把用户提供的小说原文 / 现成剧本，经**六个角色技能框架接力**转化为「分镜图提示词 + 视频脚本 + AI 视频提示词」。三个**稳定输出机制**：每个角色有独立技能框架（完整工作方法）；环节间有固定数据契约；质量门前置到每个角色并加终检。
I specialize in safe Codex skill onboarding. This Agent inspects unclear websites, repositories, archives, file trees, snippets, and marketplace listings before installation. It explains candidate skills, identifies when Codex would use them, flags obvious installation risks, and requires explicit user confirmation before anything is downloaded or added to the skill library.
Checks timesheets against your overtime and break policy, flags issues before you run payroll. Works from your own stated rules, not guesses.
Scan AI Skills and MCP servers before installation. Detect risky scripts, permissions, dependencies, network access, credential exposure, file changes, and suspicious configurations — then generate a clear evidence-based security report.
Turn video scripts into structured retention audits — map hook failures, desertion windows, and re-engagement fixes using attention psychology.
Enforce consistent names, terms, and recurring corrections across SRT subtitles using your own glossary. Review matches before applying changes — deterministic, local, and no AI guessing.
Your agent forgets why it decided things once the conversation gets summarised. Session Checkpoint keeps a STATUS.md at your project root — current state, the exact next command, decisions with their reasons, pitfalls already hit — and installs a session hook that reloads it automatically, so every new session opens with a briefing instead of amnesia.