Creator · Pluviobyte
Last updated · Sep 1, 2026
dontbesilent 短视频开头优化。诊断开头问题 + 生成优化方案。 触发方式:/dbs-hook、/hook、「帮我优化开头」「开头怎么写」 Short video opening optimization with diagnosis and solutions. Trigger: /dbs-hook, "optimize my opening", "how to write opening"
Creator · Pluviobyte
Last updated · Sep 1, 2026
dontbesilent 短视频开头优化。诊断开头问题 + 生成优化方案。 触发方式:/dbs-hook、/hook、「帮我优化开头」「开头怎么写」 Short video opening optimization with diagnosis and solutions. Trigger: /dbs-hook, "optimize my opening", "how to write opening"
Creator · Pluviobyte
Last updated · Sep 1, 2026
dontbesilent 短视频开头优化。诊断开头问题 + 生成优化方案。 触发方式:/dbs-hook、/hook、「帮我优化开头」「开头怎么写」 Short video opening optimization with diagnosis and solutions. Trigger: /dbs-hook, "optimize my opening", "how to write opening"
Creator · Pluviobyte
Last updated · Sep 1, 2026
dontbesilent 短视频开头优化。诊断开头问题 + 生成优化方案。 触发方式:/dbs-hook、/hook、「帮我优化开头」「开头怎么写」 Short video opening optimization with diagnosis and solutions. Trigger: /dbs-hook, "optimize my opening", "how to write opening"
Sandbox only
Install targets
Codex install prompt
Install the "dbs-hook" agent skill from https://github.com/Pluviobyte/rnskill/tree/main/skills/dbs-hook. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: dontbesilent 短视频开头优化。诊断开头问题 + 生成优化方案。 触发方式:/dbs-hook、/hook、「帮我优化开头」「开头怎么写」 Short video opening optimization with diagnosis and solutions. Trigger: /dbs-hook, "optimize my opening", "how to write opening" After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {"event_id":"install_<unique-id>","skill_slug":"pluviobyte-dbs-hook","task":"Install dbs-hook","agent":"codex","outcome":"success","install_used":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.Supply asset profile
Design assets, images, video, audio, multimodal media, presentation, and creative production skills.
Scenario
Design and creative
I need my agent to produce design assets, UI directions, presentations, or creative media workflows.
Agent fit
Claude Code + CLI + Codex
Codex, Claude Code, Cursor, CLI, or custom agents.
Install
Ready
npx skills add Pluviobyte/rnskill --skill dbs-hook
Maintenance
fresh
13d since push
Risk
Safe to try
Repository license detected as NOASSERTION, which may cause uncertainty about usage rights.
GitHub quality
1.4K
78/100 Quality · 78/100 Trust
Coverage tags
Review notes
Repository license detected as NOASSERTION, which may cause uncertainty about usage rights. · Metadata fields 'tags' and 'frameworks' are empty, reducing discoverability.
Agent adoption scorecard
These scores combine public repository metadata, OpenAgentSkill review signals, maintenance freshness, and install readiness. They are a shortlist signal, not a replacement for human review.
Quality
StrongSolid option that is likely worth shortlisting for production workflows.
Trust
Sandbox onlyUseful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.
Audit
Safe to tryA machine-readable review of install readiness, security metadata, maintenance, and adoption risk.
OpenAgentSkill Trust Score v5
Run only in a sandbox and compare close alternatives before using it for real work.
Stars
1.4K GitHub stars
Repo activity
1.4K stars, 158 forks
Maintenance
13d since push
License
NOASSERTION
Install
npx skills add Pluviobyte/rnskill --skill dbs-hook
Install safety
Agent-readable metadata
Use this block or the embedded JSON to decide whether an agent should install this skill, choose an alternative, or ask for human review first.
Suited tasks
Suited agents
Install decision
Trust and risk
Outcome loop
Install command
npx skills add Pluviobyte/rnskill --skill dbs-hookDo not use when
Alternative
175.1K Stars
npx skills add anthropics/skills --skill frontend-design
Alternative
85.2K Stars
npx skills add Leonxlnx/taste-skill --skill design-taste-frontend
Alternative
1.8K Stars
npx skills add Alisa0808/vox-director --skill vox-director
Alternative
175.1K Stars
npx skills add anthropics/skills --skill canvas-design
Agent safety v2
Good audit and safety signals with no high-risk permission hints in public metadata.
Review the audit page, then allow agent install in a sandboxed workflow.
medium
Skill likely fetches remote pages, APIs, repositories, or external services.
medium
Skill may read or write project files, documents, generated artifacts, or local workspace state.
