Skip to content
SkillModel-led2,926 tokens in use

dbs-resonate

Finds where a written draft fails to reach its target audience, ties the diagnosis to the original sentences, and lists what to cut, trim and strengthen.

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

99tokens idle
2,926tokens 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-resonate is a Chinese-language agent skill for revising a draft that is already written. It pulls out every claim in the text, decides which one should be the core, and picks one main communication theory to explain how the draft is meant to connect with its audience.

It then rates that mechanism as working, weak or missing, quotes the sentences behind the verdict, and lists what to delete, compress, strengthen and leave alone, plus a one-line skeleton for the revised piece.

What You Get

  • A one-sentence statement of the problem that hurts resonance most
  • A list of the claims in the draft and a verdict on whether the core is clear, diluted or missing
  • A main-theory diagnosis rated effective, weak or invalid, with the original wording that triggers it
  • Four edit lists: delete, compress into support, strengthen, and keep unchanged
  • A one-line skeleton for the revised piece

Common Use Cases

  • Reviewing a long-form article draft before publishing to see which claim should stay as the core
  • Finding out why a script talks to ‘everyone’ and fails to make a specific reader feel addressed
  • Checking whether an emotional word like ‘anxious’ is backed by any wording that creates that emotion

What Makes It Unique

It keeps one core claim and one main theory per diagnosis, and ties every verdict to a quoted sentence. It separates how well the text is built from how a platform will distribute it, and declines to predict view counts or promise a hit. The output is an edit plan; rewriting the full text and explaining already-proven posts are left to other work, as are overall traffic estimates.

Under The Hood

It is a prose-only skill with no scripts and no reference files. The agent reads the SKILL.md and a small agent metadata file, then works only from the draft you paste or attach in the conversation. It does not run commands, call web services or write 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