菜单
Orchestrate Agent Teams with registry-routed teammates, module-aware context, and manifest-derived file ownership. Use for parallel research, implementation, review, and debug workflows.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Asset Hunter Pro — unused asset detection, dependency graph, duplicate finder, project cleanup automation for Unity
Practical tools and validation methods for game balance — DPS calculators, EHP formulas, spreadsheet layouts, stat audits, difficulty spike detection
GDD structure, templates, and living documentation patterns for game projects — wiki pages, design docs, section layout, sync triggers
Game feel and juice — screen shake, hit stop, particles, animation curves, input responsiveness, feedback timing. Makes actions feel satisfying.
Mobile game design patterns — session design, retention mechanics, notification strategy, portrait/landscape, battery/thermal constraints, FTUE
Create or update TheOneKit agent .md files with canonical structure. Use when adding a new agent, updating maxTurns/model, or fixing frontmatter fields.
| name | t1k:team |
| description | Orchestrate Agent Teams with registry-routed teammates, module-aware context, and manifest-derived file ownership. Use for parallel research, implementation, review, and debug workflows. |
| version | 2.0.0 |
| argument-hint | <template> <context> [--devs|--researchers|--reviewers|--debuggers N] [--delegate] |
| effort | high |
| context | fork |
| origin | theonekit-core |
| repository | The1Studio/theonekit-core |
| module | null |
| protected | true |
Orchestrate parallel Claude Code Agent Teams with T1K infrastructure: registry-routed agents, module-scoped skill injection, manifest-derived file ownership, mandatory worktree isolation.
Requires: CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 in settings.json env.
Requires: CLI terminal — Agent Teams tools are disabled in VSCode extension.
Model: All teammates run Opus 4.6 (Agent Teams constraint).
Follow protocol: rules/routing-protocol.md
Templates resolve roles dynamically: researcher, implementer, reviewer, debugger, tester, planner
| Template | Purpose | Risk | Reference |
|---|---|---|---|
research | N researchers, module-scoped angles | Low (read-only) | references/research-template.md |
review | N reviewers, registry-routed, module boundary checks | Low (read-only) | references/review-template.md |
cook | N implementers, worktree-isolated, manifest ownership | Medium (writes code) | references/cook-template.md |
debug | N debuggers, adversarial hypotheses, worktree-isolated | Medium (may add debug code) | references/debug-template.md |
triage | Parallel issue/PR processing across kit repos | Low (read + GitHub API) | references/triage-template.md |
| Flag | Default | Description |
|---|---|---|
--researchers N | 3 | Number of researchers |
--reviewers N | 3 | Number of reviewers |
--devs N | auto | Number of devs (auto = one per module) |
--debuggers N | 3 | Number of debuggers |
--delegate | off | Lead only coordinates, never touches code |
--no-plan-approval | off | Skip plan approval gate (cook template) |
TeamCreate — if it fails, STOP: "Agent Teams requires CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1."rules/routing-protocol.mdrules/module-detection-protocol.mdreferences/manifest-ownership-resolution.mdrules/subagent-injection-protocol.mdEvery teammate spawn prompt MUST include the T1K Context Block: references/t1k-context-block.md
When activated, IMMEDIATELY execute the matching template sequence. Do NOT ask for confirmation. Execute tool calls in order. Report after each major step.
Details on all operational protocols: references/team-operations.md
| Scenario | Subagents | Agent Teams |
|---|---|---|
| Focused single task | Yes | Overkill |
| Sequential chain | Yes | No |
| 3+ independent parallel workstreams | Maybe | Yes |
| Competing debug hypotheses | No | Yes |
| Cross-module implementation | Maybe | Yes |
| Token budget is tight | Yes | No |