docs(agent-development): enhance content completeness and documentation

[sjnims]

Summary

Several documentation enhancements would improve the agent-development skill's completeness and usability.

Proposed Changes

1. Add Model Selection Guidance (Medium Priority)

Location: Lines 143-154 (model field section)

Current: Lists options but doesn't explain when to choose each.

Proposed addition:

**When to choose:**
- `haiku` - Fast, simple tasks; quick analysis; cost-sensitive operations
- `sonnet` - Balanced performance; most use cases (default recommendation)
- `opus` - Complex reasoning; detailed analysis; highest capability needed

2. Enrich "Additional Resources" Section (Medium Priority)

Location: Lines 405-428

Current: Lists files without describing contents.

Proposed: Add 1-line descriptions:

### Reference Files

For detailed guidance, consult:

- **`references/system-prompt-design.md`** - Four system prompt patterns (Analysis, Generation, Validation, Orchestration) with complete templates and common pitfalls
- **`references/triggering-examples.md`** - Example block anatomy, four example types, template library, and debugging guide
- **`references/agent-creation-system-prompt.md`** - The exact prompt used by Claude Code's agent generation feature with usage patterns

3. Add Full Script Path in Workflow (Medium Priority)

Location: Line 437 in "Implementation Workflow"

Current: 7. Validate with \scripts/validate-agent.sh``

Proposed: 7. Validate with \./skills/agent-development/scripts/validate-agent.sh agents/your-agent.md``

4. Note Skills vs Agents Tool Field Difference (Low Priority)

Location: Quick Reference section or Frontmatter Fields section

Proposed addition:

> **Note:** Agents use `tools` to restrict tool access. Skills use `allowed-tools` for the same purpose. The field names differ between component types.

Rationale

These enhancements improve:

• Discoverability: Users understand what each reference file provides
• Actionability: Full paths make commands copy-pasteable
• Completeness: Model guidance helps users make informed choices
• Clarity: Tool field naming difference prevents confusion

Acceptance Criteria

• Model selection guidance added with clear use cases
• Additional Resources section includes brief file descriptions
• Workflow section includes full, runnable script path
• Note about tools vs allowed-tools added
• Word count remains in ideal range (currently 1,623 words; target <2,000)

Related

• Identified during comprehensive skill review against Claude Code plugin best practices

[sjnims]

PR submitted: #22