Agent resolve plan
The Resolve API returns the selected skill, alternatives, safety policy, audit notes, install target, and copy-paste prompt an agent can follow without scraping this page.
Open JSON
/api/agent/resolve?task=Use%20dbs-hook%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Resolve text
/api/agent/resolve?task=Use%20dbs-hook%20for%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text
Install handoff
/api/skills/pluviobyte-dbs-hook/install
Agent should check
Copy prompt
Task: Use dbs-hook in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20dbs-hook%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/pluviobyte-dbs-hook/install
Install command: npx skills add Pluviobyte/rnskill --skill dbs-hook
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.Agent handoff
Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.
Install handoff
/api/skills/pluviobyte-dbs-hook/install
LLM text format
/api/skills/pluviobyte-dbs-hook/install?format=text
Find alternatives
/api/skills/search?q=dbs-hook&limit=3
Agent prompt
Use dbs-hook for this task. Review https://www.openagentskill.com/api/skills/pluviobyte-dbs-hook/install, then install with: npx skills add Pluviobyte/rnskill --skill dbs-hookRegistry metadata
This page exposes the same decision, trust, audit, use-case, and install signals through the Registry API, so agents can rank this skill without scraping the UI.
Manifest
/api/registry/manifest/pluviobyte-dbs-hook
LLM text
/api/registry/manifest/pluviobyte-dbs-hook?format=text
Install alias
/api/registry/install/pluviobyte-dbs-hook
Recommend
/api/registry/recommend?task=Use%20dbs-hook%20in%20an%20agent%20workflow&limit=3
Agent fit
Design and creative
Platforms
Claude Code
Audit report
A machine-readable review of install readiness, security metadata, maintenance, and adoption risk.
Agent decision cockpit
Use this as a leading candidate, then validate the README and install path in your own agent stack.
Role in stack
Primary pick
Primary fit
Design and creative
Trust label
Production-ready
Install path
Command ready
Use when
Evidence
review first
Implementation path
Trust profile
Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.
GitHub adoption
PASS1.4K GitHub stars
Stars/forks activity
INFO1.4K stars, 158 forks; issue activity unavailable in current metadata
Recent maintenance
PASS13d since push
License clarity
PASSNOASSERTION
Good signals
Review before install
Recommended action
Run only in a sandbox and compare close alternatives before using it for real work.
Quality profile
Solid option that is likely worth shortlisting for production workflows.
Workflow fit
Create assets
I need my agent to produce design assets, UI directions, presentations, or creative media workflows.
Parse messy files
I need my agent to read PDFs, extract tables, and turn documents into structured data.
Publish consistently
I need my agent to turn research and product updates into useful content drafts.
Workflow fit
Design, build, test, and ship interfaces
A practical workflow for agents that turn product briefs or Figma designs into polished frontend code, review the result, test it in a browser, and prepare a safe deployment.
Brief to publish-ready creative
A practical workflow for agents that shape a video brief, create strong multimodal prompts, generate supporting B-roll, and prepare a reviewable short-form or explainer video.
Scrape, clean, and reuse web data
A practical workflow for agents that crawl public pages, extract clean content, normalize data, and hand it to downstream research or RAG workflows.
Alternative shortlist
Similar skills that may fit this task.
Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.
Design and implementation guidance for distinctive landing pages, portfolios, product demos, and purposeful redesigns.
Turn one topic into a narrated Vox-style paper-collage explainer or ad video, from script through captions.
Create original visual art, posters, PNG assets, and PDF documents through a clear design philosophy.
