dbs-spread (dbskill): a Chinese-language skill that explains why content resonates or gets shared
A Chinese-language skill from the dbskill set that explains why a piece of content triggers resonance, emotion or sharing.
- Installs
- 19.3K
- on skills.sh
- Stars
- 11K
- on GitHub
- Files
- 1
- besides SKILL.md
- Updated
- Oct 2026
- last repo commit
dbs-spread makes Claude fix the content's core claim, audience and main reader action, then pick one main theory from a pool of five and cite the original text as evidence. It reports the audience emotion hypothesis, the stance that works, why people would view, save, comment or share, and what else the audience would want to hear.
The skill is written and answers in Chinese. It does not edit your draft sentence by sentence, estimate traffic or business value, predict platform numbers, or say whether something will go viral. It is one file plus a small agents/openai.yaml, and it runs no scripts.
Good for
- Creators who want to know why a post got a reaction
- Marketers analyzing the audience motive behind a shared piece
- Researchers who want theory-backed, text-grounded readings of content
Install dbs-spread
Claude Code
- 1
Copy this prompt.
Install the dbs-spread skill in Claude Code. Run this command: npx skills add https://github.com/dontbesilent2025/dbskill --skill dbs-spread 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 Node.js.
From its listing on skills.sh. Source.
What's in the skill
When it loads
解释一段已有内容为什么引发共鸣、情绪或分享，识别传播机制、有效立场和受众动机，并提炼讨论方向。适用于传播机制解读；不负责整篇逐句改稿或整体流量和商业价值评估。
Sections in SKILL.md
- 近邻任务边界
- 这个 skill 做什么
- 核心原则
- 1. 先识别机制，再选择理论
- 2. 每次只保留一个主理论
- 3. 理论解释需要文本证据
- 4. 情绪、接受和分享属于不同结果
- 主理论池
- A. 社会认同与自我分类
- B. 情绪评价理论
- C. 框架理论
- D. 使用与满足研究
- E. 情绪激活与在线分享
- 条件理论池
- 工作流程
- Step 1：固定分析对象
Key facts
- Installs on skills.sh
- 19,286 as of 2026-11-02
- Last repo commit
- 2026-10-28
- skills.sh audits
- Gen Agent Trust Hub: pass, Socket: pass, Snyk: pass
What it includes
Social identity, emotional appraisal, framing, uses and gratifications, online sharing
Each theory has a source, a task, trigger evidence, diagnostic questions and a boundary. Only one main theory is kept.
Try: “Use dbs-spread to explain why this post got so many shares.”
Read ·
Theory pool A to ESpiral of silence, cognitive dissonance, two-step flow
Used only when the stated trigger conditions are met.
Read ·
Conditional theoriesCore claim, audience, main action, key sentences
Extracts what the content claims and what reader action it aims for.
Read ·
Step 1: fix the object of analysisScreen five mechanism types, add an extra only with new evidence
Checks identity, framing, emotional appraisal, content use and social spread.
Read ·
Step 2: choose the main theoryEvidence, mechanism, limits and high, medium or low confidence
Every chosen theory is written with its text evidence and what it cannot explain.
Read ·
Step 3: write the mechanism judgmentEmotion hypothesis, effective stance, expected use, what the audience wants next
Ends with one question worth deepening and the mechanism to preserve.
Read ·
Step 4: derive conclusionsA fixed decoding report template, written in Chinese
Sections for the object of analysis, the main mechanism, any extra mechanism, derived conclusions and discussion points.
Read ·
Output formatSeven checks before finishing
Includes separating text fact, mechanism inference and facts still to verify.
Read ·
Self-check
From the official docs
Questions
What does dbs-spread do?
It explains why a piece of content could trigger resonance, emotion or sharing, using one main communication theory tied to the original text. It also suggests what the audience would want to hear next. SKILL.md and its report template are written in Chinese; the file does not set a reply language, so check how it answers an English text.
How do I install it?
Use the install box at the top of this page for this skill alone. The dbskill README also documents installing all 34 skills with one npx skills command and a Claude Code plugin route.
Does it tell me whether a post will go viral?
No. SKILL.md lists predicting completion rate, click rate and recommendation volume and judging that something will definitely go viral as out of scope. It labels each judgment with high, medium or low confidence.
Can it rewrite my draft?
No. Its handoff note lists sentence-by-sentence edits as something it does not deliver, and the skill treats that as outside its scope.
Is it safe to use?
It works on the text you give it, and the folder holds SKILL.md plus agents/openai.yaml (a display name and default prompt), with no scripts. Its frontmatter lists no tools or API keys. The license is CC BY-NC 4.0, so commercial use needs permission from the author.
How is it different from dbs-resonate?
dbs-spread explains why content that already exists resonates or spreads and keeps to analysis. dbs-resonate, another dbskill skill, diagnoses a draft and gives concrete cut and rewrite advice for specific sentences. See dbs-resonate's SKILL.md for its steps.
Information
updated Nov 2, 2026
- Repository
- dontbesilent2025/dbskill
- Folder
skills/dbs-spread
Sources
Docs, issue trackers and discussions this page is built from.