Skip to content
SkillModel-led5,678 tokens in use

dbs-content-value

Judges whether a post or script keeps people past its opening, who it attracts, what they get from watching and what the traffic is worth to you.

11,518 stars on the repository Custom / Unknowndontbesilent2025/dbskill · skills/dbs-content-value
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-content-value costs

74tokens idle
5,678tokens in use
11,336tokens, 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
  • Structure22/25
  • Examples6/15
  • Output0/15
  • Size13/15
  • Resources7/15

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-content-value is a diagnostic for content that is not yet published or has low traffic. It looks at the opening alone first, the way a stranger sees it, and says whether most people would keep going or leave and why. If the opening loses people, it says the good material later may never be seen.

It then maps who finds the topic relevant, what viewers get from watching, which of six behaviors it drives (stopping, watching on, commenting, saving, sharing, following) and how the traffic fits your product or account. It does not predict view counts, check whether claims are true or rewrite your text. The Skill is written in Chinese and replies in your language.

What You Get

  • A one-sentence verdict on who the content attracts and whether most people continue
  • What a viewer expects after seeing the opening, and why they stay or leave
  • What viewers gain from watching on, named in a few points
  • Likely traffic and business value, including how close the audience is to your product
  • Up to three changes, each with what it strengthens and what it may cost
  • For published pieces with low traffic, a pointer to the weak stage: exposure, staying, continued watching, interaction or business follow-through

Common Use Cases

  • Testing a short video script before filming
  • Working out why a published post got views but no follows
  • Checking whether a topic will bring buyers or only passers-by
  • Comparing two titles by how each opening reads to a stranger

What Makes It Unique

Most content reviewers critique the writing. This one reads only the opening before anything else, refuses to let later strengths raise the score of a weak opening, and reports stopping, continued watching, commenting, saving, sharing and following as separate judgments. It keeps method terms out of the report and speaks in everyday sentences quoting your own text.

Under The Hood

This Skill is instructions only. The agent reads SKILL.md and, for a full report, a reference file with the diagnostic model, and applies them to the text you provide. It has no scripts, runs no commands, makes no web requests and writes no files. Anything it cannot see, such as platform data you did not supply, is marked unknown.

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