Large-scale parallel implementation with multi-agent swarm. Architect + QA + Implementer(s) collaborate via peer DM. Use when user mentions 大規模実装, 並列実装, swarm, チーム実装.
From shipnpx claudepluginhub thkt/dotclaude --plugin toolkitThis skill is limited to using the following tools:
reference.mdProvides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
Calculates TAM/SAM/SOM using top-down, bottom-up, and value theory methodologies for market sizing, revenue estimation, and startup validation.
Multi-agent swarm for large-scale implementation. Use /code for tasks under 5 files.
Use /swarm when ANY condition applies. Otherwise use /code.
| Condition | /swarm |
|---|---|
| Files >= 5 | Yes |
| Multi-domain | Yes |
| Design decisions many | Yes |
Leader does NOT do substantive work:
Leader ONLY:
All substantive work happens through peer DM between Architect, QA, and Implementer(s).
Implementation description: $1 (required, prompt if empty)
[@../skills/lib/sow-resolution.md]
| Agent | subagent_type | Responsibility | Bash | SendMessage | Model |
|---|---|---|---|---|---|
| Leader | (self) | User interface, QG, lifecycle | Yes | broadcast | opus |
| Architect | feature-architect | Codebase analysis, contracts | No | peer DM | opus |
| QA | qa-reviewer | Quality observations (non-blocking) | No | peer DM | sonnet |
| Implementer(s) | unit-implementer | RGRC implementation | Yes | peer DM | opus |
Haiku is excluded from team agents — it cannot reliably follow multi-step instructions or handle the shutdown protocol. The Model column in Team Architecture defines each agent's model.
Peer DM transport with defined handoff structures: Spawn Context, Architect Output, Implementer Started/Assignment/Completion.
→ Templates and response rules: reference.md
$1 is sole instructionTeamCreate with name swarm-{timestamp}$1 implementation descriptionsubagent_type: test-generator, run_in_background: true)TaskOutputTaskOutputparallel_units (mechanical — no
analysis):
mode: "dontAsk" (worktree isolation provides safety for autonomous Bash)started DM from each Implementer (receipt confirmation)
started DM within 120s → shutdown, re-spawn same assignment (max 1
retry → escalate to user)git -C <worktree-path> statusgit merge or update branchgit diff --name-only against Spec
## Implementation file list. New test files and config files are exemptshutdown_request)TeamDelete for cleanup| Scenario | Action |
|---|---|
| User cancels | shutdown_request to all agents, TeamDelete |
| Contract fundamentally wrong | Shutdown Implementers → Architect redesign |
| Implementer no started DM | 120s timeout → shutdown → re-spawn (max 1 retry → user) |
| Implementer death mid-work | Leader checks worktree via git status → re-spawn (max 1 retry) |
| QG fails 3 times | Escalate to user with details |
| Agent Bash permission block | Use mode: "dontAsk" for worktree-isolated Implementers |
| test-gen timeout | Leader generates tests directly |
| test-gen produces 0 tests | Verify spec exists, ask user |
| Shutdown unresponsive | Retry with explicit tool params → move team dir to ~/.Trash/ |
Leader reports progress table at key events (Phase 3 start, Implementer started/completion, merge/QG results).
→ Display format and trigger events: reference.md
→ Recovery procedures by phase: reference.md