Agent skill
request-patterns
Patterns for classifying and routing game development requests to expert agents. Use when parsing vague requests like "improve the game", "fix bugs", "make it better", or multi-domain requests needing intelligent dispatch. **Load references when:** - Request routing tables → `references/routing-tables.md` - Quality agent selection → `references/quality-agents.md` - Orchestrator selection → `references/orchestrators.md`
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/request-patterns
SKILL.md
Request Patterns
Route game development requests to the right expert agents.
Classification Flow
- Identify type: Quality / Bug / Feature / Discovery / Asset / Review
- Identify scope: Single-domain or multi-domain
- Route: Direct to agent, or decompose first
Request Types
| Type | Trigger Phrases | Primary Action |
|---|---|---|
| Quality | "improve", "better", "polish" | Analyze → Fix |
| Bug | "fix", "broken", "doesn't work" | Categorize → Route |
| Feature | "add", "implement", "create" | Check GDD → Implement |
| Discovery | "what's missing", "status" | project-health-monitor |
| Asset | "generate", "create asset" | Design → Generate → Integrate |
| Review | "review", "check", "audit" | Route to appropriate director |
Vague Request Handling
Ask clarifying questions before routing:
- "Make it better": What feels wrong? (gameplay/visuals/audio/performance)
- "Fix bugs": What symptoms? When does it happen?
- "Improve quality": Which assets? What aspect?
Multi-Domain Decomposition
For requests spanning domains:
- Identify all domains involved
- Check dependencies (design → generate → integrate)
- Parallelize independent tasks
- Verify each domain
Quick Agent Reference
Analysis: project-health-monitor, gdd-implementation-tracker, completion-auditor
Direction: creative-director, art-director, sound-director, tech-director
Implementation: feature-implementer, code-scaffolder, integration-assistant
Assets: asset-designer, asset-generator, character-generator, sfx-architect, music-architect
Validation: rollback-reviewer, release-validator, test-runner
For full routing tables, load references/routing-tables.md.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?