Team Combat Orchestrator
Coordinates a multi-agent team to design, implement and test a game combat feature
- Repository
- Donchitos/Claude-Code-Game-Studios
- Stars
- 32,965
- Licence
- MIT
- Files
- 1 file
What it does
When invoked with a combat feature description, this skill tells the agent to run a structured pipeline that mimics a game studio combat team. It moves through design, implementation and validation phases, asking the user to choose between options at each transition, and delegates parts of the work to role-specific subagents such as a game designer, gameplay programmer, AI programmer, technical artist, sound designer and QA tester. It is aimed at people building games using the wider Claude Code Game Studios framework, and it depends on that framework's config, hook and documentation files, which are not included in this skill folder.
Great for
- Game developers using the Claude Code Game Studios framework who want a combat feature designed and implemented in stages
- Solo developers who want a structured design-to-test checklist for a mechanic like a melee parry or ranged spread
Skip it if
- Non-game projects, since the pipeline and roles are specific to game development
- Users without the surrounding framework (hooks, config and docs files it references), because the referenced helper scripts and config will be missing and the pipeline will not run as written
Try asking
- “/team-combat melee parry system”
- “/team-combat ranged weapon spread --review lean”
- “/team-combat enemy dodge behaviour with hit feedback --review full”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 1 original files, the MIT licence and an attribution note.
team-combat.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip team-combat.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip team-combat.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Give a specific feature description, such as the mechanic and its key rules, because the skill refuses to run without one
- Use --review lean or the default team size for small features to limit token use, since the pipeline spawns many subagents at larger team sizes
- Check the announced active set of agents before the run starts so you know which roles are actually spawned
What's inside
- SKILL.md
Redistributed unmodified from Donchitos/Claude-Code-Game-Studios under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.