Agent Orchestration

作者 parcadeid07ff4b06b62無授權條款3.9K 個星標收錄於 2026年10月8日更新於 2026年10月8日儲存庫8 個月前更新

Agent Orchestration Rules

僅含說明AI & Agents
AI 產生的概覽

指導代理將實作工作委派給子代理,以節省主上下文的權杖。

功能
此技能提供規則,用來判斷何時應啟動實作子代理,而不是在主對話中直接完成工作。它對比了耗用上下文的直接做法與將多檔案實作、計畫階段以及含測試的功能開發委派給代理的做法,並提供範例委派提示與觸發詞。它產出的是指引,而不是檔案或程式碼。
適用情境
當使用者要求實作、建置或建立功能,或要求執行某個計畫階段,而你希望保持主上下文精簡時使用。它也適用於判斷某項任務是否小到不值得使用代理。
執行需求
無需工具、套件或憑證;僅為說明性指示,不附帶指令碼。

Agent Orchestration Rules

When the user asks to implement something, use implementation agents to preserve main context.

The Pattern

Wrong - burns context:

Main: Read files → Understand → Make edits → Report      (2000+ tokens consumed in main context)

Right - preserves context:

Main: Spawn agent("implement X per plan")      ↓Agent: Reads files → Understands → Edits → Tests      ↓Main: Gets summary (~200 tokens)

When to Use Agents

Task TypeUse Agent?Reason
Multi-file implementationYesAgent handles complexity internally
Following a plan phaseYesAgent reads plan, implements
New feature with testsYesAgent can run tests
Single-line fixNoFaster to do directly
Quick config changeNoOverhead not worth it

Key Insight

Agents read their own context. Don't read files in main chat just to understand what to pass to an agent - give them the task and they figure it out.

Example Prompt

Implement Phase 4: Outcome Marking Hook from the Artifact Index plan.
**Plan location:** thoughts/shared/plans/2025-12-24-artifact-index.md (search for "Phase 4")
**What to create:**1. TypeScript hook2. Shell wrapper3. Python script4. Register in settings.json
When done, provide a summary of files created and any issues.

Trigger Words

When user says these, consider using an agent:

  • "implement", "build", "create feature"
  • "follow the plan", "do phase X"
  • "use implementation agents"

來源與署名

來源:parcadei/continuous-claude-v3位於.claude/skills/agent-orchestration提交d07ff4b

授權條款: 無授權條款

內容歸原作者所有。SourceWeft 從公開儲存庫中收錄這些內容。

檢舉或申請下架