- 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 vibeeval/vibecosystem --skill agent-orchestration -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 vibeeval/vibecosystem --skill agent-orchestration -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 vibeeval/vibecosystem --skill agent-orchestration -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 vibeeval/vibecosystem --skill agent-orchestration -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/vibeeval/vibecosystem/tree/HEAD/skills/agent-orchestration來自發布者
When the user asks to implement something, use implementation agents to preserve main context.
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)
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.
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 hook
2. Shell wrapper
3. Python script
4. Register in settings.json
When done, provide a summary of files created and any issues.
When user says these, consider using an agent:
Agent Orchestration Rules
---name: agent-orchestrationdescription: Agent Orchestration Rules---# skills/agent-orchestration/SKILL.md常見問題
從發布者下載 skills/agent-orchestration/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/vibeeval/vibecosystem。
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。