القائمة
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Use when an HTML UI beats terminal text — collecting structured answers (decision trees, multi-select, code/SQL fields), showing visual comparisons or mockups, running interactive demos, or presenting decisions for approval. A local browser companion renders markdown+YAML screens and streams the user's answers back. Use when: many questions at once, layout/visual choices, mockup or diagram feedback, config wizard, demo review, approve/revise decisions. Skip: a single quick question (use AskUserQuestion or plain text).
Use when you have a spec or requirements for a multi-step task, before touching code
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
| name | dispatching-parallel-agents |
| description | Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies |
委任務於特化 agent，孤立 context。精工其 instruction 與 context，使專注成事。勿令承汝 session 之歷史——汝構其所需。此亦保汝 context 於協調之務。
多失敗而無關（異測檔、異子系統、異 bug），序查耗時。每查獨立，可並行。
核心原則： 每獨立問題域派一 agent。使其並行。
digraph when_to_use {
"Multiple failures?" [shape=diamond];
"Are they independent?" [shape=diamond];
"Single agent investigates all" [shape=box];
"One agent per problem domain" [shape=box];
"Can they work in parallel?" [shape=diamond];
"Sequential agents" [shape=box];
"Parallel dispatch" [shape=box];
"Multiple failures?" -> "Are they independent?" [label="yes"];
"Are they independent?" -> "Single agent investigates all" [label="no - related"];
"Are they independent?" -> "Can they work in parallel?" [label="yes"];
"Can they work in parallel?" -> "Parallel dispatch" [label="yes"];
"Can they work in parallel?" -> "Sequential agents" [label="no - shared state"];
}
用於：
不用於：
以所斷分失敗：
每域獨立——修 tool approval 不影 abort 測。
每 agent 獲：
// In Claude Code / AI environment
Task("Fix agent-tool-abort.test.ts failures")
Task("Fix batch-completion-behavior.test.ts failures")
Task("Fix tool-approval-race-conditions.test.ts failures")
// All three run concurrently
Agent 返時：
善 agent prompt：
Fix the 3 failing tests in src/agents/agent-tool-abort.test.ts:
1. "should abort tool with partial output capture" - expects 'interrupted at' in message
2. "should handle mixed completed and aborted tools" - fast tool aborted instead of completed
3. "should properly track pendingToolCount" - expects 3 results but gets 0
These are timing/race condition issues. Your task:
1. Read the test file and understand what each test verifies
2. Identify root cause - timing issues or actual bugs?
3. Fix by:
- Replacing arbitrary timeouts with event-based waiting
- Fixing bugs in abort implementation if found
- Adjusting test expectations if testing changed behavior
Do NOT just increase timeouts - find the real issue.
Return: Summary of what you found and what you fixed.
❌ 過廣： "Fix all the tests" - agent 迷 ✅ 具體： "Fix agent-tool-abort.test.ts" - 範圍明
❌ 無 context： "Fix the race condition" - agent 不知何處 ✅ 有 context： 貼錯訊與測名
❌ 無限制： agent 或重構所有 ✅ 有限制： "Do NOT change production code" 或 "Fix tests only"
❌ 輸出模糊： "Fix it" - 汝不知何變 ✅ 具體： "Return summary of root cause and changes"
相關失敗： 修一或修他——先合查 需全 context： 理解需見全系統 探索性 debug： 汝未知何斷 共享 state： agent 互擾（編同檔、用同資源）
情境： 大重構後 3 檔 6 測失敗
失敗：
決： 域獨——abort 邏輯與 batch completion 與 race condition 分
派：
Agent 1 → Fix agent-tool-abort.test.ts
Agent 2 → Fix batch-completion-behavior.test.ts
Agent 3 → Fix tool-approval-race-conditions.test.ts
果：
整合： 所修獨，無衝，全套綠
省時： 3 問並行 vs 序
Agent 返後：
From debugging session (2025-10-03):