns for product owners. Load when designing web application interfaces, writing web-specific acceptance criteria, or evaluating responsive designs.
nw-ux-tui-patterns
Terminal UI and CLI design patterns for product owners. Load when designing command-line tools, interactive terminal applications, or writing CLI-specific acceptance criteria.
nw-ux-principles
Core UX principles for product owners. Load when evaluating interface designs, writing acceptance criteria with UX requirements, or reviewing wireframes and mockups.
nw-ux-emotional-design
Emotional design and delight patterns for product owners. Load when designing onboarding flows, empty states, first-run experiences, or evaluating the emotional quality of an interface.
nw-ux-desktop-patterns
Desktop application UI patterns for product owners. Load when designing native or cross-platform desktop applications, writing desktop-specific acceptance criteria, or evaluating panel layouts and keyboard workflows.
nw-user-story-mapping
User story mapping for backlog management and outcome-based prioritization. Load during Phase 2.5 (User Story Mapping) to produce story-map.md and prioritization.md.
nw-tr-review-criteria
Review dimensions and scoring for root cause analysis quality assessment
nw-tlaplus-verification
TLA+ formal verification for design correctness and PBT pipeline integration
nw-test-refactoring-catalog
Detailed refactoring mechanics with step-by-step procedures, and test code smell catalog with detection patterns and before/after examples
nw-test-organization-conventions
Test directory structure patterns by architecture style, language conventions, naming rules, and fixture placement. Decision tree for selecting test organization strategy.
nw-test-design-mandates
Four design mandates for acceptance tests - hexagonal boundary enforcement, business language abstraction, user journey completeness, walking skeleton strategy, and pure function extraction
nw-tdd-review-enforcement
Test design mandate enforcement, test budget validation, 5-phase TDD validation, and external validity checks for the software crafter reviewer