dbs-title-cover-intro starts from your script or footage and works out whether you can still edit the text, reshoot, or only cut what exists. If the angle is open, it sends a menu of up to four topics aimed at different audiences, each with what changes, who cares, whether the script supports it and a sample title, plus up to two questions about experience or numbers that make viewers trust you.
Once you pick, it delivers a single-screen set: a one-line direction, up to three body edits, three Xiaohongshu and Bilibili titles, one or two Douyin and Channels captions, cover text with line and character limits, a Douyin profile cover and a ten-second opening that links back to your script. It does not make cover images or publishing risk notices.
What You Get
- A menu of up to four topic options with audience, required changes, support from the script and a sample title
- Three titles for Xiaohongshu and Bilibili and one or two captions for Douyin and WeChat Channels
- Cover text with a six-character line limit and a separate two-line Douyin profile cover
- A ten-second opening and the line where it rejoins the script, or a cold-open plan from existing footage
- Up to three suggested edits to the body before filming, and a short list of other directions
Common Use Cases
- Choosing which angle of a draft to build a short video around before recording
- Writing platform-specific titles and covers for a finished script
- Finding a strong cold open in footage that is already shot and cannot be retaken
What Makes It Unique
It settles the topic before the wording, following a stated content method, and sizes its advice to production status from unwritten to fully shot. It limits itself to what the content can deliver, keeps the author’s strong phrasing and avoids invented facts or experiences. It reads cover lines joined together to catch sentences that blame the wrong person.
Under The Hood
The skill is an instruction file with thirteen reference documents and no scripts. It reads the script and any files you give it and replies in the chat. By default the main agent works alone, and in deep mode it may start up to three sub-agents to explore angles. It asks its questions in ordinary chat, never in pop-up forms, and runs no commands, calls no services and writes no files.