Skip to content
SkillModel-led4,338 tokens in use

dbs-title-cover-intro

Agrees the topic with you first, then writes titles, cover text and video openings for Xiaohongshu, Bilibili, Douyin and WeChat Channels in one screen.

11,518 stars on the repository Custom / Unknowndontbesilent2025/dbskill · skills/dbs-title-cover-intro
npx -y skills add dontbesilent2025/dbskill -g --all
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing dbs-title-cover-intro costs

158tokens idle
4,338tokens in use
33,959tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Fair
  • Frontmatter8/15
  • Structure16/25
  • Examples6/15
  • Output0/15
  • Size13/15
  • Resources13/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity96
  • Maintenance100
  • Community64
  • Maturity28
  • Momentum40

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.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers