此Skill整合了APP製作的角色權限控管、智慧財務自動結算、動態資源預約排程、系統級通知功能、分工遊戲化模組等等 本 Agent 專長於： 執行階層化權限管理（EX：房長/財務/成員）。 自動化記帳與私密催繳通知。 即時資源調度與過期自動清理。 提供溫馨、簡潔的 AI 生活助理服務。 無論是共居空間、工作室或宿舍，透過 CollabSpaceOS 皆可快速部署具備高安全性與生活溫度感的專屬 App。 匯入此技能包，讓您的 AI 瞬間進化為精通 React + Firebase 的資深架構師！本 Skill 內建『蒐集代幣的遊戲化任務』、『智慧財務記帳』與『PWA 系統推播』等高度模組化的領域知識。 您的專屬 AI 將為您精準產出高品質代碼，完美處理『跨時區同步』與『防資料流失』等高階邏輯。從架構整合、客製化微調到進階 Debug，為接案者與開發者省下破百小時的摸索期。獲取神級框架，極速部署您的專案！」
Batch validate, clean, normalize, swap, and convert subtitle files with deterministic processing and failure-safe reports.
A daily AI planner that turns your routine — sleep, work, commute, meals, exercise — into a ranked, explainable "what to do next" list. Self-corrects when you report what you actually did. Nothing saved or reminded without your confirmation first.
This skill is based on practical Power Platform delivery patterns for safely creating, reviewing, and modifying Power Automate cloud-flow JSON in Dataverse solution exports. It focuses on issues that often break real client automations: runAfter paths, renamed action references, connection references, hardcoded values, TRY/CATCH logging, import safety, validation, and rollback notes.
Five demands, three people, one Friday deadline. Get a defensible schedule in one pass — who goes first on contested resources, the zero-float critical path, and the honest date when it doesn't fit.
AI Agent Skill：根據你主動提供的作息、當下情境與修正，提出可解釋的下一步假設。跨對話分層記憶與提醒都需要相容的宿主工具、欄位揭露及你的確認；沒有工具時只使用目前對話或提供未排程計畫。
Check SRT files in batches, get cue-level QA reports, and export conservative repair copies while preserving your originals. Includes explicit time shifts, overlap trimming and two-line track splitting. English edition. Python 3.10+; no API key needed for the local engine.
Fix SRT subtitle timing with precise offset, FPS conversion, and two-anchor drift correction. Deterministic, local, and fail-safe — no AI guessing.
A kickoff protocol (agent skill) for multi-step tasks. Before writing any code, the agent must: run a spec interview, batch every human-authorization step into one checklist, build a self-verification loop (log sink + verify script + dry-run) *before* the feature itself, and build comparable variants instead of blocking on third-party decisions.