Nw Agent Creation Workflow Skill for Claude

Agent Creation Workflow

Overview

Create agents through 5 phases: ANALYZE -> DESIGN -> CREATE -> VALIDATE -> REFINE. Each phase has clear inputs, outputs, and quality gates. Follow "start minimal, add based on failure."

Phase 1: ANALYZE

Goal: Understand requirements and determine agent architecture.

Inputs: User requirements, use case description, existing codebase context.

Steps:

• Identify single clear responsibility
• Determine new agent or modification of existing
• Check overlap with existing agents (avoid duplication)
• Classify agent type:
• Specialist: Single-domain expert (most common)
• Reviewer: Validates outputs from another agent (Reflection pattern)
• Orchestrator: Coordinates multiple agents
• Identify required tools (start with Read, Glob, Grep -- add only what's needed)
• Determine if Skills needed (domain knowledge > 50 lines)

Gate: Single responsibility identified. Agent type classified. No overlap.

Output: Requirements summary with agent type, tools list, skill needs.

Phase 2: DESIGN

Goal: Design agent architecture and structure.

Inputs: Requirements summary from Phase 1.

Steps:

• Select design pattern (load design-patterns skill)
• Define role and goal (1-2 sentences each)
• Identify core principles that DIVERGE from Claude defaults:
• What must this agent do differently than Claude naturally would?
• Domain-specific methodology steps
• Non-obvious constraints | Project-specific conventions
• Design workflow (3-7 phases)
• Plan Skills extraction: domain knowledge -> separate Skill | Testing/validation -> separate Skill | Keep workflow and principles in core agent
• Design Skill Loading Strategy (required for 3+ skills):
• Map each skill to the workflow phase where it's needed
• Create a loading table: Phase → Skill → Trigger condition
• Add explicit Load: skill-name directives in each workflow phase
• Document path: ~/.claude/skills/nw-{skill-name}/SKILL.md (installed) or nWave/skills/nw-{skill-name}/SKILL.md (repo)
• Note: skills: in frontmatter is declarative only — Claude Code does NOT auto-load skill files. The agent must use Read tool to load them, triggered by Load: directives in workflow text.
• Draft frontmatter:

   ---
   name: {kebab-case-id}
   description: Use for {domain}. {When to delegate.}
   model: inherit
   tools: [{minimum tools needed}]
   maxTurns: 30
   skills:
     - nw-{skill-name}
   ---

Gate: Design fits ~200-300 lines (core) + Skills. Pattern selected. Frontmatter drafted.

Output: Agent architecture document (working notes, not deliverable).

Phase 3: CREATE

Goal: Write agent definition file and Skills.

Inputs: Design from Phase 2.

Steps:

• Create agent .md file:
• YAML frontmatter (name, description, tools, model, maxTurns, skills)
• Role + Goal paragraph
• Core Principles (divergences only, 3-8 items)
• Workflow phases
• Critical Rules (3-5, where violation causes real harm)
• Examples (3-5 canonical cases)
• Subagent mode instructions
• Constraints (what agent does NOT do)
• Create Skill files if needed: each in nWave/skills/{agent-name}/ | YAML frontmatter with name and description | Focused content, 100-250 lines each
• Measure: wc -l. Target: under 300 lines.

• Add Skill Loading Strategy section (required for agents with 3+ skills):

   ## Skill Loading Strategy

   Load on-demand by phase, not all at once:

   | Phase | Load | Trigger |
   |-------|------|---------|
   | 1 Phase Name | `skill-name` | Always — core methodology |
   | 2 Phase Name | `other-skill` | When condition is met |

   Skills path: `~/.claude/skills/nw-{skill-name}/SKILL.md` (installed) or `nWave/skills/nw-{skill-name}/SKILL.md` (repo)

• Add Load: directives at the start of each workflow phase referencing the applicable skills
• Verify: every skill in frontmatter skills: has at least one Load: directive in the workflow text. Orphan skills (declared but never loaded) are a bug.

Gate: Agent file created. Under 300 lines. Skills created if needed. Skill Loading Strategy present for 3+ skills.

Output: Agent .md file + Skill files.

Phase 4: VALIDATE

Goal: Verify agent meets quality standards.

Steps:

• Run 14-point validation checklist:
• [ ] Uses official YAML frontmatter format
• [ ] Total definition under 400 lines (domain knowledge in Skills)
• [ ] Only specifies behaviors diverging from Claude defaults
• [ ] No aggressive signaling language
• [ ] 3-5 canonical examples for critical behaviors
• [ ] Tools restricted to minimum needed
• [ ] maxTurns set in frontmatter
• [ ] Safety via platform features, not prose
• [ ] Instructions phrased affirmatively
• [ ] Consistent terminology throughout
• [ ] Description clearly states delegation criteria
• Check anti-patterns: no monolithic sections (>50 lines without structure) | No duplicated Claude defaults | No embedded safety frameworks | No aggressive language
• Test with representative inputs (Layer 1 testing)

Gate: All 14 items pass. No anti-patterns.

Output: Validation report (pass/fail per item).

Phase 5: REFINE

Goal: Iteratively improve based on testing feedback.

Steps:

• Address validation failures
• Test with edge cases
• Add instructions ONLY for observed failure modes: wrong decision -> add rule/example | Missed step -> clarify workflow | Over-generated -> add constraint
• Re-measure: wc -l. If approaching 400 lines, extract to Skills.
• Re-validate with 14-point checklist.

Gate: All validation passes. Line count within target. Edge cases handled.

Output: Final agent definition, ready for installation.

Quality Gates Summary

| Phase | Gate | Blocks |

|-------|------|--------|

| ANALYZE | Single responsibility, no overlap | DESIGN |

| DESIGN | Architecture fits size target | CREATE |

| CREATE | File created, under 300 lines | VALIDATE |

| VALIDATE | 14-point checklist passes | REFINE/Deploy |

| REFINE | Edge cases handled, within target | Deploy |

Naming Conventions

• Agent files: nw-{name}.md in nWave/agents/
• Skill files: {skill-name}.md in nWave/skills/{agent-name}/
• Reviewer agents: nw-{name}-reviewer.md
• Agent names in frontmatter: nw-{name} (kebab-case with nw- prefix)

Reviewer Agent Creation (Special Case)

Reviewer agents pair with a primary agent and use the Reflection pattern:

• Set model: haiku in frontmatter (cost-efficient review)
• Use same tools as primary agent (no Write/Edit -- reviewers don't modify)
• Define structured critique output format (YAML)
• Include max 2 review iterations
• Define clear approval/rejection criteria