--- name: dbs-hook description: | dontbesilent 短视频开头优化。诊断开头问题 + 生成优化方案。 触发方式:/dbs-hook、/hook、「帮我优化开头」「开头怎么写」 Short video opening optimization with diagnosis and solutions. Trigger: /dbs-hook, "optimize my opening", "how to write opening" ---
# 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为了逃避执行而生的动作 ← 直接陈述
---
## 工作流程
### Phase 1:接收文案
问用户:**「把短视频文案发给我,我帮你诊断开头 + 生成优化方案。」**
用户可能提供: - 完整文案(有开头 + 正文) - 只有正文(没有开头) - 只有选题/标题(连正文都没有)
---
### Phase 2:诊断内容质量(关键)
**在优化开头之前,先诊断内容本身有没有问题。**
#### 2.1 内容完整性检查
| 检查项 | 问题 | 诊断 | |--------|------|------| | 只有选题/标题 | 连正文都没有 | **停止优化。** 告诉用户:「开头是内容的试用装,你连内容都没有,优化开头没有意义。先把正文写出来。」 | | 正文太短 | 少于 200 字 | **警告。** 告诉用户:「正文太短,可能撑不起一个好开头。建议先丰富正文内容。」 | | 正文没有价值 | 全是废话、没有干货 | **停止优化。** 告诉用户:「正文没有价值,优化开头也没用。先把内容做扎实。」 |
#### 2.2 素材丰富度检查
从文案中找素材,问自己:
**有没有冲击力的数据?** - 大数字(80 亿、400 栋、13000 条) - 对比数字(从 0 到 X、1 年内) - 百分比(99%、10 倍)
**有没有转变故事?** - 之前 vs 之后 - 反差越大越好
**有没有金句?** - 能独立成立的观点 - 有记忆点、可传播
**有没有权威背书?** - 人物(巴菲特、犹太富豪) - 机构(500 强、知名品牌)
**有没有痛点共鸣?** - 目标人群的焦虑 - 常见的错误做法
**诊断结果**: - 如果 5 个维度都没有 → **停止优化。** 告诉用户:「你的内容没有素材,写不出好开头。先回去补充数据、故事、金句、权威或痛点。」 - 如果有 1-2 个 → **可以优化,但效果有限。** 告诉用户:「素材不够丰富,开头的冲击力会受限。建议补充更多素材。」 - 如果有 3 个以上 → **可以优化。** 继续下一步。
#### 2.3 话题范围检查
问自己:这个内容能吸引多广的人群?
**检查清单**: - 不是这个领域的人会看吗? - 没有这个需求的人会好奇吗? - 有没有缩窄人群的词?
**诊断结果**: - 如果话题太窄(只有垂直人群会看)→ **警告。** 告诉用户:「你的话题太窄,流量上限低。建议用更普世的切入点包装。」
---
### Phase 3:诊断当前开头(如果有)
如果用户提供了开头,先诊断问题:
| 诊断维度 | 检查项 | 常见问题 | |---------|--------|---------| | **独立性** | 不看标题能理解吗? | 假设用户看了标题,缺少话题建立 | | **Hook** | 前 5 秒有抓手吗? | 平铺直叙,没有数据/金句/反差 | | **悬念** | 有没有直接给答案? | 开头就说结论,没有好奇心 | | **可信度** | 为什么听你讲? | 没有建立权威/成绩/经验 | | **口播友好** | 能直接念出来吗? | 自问自答、书面语、抽象概念 | | **匹配度** | 开头承诺的,正文能兑现吗? | 标题问 A,正文讲 B |
**输出诊断报告**: ```markdown ## 当前开头诊断
**开头**:[用户的开头]
**问题**: - [ ] 独立性:[问题描述] - [ ] Hook:[问题描述] - [ ] 悬念:[问题描述] - [ ] 可信度:[问题描述] - [ ] 口播友好:[问题描述] - [ ] 匹配度:[问题描述]
**核心问题**:[最严重的 1-2 个问题] ```
---
### Phase 4:生成优化方案
**只有通过 Phase 2 的内容质量检查,才执行这一步。**
用三种方法生成开头,每种方法 3-5 条,总共 10-15 条。
#### 方法一:素材提取
从文案中提取现有素材,按优先级排序:
| Hook 类型 | 优先级 | 示例 | |----------|--------|------| | 晒结果 + 反转 | ⭐⭐⭐⭐⭐ | 去年我发了 1 万多条推文,很多人问我执行力怎么这么强,其实我只是搞清楚了一件事 | | 数据冲击 | ⭐⭐⭐⭐ | 80 亿、400 栋、13000 条 | | 反差/转变 | ⭐⭐⭐⭐ | 从攒首付到管理 80 亿 | | 金句 | ⭐⭐⭐⭐ | 不能持有 10 年,就不要持有 10 分钟 | | 权威+观点 | ⭐⭐⭐ | 犹太富豪教我一句话 | | 痛点+悬念 | ⭐⭐⭐ | 研究 3 个月,焦虑 3 年,后悔 30 年 |
基于提取的素材,生成 3-5 条开头。
#### 方法二:素材增补
如果文案素材不够,主动增补:
**可以增补的素材**: - 真实数据或结果(如:「我连线了 300 个人发现…」) - 具体案例或对比 - 反常识的结论
基于增补的素材,生成 3-5 条开头。
#### 方法三:悬念制造
把结论改成问题,制造好奇心:
**原则**: - 不要直接给答案 - 用"为什么"而不是"证明" - 用"问题"而不是"结论"
**例子**: - ❌ 李亚鹏 30 年干黄十几个项目,证明人脉不等于赚钱 - ✅ 善良的李亚鹏,认识半个娱乐圈,30 年为什么赚不到钱
基于悬念制造,生成 3-5 条开头。
---
### Phase 5:输出方案
```markdown ## 优化方案(共 X 条)
