Orchestrate the combat team: coordinates game-designer, gameplay-programmer, ai-programmer, technical-artist, sound-designer, and qa-tester to design, implement, and validate a combat feature end-to-end.
"Usage:
/team-combat [combat feature description]— Provide a description of the combat feature to design and implement (e.g.,melee parry system,ranged weapon spread)." Then stop immediately without spawning any subagents or reading any files.
When this skill is invoked with a valid argument, orchestrate the combat team through a structured pipeline.
Decision Points: At each phase transition, use AskUserQuestion to present
the user with the subagent's proposals as selectable options. Write the agent's
full analysis in conversation, then capture the decision with concise labels.
The user must approve before moving to the next phase.
.claude/docs/technical-preferences.md Engine Specialists section)Use the Task tool to spawn each team member as a subagent:
subagent_type: game-designer — Design the mechanic, define formulas and edge casessubagent_type: gameplay-programmer — Implement the core gameplay codesubagent_type: ai-programmer — Implement NPC/enemy AI behaviorsubagent_type: technical-artist — Create VFX, shader effects, visual feedbacksubagent_type: sound-designer — Define audio events, impact sounds, ambient audiosubagent_type: [primary engine specialist] — Engine idiom validation for architecture and implementationsubagent_type: qa-tester — Write test cases and validate implementationAlways provide full context in each agent's prompt (design doc path, relevant code files, constraints). Launch independent agents in parallel where the pipeline allows it (e.g., Phase 3 agents can run simultaneously).
Delegate to game-designer:
design/gdd/ covering: mechanic overview, player fantasy, detailed rules, formulas with variable definitions, edge cases, dependencies, tuning knobs with safe ranges, and acceptance criteriaDelegate to gameplay-programmer (with ai-programmer if AI is involved):
Then spawn the primary engine specialist to validate the proposed architecture:
Delegate in parallel:
Delegate to qa-tester:
If any spawned agent (via Task) returns BLOCKED, errors, or cannot complete:
Common blockers:
/architecture-decision first/create-storiesAll file writes (design documents, implementation files, test cases) are delegated to sub-agents spawned via Task. Each sub-agent enforces the "May I write to [path]?" protocol. This orchestrator does not write files directly.
A summary report covering: design completion status, implementation status per team member, test results, and any open issues.
Verdict: COMPLETE — combat feature designed, implemented, and validated. Verdict: BLOCKED — one or more phases could not complete; partial report produced with unresolved items listed.
/code-review on the implemented combat code before closing stories./balance-check to validate combat formulas and tuning values./team-polish if VFX, audio, or performance polish is needed.