dbs-hook
dbs-hook is an AI skill designed to diagnose and optimize short video openings. It evaluates content quality, checks for hook elements, and generates multiple variations based on material extraction, supplementation, and suspense creation.
Is dbs-hook safe to install?
Safe to install: our audit of dbs-hook's source files found 0 shell commands, 0 external URLs, no file writes (none risk). Every command and URL listed appears verbatim in the skill's source. The skill performs text analysis and generation based on user input. It does not execute shell commands or make network requests.
How we audit skills: our security review methodology.
Who is this skill for?
Content creators and social media managers looking to improve the engagement and retention of their short video scripts.
What can you do with it?
- Diagnosing issues in existing video openings
- Generating multiple optimized opening variations for a script
- Checking content quality and material richness before optimization
- Creating suspenseful hooks that avoid giving away conclusions too early
How good is this skill?
Quality score: 5/10. The skill provides a clear, structured methodology for content optimization. It includes specific diagnostic criteria and follows a logical workflow for generating improvements.
What does the skill file contain?
# dbs-hook：短视频开头优化 你是 dontbesilent 的开头优化 AI。你的任务是诊断短视频开头的问题，并生成可执行的优化方案。 **核心信念：写不出好开头，90% 是因为内容本身有问题。** 开头是内容的试用装，如果内容没有价值、没有素材、没有冲击力，再怎么优化开头也没用。 --- ## 核心哲学 ### 信条 1：开头是内容的试用装，不是标题的延续 开头必须独立工作。不能假设用户看了标题、看了封面。开头必须在 5 秒内独立建立吸引力。 ### 信条 2：好开头 = 话题 + Hook + 可信度 ``` 开头公式 = 话题（讲什么）+ Hook（为什么看）+ 可信度（为什么信你） ``` **例子**： - 话题：选题和标题的区别 - Hook：我去年涨粉 200 万 - 可信度：靠的就是搞清楚这个 - 完整开头：「我去年涨粉 200 万，靠的就是搞清楚选题和标题的区别」 ### 信条 3：开头要制造悬念，不要直接给答案 **错误**：李亚鹏 30 年干黄十几个项目，证明人脉不等于赚钱 ← 说了答案 **正确**：善良的李亚鹏，认识半个娱乐圈，30 年为什么赚不到钱 ← 留悬念 ### 信条 4：开头必须口播友好 **错误**：你以为你在自律？其实你只是在逃避执行 ← 自问自答，念不出口 **正确**：只要你没在执行，你的动作大概率就是...
Frequently asked questions
What triggers the dbs-hook skill?
The skill triggers via /dbs-hook, /hook, or phrases like 'optimize my opening' and 'how to write opening'.
Will the skill optimize any script provided?
No. The skill performs a quality check first. It stops optimization if the content lacks a body, is too short (under 200 words), lacks value, or contains insufficient material like data, stories, or hooks.
How does the skill handle existing openings?
It evaluates the opening based on independence, hook strength, suspense, credibility, spoken-word friendliness, and alignment with the main content.
What happens if I don't know which skill to use?
You can input /dbs to access the navigation entry for the commercial toolset, which routes you to the appropriate skill based on your needs.
Related skills
supabase-postgres-best-practices
264.3KDevelopers and database administrators working with Postgres and Supabase
This skill provides a structured set of Postgres performance optimization rules and best practices maintained by Supabase. It guides developers in writing, reviewing, and optimizing SQL queries, schema designs, and database configurations.
caveman-compress
224.1KDevelopers and users who want to optimize memory files like CLAUDE
The caveman-compress skill reduces input token usage by rewriting natural language files into a concise, caveman-style format while preserving technical content, code blocks, and file structure.
copywriting
123.0KUsers who need to write or improve marketing copy for web pages and require a structured, conversion-oriented approach
The copywriting skill provides a framework for generating and refining marketing copy for websites, including homepages, landing pages, and product pages. It guides the agent to gather product marketing context from local files, apply conversion-focused writing principles, and structure content for clarity and persuasion.
convex-performance-audit
79.2KDevelopers working with Convex applications who need to optimize slow features, resolve high-resource usage, or address transaction contention
The convex-performance-audit skill provides a structured workflow for diagnosing and resolving performance issues in Convex applications, including read amplification, OCC conflicts, subscription costs, and function limits.