CommunitySchreiben & Editierengithub.com

ouob-tw/LoopAgentTeams

Spec-driven multi-agent teamwork for any skills-capable agent (Claude Code, Codex, and more) — plan, dispatch, monitor, QA. No framework lock-in.

Was ist LoopAgentTeams?

LoopAgentTeams is a Claude Code agent skill that spec-driven multi-agent teamwork for any skills-capable agent (Claude Code, Codex, and more) — plan, dispatch, monitor, QA. No framework lock-in.

Funktioniert mitClaude CodeCodex CLI~Cursor
npx skills add ouob-tw/LoopAgentTeams

Installed? Explore more Schreiben & Editieren skills: steipete/notion, affaan-m/seo, affaan-m/brand-voice · View all 6 →

In Ihrer bevorzugten KI fragen

Öffnet einen neuen Chat, in dem dieser Agent-Skill bereits geladen ist.

Dokumentation

LAT Runner

執行 .lat/tasks.yaml 的已核准實作任務,通常由 lat-dispatch 啟動。

執行邊界

  • 僅執行已核准的實作任務。不處理規格審查或計劃審查。
  • 處理完當前佇列後正常退出。不建立背景守護程序或長期監聽器。

處理流程

  1. 讀取 .lat/tasks.yaml
  2. 檔案遺失、空、或 [] → 輸出 No pending tasks,exit code 0 退出。
  3. YAML 解析失敗 → 依 references/yaml-schema.md 的解析錯誤處理流程。
  4. 由上而下處理任務,每個任務依照以下檢查清單執行:
- [ ] 讀取任務的 goal、context、constraints
- [ ] 若有 plan_file → 讀取計劃檔案,確認階段順序
- [ ] 判斷是否匹配可用領域技能,匹配時載入
- [ ] 依計劃階段順序(或 goal)執行實作
- [ ] 在 results.yaml 頂部插入結果(使用相同 task_id 與 agent_id)
- [ ] 從 tasks.yaml 移除此任務

補充規則:

  • context.plan_file 時,必須先讀取計劃,依定義的階段順序執行。每個階段完成後專案應可執行。
  • 無計劃檔案的簡單任務:依 goal 直接執行。
  • 技能不得擴大任務範圍;與 constraints 衝突時以 constraints 為準。
  • tasks.yaml 移除已處理任務(不論完成、部分完成、或失敗)。保留未處理任務。

結果狀態

狀態意義
completed任務目標完全實現
partial部分實現;summary 須說明已完成與未完成範圍
failed未完成;errors 須包含至少一個 {code, message} 物件

後續任務

  • 僅在大型任務需拆分且剩餘工作可追蹤時才新增。
  • 沿用相同 task_id(Spec 檔名),agent_id 遞增 round(如 code_executor_2_<task_id>code_executor_3_<task_id>),created_by 填入目前 agent 的識別名稱。
  • 僅限實作任務,不新增審查類任務。

完成輸出

  • 無任務 → No pending tasks,exit code 0
  • 有任務 → 輸出各狀態計數(processed / completed / partial / failed)與修改檔案清單。
  • 處理完成後不保持 zmx 工作階段。

注意事項

  • 不要跳過或重新排序計劃中的階段。
  • 結果寫入規則、YAML 欄位順序、空狀態處理、解析錯誤備份流程皆參見 references/yaml-schema.md

Verwandte Skills

steipete/notion

Notion CLI/API for pages, Markdown content, data sources, files, comments, search, Workers, and raw API calls.

community

affaan-m/seo

Audit, plan, and implement SEO improvements across technical SEO, on-page optimization, structured data, Core Web Vitals, and content strategy. Use when the user wants better search visibility, SEO remediation, schema markup, sitemap/robots work, or keyword mapping.

community

affaan-m/brand-voice

Build a source-derived writing style profile from real posts, essays, launch notes, docs, or site copy, then reuse that profile across content, outreach, and social workflows. Use when the user wants voice consistency without generic AI writing tropes.

community

affaan-m/crosspost

Multi-platform content distribution across X, LinkedIn, Threads, and Bluesky. Adapts content per platform using content-engine patterns. Never posts identical content cross-platform. Use when the user wants to distribute content across social platforms.

community

affaan-m/x-api

X/Twitter API integration for posting tweets, threads, reading timelines, search, and analytics. Covers OAuth auth patterns, rate limits, and platform-native content posting. Use when the user wants to interact with X programmatically.

community

affaan-m/content-engine

Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content calendars, or one source asset adapted cleanly across platforms.

community