dbs-deconstruct Skill for Claude: Unpack a Vague Business Term in Plain Words
Makes your assistant take apart a vague business term, show how people use it, and restate it in plain words.
- Installs
- 30K
- on skills.sh
- Stars
- 11K
- on GitHub
- Files
- 3
- besides SKILL.md
- Updated
- Oct 2026
- last repo commit
dbs-deconstruct takes one term or sentence and shows who uses it for what. It checks whether the term is packaging, used in mixed ways, built on a wrong assumption or a pseudo-concept, gives the limits of where it applies, and ends with a plain-words summary. It only explains the concept; setting goals or diagnosing a business belongs elsewhere.
It triggers when you ask what a word means, how two words differ or what is wrong with a sentence. If your own question hides a vague term, it also names the wrong assumption and rewrites the question so it can be answered. The folder holds 4 files including SKILL.md and bundles no scripts. The README licenses dbskill under CC BY-NC 4.0, for non-commercial use.
Good for
- Anyone puzzled by business buzzwords such as 'precise traffic' or 'must-have demand'
- Founders who suspect a question contains a hidden wrong assumption
- People arguing over what a word really means
Install dbs-deconstruct
Claude Code
- 1
Copy this prompt.
Install the dbs-deconstruct skill in Claude Code. Run this command: claude plugin marketplace add dontbesilent2025/dbskill claude plugin install dbs-deconstruct@dontbesilent-skills Then check that it loaded and tell me how to use it.
- 2
Paste it into Claude Code. It shows the change and asks before running it.
Requires Claude Code.
The plugin route installs only this one skill. The README says the exact command name is whatever your agent shows; plugin installs may add a prefix. The README's whole toolkit command (claude plugin install dbs@dontbesilent-skills) is not needed for this skill.
From the project README. Source.
What's in the skill
When it loads
用维特根斯坦与奥派经济学方法拆解模糊的商业概念。用户要求解释一个词、澄清概念边界或识别概念混用时使用。
Sections in SKILL.md
- 本 Skill 的边界
- 核心判断
- 1.意义即使用
- 2.语言游戏与家族相似
- 3.大白话测试
- 4.错误预设
- 5.Question 与 Problem
- 6.奥派经济学校准
- 7.维特根斯坦式的克制
- 工作流程
- Step 0:读取全部材料
- Step 1:只在缺口处提问
- Step 2:选择深度
- Step 3:拆解
- 输出
- 默认形态
Key facts
- Installs on skills.sh
- 30,042 (Nov 2, 2026)
- GitHub stars (whole repo)
- 11,039 (Nov 2, 2026)
- Last repo commit
- Oct 28, 2026
- Language of SKILL.md
- Chinese; replies in the language you write in
- Intended use
- Personal study, research and non-commercial use; commercial use needs the author's authorization
- skills.sh audits
- Gen Agent Trust Hub pass, Socket pass, Snyk warn
What it includes
Explains concepts only; goal-setting and full business diagnosis are left to other tools
ScopeA word means what it makes people do in a setting, not its definition alone
Meaning is useSame word, different rules in different settings; lists traits, not one definition
Same word, different rules in different settings; lists traits instead of forcing one definition
Language games, family resemblanceRetells the idea without the term to spot packaging, gaps and mixed use
Retells the idea without the term: nothing lost means packaging, cannot do it means a gap, differing versions mean mixed use
Plain-words testStates the hidden premise in a question, then rewrites it into one that can be answered
False presuppositionsA Question has a text answer; a Problem needs practice, so it names the practice
A Question has a text answer; a Problem needs practice, so it gives the text part and names the practice
Question or ProblemFor business terms: value, action, order, price and profit signals; shows findings only
For business terms: subjective value, action, spontaneous order, price and profit signals; only findings are shown
Austrian economics checkSays 'I am not sure of the origin' instead of inventing etymology, quotes or data
RestraintPicks out the term, the setting, how you use it and what triggered the question
Picks out the term, the setting you met it in, how you use it and what triggered the question
Step 0: read all materialAt most one question, only when a gap would change the result
At most one question, only if no term was given or two very different meanings would change the result
Step 1: ask only at a gapShort for one quick term, standard by default, deep when asked
Short for one quick term, standard by default, deep when asked for or when many parts are involved
Step 2: pick a depthUsage table, restoration, packaging test, Question or Problem, economics, plain words
Usage table, concept restoration, packaging or mixed-use test, Question or Problem, economics check, plain words
Step 3: deconstructPlain words, usage table, where the problem is, limits, economics check, one-line summary
Output: default formThree lines: plain words, main usages, verdict
Output: short formThe default form plus seven tables from framework.md
The default form plus seven tables from framework.md; unfilled tables mark where understanding is missing
Output: deep formMental health, medical, legal and investment terms: everyday usage, not your own case
Mental health, medical, legal and investment terms: explains everyday usage, not your own case
Safety limitsPrecise and plain; offers "save" once; replies in your language
Precise and plain; offers "save" once (the README says /dbs-save does the saving); replies in your language
Style, save reminder, language
From the official docs
Questions
What does dbs-deconstruct do?
It takes apart a vague business word or sentence. It shows how different people use it, where it is mixed up or built on a wrong assumption, and restates it in plain words.
How do I install dbs-deconstruct?
Use the install box at the top of this page. For Claude Code the README documents a plugin that installs only this skill, and the skills CLI also works. Run install commands in a terminal, not in the agent chat.
Does it work in English?
Yes. The skill text is Chinese, but it says to reply in English when you write in English. Its example terms are Chinese business words, such as 'precise traffic'.
What does it not do?
It does not turn a vague wish into a checkable goal or give a full business diagnosis. The skill says those are separate jobs.
Is dbs-deconstruct safe to install?
The folder holds SKILL.md, an agent config file and two reference notes, and it bundles no scripts. It works from the words you give it. Share only what you are comfortable pasting into your assistant. Saving a conclusion is done by a separate skill, /dbs-save, which the README says writes to ~/.dbs/.
Can I use it for my company's paid work?
Check with the author first. The README and LICENSE say CC BY-NC 4.0, for personal study, research and non-commercial use. GitHub shows no detected license.
How is it different from dbs-diagnosis?
dbs-deconstruct explains what a term means and where it misleads. The README describes dbs-diagnosis as judging whether a business problem holds up or checking a whole business.
Information
updated Nov 2, 2026
- Repository
- dontbesilent2025/dbskill
- Folder
skills/dbs-deconstruct
Sources
Docs, issue trackers and discussions this page is built from.
Show all 5Hide
- dbskill README (English) · github.com
- dbs-deconstruct on skills.sh · skills.sh
- dbs-deconstruct SKILL.md · github.com
- dbs-deconstruct framework.md · github.com
- dbs-deconstruct cases.md · github.com