Skip to content
SkillModel-led3,647 tokens in use

dbs-deconstruct

Takes a fuzzy business word or sentence apart: how different people use it, where it is mixed up, and what it means once the jargon is removed.

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

74tokens idle
3,647tokens in use
9,475tokens, 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
  • Examples9/15
  • Output0/15
  • Size15/15
  • Resources10/15

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-deconstruct is a Chinese-language agent skill for clarifying vague business concepts such as “precise traffic”, “niche”, “must-have need” or “IP positioning”. It applies Wittgenstein’s idea that meaning is use, plus a short Austrian-economics check, to show what a word does in different mouths.

You give it a word, a group of similar words or a sentence someone said. It returns a restatement in everyday language, a table of how the term is used, a verdict on whether it is packaging, a mixed-up term, a false premise or an empty concept, and the limits of where it applies.

What You Get

  • A restatement of the idea with the jargon removed
  • A table of who uses the term, what they want the listener to do, and what they really mean
  • A verdict on the problem: packaging, mixed usage, false premise or empty concept
  • Stated limits: where the term applies and where it starts to mislead
  • A one-line summary, plus a three-line short form for quick questions
  • An optional seven-table deep breakdown for concepts with many parts

Common Use Cases

  • Checking what a course seller means by “precise traffic” before paying for it
  • Settling an argument where two people use the same business word differently
  • Rewriting a question that rests on a false premise, such as asking for the single best posting time

What Makes It Unique

Most skills in this area give frameworks for solving a business problem. This one works on the words in the question itself. It tests each term by restating it without the jargon, checks whether the question assumes something that does not exist, and separates questions with a written answer from problems that only practice can answer. When it is unsure of a term’s origin, it says so and invents no etymology.

Under The Hood

It is a prose-only skill with no scripts. The agent reads the SKILL.md and, for deep mode or hard calls, two reference files (a framework file and a case file) from the skill folder. It reads only what you type or attach in the conversation. It does not run commands, call web services or write files; if you want the result kept, the skill only tells you to say save, which belongs 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