Skip to content
SkillModel-led4,723 tokens in use

dbs-diagnosis

Checks whether a business question holds up before answering it, or runs a seven-point checkup of a whole business, and ends with tomorrow's first action.

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

78tokens idle
4,723tokens in use
10,483tokens, 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 →
Good
  • Frontmatter8/15
  • Structure22/25
  • Examples0/15
  • Output5/15
  • Size15/15
  • Resources12/15

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-diagnosis is a Chinese-language agent skill for diagnosing small businesses and online ventures. It decides on its own whether you are asking a specific business question or want a full review, and follows the matching path.

For a specific question it tests the wording, the hidden assumptions, the logic and the stated facts before answering, because many questions dissolve once they are examined. For a full review it checks the product, price, buyer, customer acquisition, delivery and revenue, and writes a report with a one-line prescription.

What You Get

  • A restated core question, then a verdict on whether the question holds
  • A judgment with its basis, written conditionally when a key fact is missing
  • One or two alternative business models to test your assumptions
  • A seven-item checkup report for a full business review
  • A closing line in the form: the first thing to do tomorrow is a named action
  • A reminder that you can say save to keep the result

Common Use Cases

  • Asking why renewals are low on a course business and learning which assumption in the question is wrong
  • Deciding between two price points with no sales record, and getting a conditional answer plus the cheapest test
  • Having a one-person service business reviewed end to end for pricing, demand and delivery structure

What Makes It Unique

It examines the question before answering it. A five-layer funnel can end a question at the wording or assumption layer, which saves effort on problems that were framed wrongly. Judgments trace back to six stated axioms, such as pricing being part of the product, and every answer closes with one concrete first action. It also watches for signs that the user already knows what to do and is avoiding it, and points that out once. It declines to quote success rates or give legal, tax or investment opinions, and does not handle emotional problems.

Under The Hood

It is a prose-only skill with no scripts. The agent reads the SKILL.md and loads reference files from the skill folder when needed: a funnel guide, a checkup checklist, output formats and a case library. It works from what you type or attach in the conversation. It does not run commands, call web services or write files; saving a result is left to a separate 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