team-combat

Orchestrates a multi-agent pipeline to design, implement, and validate game combat features.

Updated Aug 2, 2026
One-click install
npx skills add https://github.com/claretagrapelike32/codex-ai-game-studio --skill team-combat-claretagrapelike32
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: team-combat
Source: https://github.com/claretagrapelike32/codex-ai-game-studio/tree/main/plugins/ai-game-studio/skills/team-combat
Command: npx skills add https://github.com/claretagrapelike32/codex-ai-game-studio --skill team-combat-claretagrapelike32

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Building a game combat feature requires coordinating design, gameplay code, AI behavior, VFX, audio, and QA across multiple disciplines. This Skill orchestrates that entire workflow as a structured multi-agent pipeline so a combat feature goes from description to validated implementation without manual handoffs. ## Core Features & Use Cases - Phased Team Pipeline: Runs design, architecture, parallel implementation, integration, validation, and sign-off phases with specialized subagents (game-designer, gameplay-programmer, ai-programmer, technical-artist, sound-designer, qa-tester). - Engine Validation: Consults the project's pinned engine specialist (Godot, Unity, or Unreal) to verify architecture is idiomatic before implementation begins. - Configurable Review Modes: Supports full, lean, and solo review modes plus an error recovery protocol that surfaces blocked agents and offers skip, retry, or stop options. - Use Case: Describe a melee parry system, and the Skill produces a GDD section with formulas and edge cases, an approved architecture, parallel implementation of code, AI, VFX, and audio, plus QA test results and a final status verdict. ## Quick Start Use $ai-game-studio:team-combat to design and implement a melee parry system for this project.

Frequently Asked Questions about team-combat

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I implement a combat system with AI agents?

Invoke the skill with a combat feature description, such as a melee parry system. It runs a phased pipeline where a game-designer writes the design document, programmers implement code and AI, artists add VFX and audio, and a qa-tester validates the result.

What game engines does this combat workflow support?

The workflow supports Godot, Unity, and Unreal Engine. It reads the primary engine specialist from the project configuration and validates that the proposed architecture uses idiomatic patterns for the pinned engine version before implementation starts.

Can I skip review gates when orchestrating the combat team?

Yes, pass a review mode argument or set it in production/review-mode.txt. The lean mode skips director gates except phase gates, and solo mode skips all director gate spawning entirely.

What happens when a subagent gets blocked during implementation?

The error recovery protocol surfaces the blocked agent and reason immediately, checks whether later phases depend on its output, and offers options to skip with a noted gap, retry with narrower scope, or stop and resolve the blocker first.

Does the orchestrator write game code files directly?

No, all file writes are delegated to spawned subagents, each of which enforces a write-permission protocol. The orchestrator only coordinates phases, collects results, and produces the final summary report.