Skip to content
SkillModel-led3,599 tokens in use

dbs-content

Diagnoses how to build content around a topic you have already chosen: format, platform, wording, title, efficiency and audience gap, ending in a first step.

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

75tokens idle
3,599tokens 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
  • Structure16/25
  • Examples9/15
  • 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-content is a content creation diagnostic. You give it a settled topic and, if you have one, a first draft. It recommends a format and platform, then judges the content on five dimensions and names the one action to take first.

It is a diagnostician and does not write for you. It gives no line edits and does not draft titles, covers or openings. It also pushes back on common habits, such as asking for content before there is a product with a working payment link. The Skill text is in Chinese and replies in the language you use.

What You Get

  • A recommended content form and platform with a one-line reason
  • A five-row table covering writing cleanliness, cover and title, efficiency of expression, knowledge gap and AI workflow
  • A rating of clean, needs work or redo for each of the first four rows
  • One concrete first action to take
  • A one-sentence summary of the verdict

Common Use Cases

  • Deciding whether a topic fits a short video, a note or a long article
  • Checking a draft for how it is organized and argued before polishing
  • Choosing between Xiaohongshu, Douyin, X and a public account for a topic
  • Testing whether your explanation beats what peers already published

What Makes It Unique

Most content tools write copy. This one refuses to ghostwrite and works as an editor who diagnoses direction, form and expression. It carries stated positions, such as that product comes before content and that a gap in understanding between you and peers decides whether content is worth making, and it speaks directly when a draft is weak.

Under The Hood

This Skill is instructions only. The agent reads SKILL.md, which holds the principles, the form and platform table, the five checks, the report template and a few cases, and applies them to your topic and draft. It has no scripts, runs no commands, makes no network calls and writes no files. If you say save, the save step belongs to another dbskill Skill.

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