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.