Skip to content
SkillModel-led3,559 tokens in use

dbs-spread

Explains why a piece of content moves its audience or gets shared, picking one communication theory and tying each claim to quoted text.

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

96tokens idle
3,559tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. 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
  • Size15/15
  • Resources0/15

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-spread takes content that already exists and decodes the psychology behind its reception. It fixes the core claim, target audience and desired action, then chooses one main theory from social identity, emotional appraisal, framing, uses and gratifications, or emotional arousal and sharing. A second theory is added only when the first cannot explain a visible mechanism.

Each theory comes with the triggering quote, the mechanism, what it cannot explain and a confidence level. The output ends with an audience emotion hypothesis, the stance that works, expected use such as watching, saving, commenting or sharing, and two or three topics the audience may want to hear next.

What You Get

  • A fixed analysis block with core claim, audience situation, intended action and key quotes
  • One main theory with trigger evidence, mechanism, limits and confidence, and a second only when needed
  • An audience emotion hypothesis, effective stance and expected use behaviour
  • Two or three follow-up topics that keep the same mechanism, and one core question to discuss

Common Use Cases

  • Understanding why an old post drew many comments or reposts
  • Planning follow-up topics from a piece that struck a nerve
  • Checking whether a draft speaks to a group identity or only gives information

What Makes It Unique

It limits the analysis to one main theory and a source list with citations, and it blocks a theory unless the text contains its trigger. Conditional theories such as the spiral of silence, cognitive dissonance and two-step flow have explicit entry conditions. It separates what the text says from what the audience might feel and never turns a theory into a traffic forecast.

Under The Hood

The skill is a single instruction file with no scripts and no references. It reads the content you paste and writes a structured analysis in the chat. It runs no commands, calls no services and writes no files. The theory pool is listed in the instructions with citations, so the model works from that list without looking anything up.

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