一键导入
coordinate
Advanced multi-agent coordination with parallel dispatch and synthesis. Use for complex tasks requiring multiple specialist perspectives.
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。
菜单
Advanced multi-agent coordination with parallel dispatch and synthesis. Use for complex tasks requiring multiple specialist perspectives.
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
Analyzes user's requests, determines tech stack, plans structure, and coordinates agents.
Apply consistent changes across many files at once. One pattern, many targets.
**MANDATORY:** Use for complex/vague requests, new features, updates.
Reduce AI token usage by **6.8x average** (up to **49x** on monorepos) by giving the AI a structural map of your codebase instead of letting it read everything.
Keep sessions productive by compressing completed work while preserving key decisions.
Distilled from production-proven coordinator patterns. Transforms sequential agent chains into intelligent parallel orchestration.
| name | coordinate |
| description | Advanced multi-agent coordination with parallel dispatch and synthesis. Use for complex tasks requiring multiple specialist perspectives. |
$ARGUMENTS
.agent/skills/coordinator-mode/SKILL.md firstUse the orchestrator agent with this context:
CONTEXT:
- User Request: $ARGUMENTS
- Mode: COORDINATOR (advanced orchestration)
- Skill: Load coordinator-mode skill for patterns
WORKFLOW:
1. DECOMPOSE the request into worker subtasks
2. CLASSIFY each subtask: Research | Implementation | Verification
3. DISPATCH workers (parallel for reads, sequential for writes)
4. SYNTHESIZE results — don't copy-paste, add insight
5. VERIFY completeness before reporting to user
RULES:
1. Follow coordinator-mode/SKILL.md protocol
2. Brief workers like smart colleagues — full context, specific scope
3. Never write "based on your findings, fix it" — prove YOU understood
4. Start with 2-3 workers, add more after synthesis if needed
5. Research before implementation — ALWAYS
| Deliverable | Description |
|---|---|
| Worker Dispatch | List of agents invoked with task descriptions |
| Synthesis Report | Consolidated findings with YOUR analysis |
| Action Items | Specific next steps with file paths |
[OK] Coordination complete
Agents dispatched: [count]
Phases completed: Research → Synthesis → [Implementation] → [Verification]
Key findings:
- [Finding 1]
- [Finding 2]
Next steps:
- [ ] [Action item 1]
- [ ] [Action item 2]
Generated by Agent Bridge