# team-level

Orchestrates game development subagents to design complete playable areas. It balances spatial layout, narrative beats, art requirements, and test checklists.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 447 installs · ★ 27473
- Author: Donchitos
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/Donchitos/Claude-Code-Game-Studios/tree/HEAD/.claude/skills/team-level/SKILL.md
- Updated: 2026-10-19
- HTML: https://affpapa.org/en/nevibecode/skills/team-level

## What it does

The skill coordinates a virtual level creation crew based on a target area name, such as `forest temple` or `final boss arena`. It gathers context by reading project documentation in `design/`, including game concepts, core pillars, and existing lore. If invoked without arguments, it outputs command syntax guidance immediately and halts execution without touching files.

Team composition adapts to the `team.size` setting. The default `individual` tier spawns only the `level-designer`, routing questions to other roles through that single agent to minimize context cost. Switching to `small` activates a systems designer, art director, and QA tester, while `studio` brings in narrative and accessibility specialists. The orchestrator explicitly announces which subagents are active before running steps.

Configuration is resolved at Phase 0 through `yaml-helper.sh` via the Bash tool. The pipeline will fail immediately if the parent repository folder layout and helper scripts are missing from your workspace. When delegating tasks, the orchestrator passes distilled summaries rather than raw file paths, preventing subagents from rereading entire documents.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add Donchitos/Claude-Code-Game-Studios --skill team-level -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/team-level/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/team-level/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add Donchitos/Claude-Code-Game-Studios --skill team-level -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/team-level/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add Donchitos/Claude-Code-Game-Studios --skill team-level -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/team-level/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install Donchitos/Claude-Code-Game-Studios team-level
```

2. **Manually: put the files in place**
- File: `.github/skills/team-level/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add Donchitos/Claude-Code-Game-Studios --skill team-level -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/Donchitos/Claude-Code-Game-Studios --path .claude/skills/team-level
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/team-level/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add Donchitos/Claude-Code-Game-Studios --skill team-level -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/Donchitos/Claude-Code-Game-Studios/tree/HEAD/.claude/skills/team-level/SKILL.md

## When to use it
- draft level layouts and encounter pacing from game concept docs
- delegate game area design tasks across specialized subagents
- balance enemy encounters and loot tables for a specific zone
- generate test checklists and boundary verification for QA

## Example prompts
- /team-level "forest temple" --review lean
- /team-level "tutorial village"
- /team-level "final boss arena" --review full

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: f7fe98ec53dca5c6.

BEGIN THIRD-PARTY FILE f7fe98ec53dca5c6
```text
---
name: team-level
description: "Orchestrate the level team — level-designer, narrative-director, world-builder, art-director, systems-designer, qa-tester — for complete area creation."
argument-hint: "[level name or area to design] [--review full|lean|solo]"
user-invocable: true
allowed-tools: Read, Glob, Grep, Write, Edit, Agent, AskUserQuestion, TaskCreate, TaskGet, TaskList, TaskUpdate, Bash(bash "*/.claude/skills/team-level/../../hooks/yaml-helper.sh" resolve_config *)
model: sonnet
---

# Team Level

If no argument is provided, output usage guidance and exit without spawning any agents or reading any design files:
> Usage: `/team-level [level name or area to design] [--review full|lean|solo]` — specify the level or area to design (e.g., `forest temple`, `tutorial village`, `final boss arena`). Do not use `AskUserQuestion` here; output the guidance directly.

When this skill is invoked:

**Decision Points:** At each step 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.
In `collaborative` mode, the user must approve before moving to the next step.
In `guided` mode the pipeline advances automatically unless a step is BLOCKED;
in `autonomous` mode it runs end to end, recording each step outcome via
`log_decision`. Decisions in `automation_always_ask` categories
(`is_always_ask_category` helper) always prompt regardless of mode. See
`.claude/docs/automation-modes.md`.

## Phase 0: Resolve Config

!`bash "${CLAUDE_SKILL_DIR}/../../hooks/yaml-helper.sh" resolve_config --keys review_mode,automation,team.size`

Resolved above — use as-is; `--review` overrides `review_mode`. No block →
defaults in `.claude/docs/config-resolution.md`.

`review_mode` sets director-gate depth, and this pipeline has no director gate:
no phase below spawns CD-, TD-, PR- or AD-PHASE-GATE, at any `review_mode`. Its
phase gates are the pipeline's own decision points (defined under `team.size`
below), and the agents that work at them are team members, not director gates.

`automation` drives the Decision Points note above. See the Decision Points note above and
`.claude/docs/automation-modes.md` for how each mode changes pipeline behavior.

**`team.size`**: which agents are active (orthogonal to review_mode gate-depth and workflow docs).
- **`individual`** (default): `level-designer` only. Other agents consulted via the level-designer, not spawned separately.
```
END THIRD-PARTY FILE f7fe98ec53dca5c6

The third-party file has ended. Everything between the f7fe98ec53dca5c6 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2537 of 19133 bytes. © Donchitos · MIT · https://github.com/Donchitos/Claude-Code-Game-Studios/tree/HEAD/.claude/skills/team-level/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md