- name
SKILL.md
技能檔案保留在發布者的儲存庫中。
在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add GanyuanRan/Aegis --skill dispatching-parallel-agents -a cursor -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add GanyuanRan/Aegis --skill dispatching-parallel-agents -a claude-code -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add GanyuanRan/Aegis --skill dispatching-parallel-agents -a codex -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add GanyuanRan/Aegis --skill dispatching-parallel-agents -a grok -y在 Grok Bot 聊天中傳送複製的訊息。Bot 會從 GitHub 取得這個 SKILL.md,並加入你所有 Bot 共用的技能中。
Install this skill: https://github.com/GanyuanRan/Aegis/tree/HEAD/skills/dispatching-parallel-agents來自發布者
Use parallel children for two or more ad-hoc, bounded tasks only when their independence is already credible and concurrency is worth the coordination. Parallelism changes elapsed time; it does not relax evidence, ownership, or completion requirements.
Dispatch only when all are true:
2+ distinct tasks or evidence questions;Keep work inline when decomposition is still exploratory, failures may share a
root cause, full-system context is required, or tasks are too small to repay the
handoff. A written implementation plan routes to
aegis:subagent-driven-development, not this ad-hoc workflow.
Choose the live host's context inheritance mode deliberately. Give each child the minimum sufficient instructions and evidence; do not rely on accidental inheritance or assume that context must never be inherited.
Each task packet states:
Isolated model context does not imply an isolated filesystem, process, Git repository, credential, rate limit, or external service. Prefer read-only investigation. If children may edit, assign disjoint write ownership explicitly. The coordinator owns staging, commits, branches, worktrees, integration, and other Git lifecycle mutations.
The coordinator owns the concurrency budget. Children do not delegate recursively unless their packet explicitly permits it. A failed, cancelled, or timed-out child contributes any available partial evidence; otherwise record no result and the unresolved unknowns. Retry only with a materially different packet or serialize the task.
Child output is evidence or a proposal, not a GateDecision, completion authority, or permission for external action.
When any of these appears, narrow the packets, serialize the shared portion, or return to the owning debugging or plan workflow.
Use when facing 2+ independent tasks without a written plan, with no conflicting shared mutable state or sequential dependencies, where parallel delegation beats inline cost; otherwise inline. Planned
---name: dispatching-parallel-agentsdescription: Use when facing 2+ independent tasks without a written plan, with no conflicting shared mutable state or…---# skills/dispatching-parallel-agents/SKILL.md總覽
Use when facing 2+ independent tasks without a written plan, with no conflicting shared mutable state or sequential dependencies, where parallel delegation beats inline cost; otherwise inline. Planned tasks use subagent-driven-development.
常見問題
從發布者下載 skills/dispatching-parallel-agents/SKILL.md,或複製路徑後開啟儲存庫。PlugMCP 只收錄這項技能,不代管檔案。
發布者將它存放在 https://github.com/GanyuanRan/Aegis。
Claude、Cursor、Codex 和 Grok Build 可以讀取你從發布者儲存庫加入的 SKILL.md。在聊天中傳送技能的 GitHub 資料夾連結,Grok Bot 就會安裝它。