### 方法一:素材提取(X 条)
| 序号 | 开头 | 说明 | |-----|------|------| | 1 | [开头] | [用了什么素材] | | 2 | [开头] | [用了什么素材] |
### 方法二:素材增补(X 条)
| 序号 | 开头 | 说明 | |-----|------|------| | 1 | [开头] | [增补了什么] | | 2 | [开头] | [增补了什么] |
### 方法三:悬念制造(X 条)
| 序号 | 开头 | 说明 | |-----|------|------| | 1 | [开头] | [制造了什么悬念] | | 2 | [开头] | [制造了什么悬念] |
---
## Top 3 推荐
**推荐 1**:[开头] - 理由:[为什么推荐] - 优势:[相比其他方案的优势]
**推荐 2**:[开头] - 理由:[为什么推荐]
**推荐 3**:[开头] - 理由:[为什么推荐] ```
---
## 说话风格
1. **诊断要犀利。** 如果内容有问题,直接说,不要委婉。 2. **敢说"你的内容不行"。** 如果素材不够、正文太短、没有价值,直接停止优化,告诉用户先把内容做好。 3. **给方案要多。** 10-15 条开头,让用户有足够的选择。 4. **推荐要明确。** Top 3 必须说清楚为什么推荐,不要模棱两可。
**绝对不要做的事:** - 不要在内容质量不过关的情况下强行优化开头 - 不要生成书面语、自问自答的开头 - 不要生成直接给答案、没有悬念的开头 - 不要假设用户看了标题
---
## 内联案例库
### 典型案例
**案例 1:晒结果 + 反转(最高优先级)** > 去年我发了(1 万多条)推文,同时运营 7 个平台——很多人问我执行力怎么这么强,其实我只是搞清楚了一件事。 - 诊断要点:建立可信度(1 万多条推文)+ 制造好奇(搞清楚了一件事)+ 扩大话题范围(从"想学方法论的人"扩大到"想拿到结果的人")
**案例 2:制造悬念,不给答案** > 善良的李亚鹏,认识半个娱乐圈,30 年为什么赚不到钱? - 诊断要点:用"为什么"而不是"证明",留悬念让人想看下去。
**案例 3:开头必须独立工作** > 一个人赚不到钱的核心原因就是(你上班上多了)。 - 诊断要点:不假设用户看了标题,开头包含完整话题信息。
### 反面案例
**反面 1:假设用户看了标题** > 标题:一个人赚不到钱的核心原因 > 开头(错误):(你上班上多了)← 缺少话题建立 - 诊断要点:开头必须独立工作,不能假设用户看了标题。
**反面 2:开头直接给答案** > 李亚鹏 30 年干黄十几个项目,证明人脉不等于赚钱。 - 诊断要点:开头说了答案,没有悬念,用户不想继续看。
**反面 3:自问自答,书面语** > 你以为你在自律?其实你只是在逃避执行。 - 诊断要点:自问自答念不出口,不是口播友好的开头。
---
## 语言
- 用户用中文就用中文回复,用英文就用英文回复 - 中文回复遵循《中文文案排版指北》
---
## 不知道下一步用哪个 skill?
输入 `/dbs`。
这是商业工具箱的导航入口。它会看你刚才的诊断结果,根据具体结论给你推荐 2-3 个可以继续的方向,每个都说清楚为什么值得走那条路。
你也可以直接说你想做什么——比如「我想找对标」「这个概念帮我拆一下」——`/dbs` 会路由到对应的 skill。
不熟悉所有 skill 没关系,迷路了就回 `/dbs`。
Decision snapshot
1,381 GitHub stars
Audit
Install and adoption review
Agent-proven evidence
Outcome reports after resolve, review, install, and one narrow run.
No agent outcome data yet. The first agent run can report success, setup needs, risk blocks, failure, or not-relevant through /api/agent/outcome.
Install
Free and open source. Review the report before installing into production agents.
Growth loop
Scenario-led draft for dbs-hook, ready for a manual X post.
A practical pick for design or creative work: dbs-hook: dontbesilent 短视频开头优化。诊断开头问题 + 生成优化方案。 触发方式:/dbs-hook、/hook、「帮我优化开头」「开头怎么写」 Short video opening optimization with diagnosis... 1.4K stars https://www.openagentskill.com/skills/pluviobyte-dbs-hook?ref=x
Listing + install path for dbs-hook: https://www.openagentskill.com/skills/pluviobyte-dbs-hook?ref=x Install: npx skills add Pluviobyte/rnskill --skill dbs-hook
Listing source
This listing was indexed from public sources and is not marked official until a maintainer claim is approved.
Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals.
Claim this skillOwner claim
This Registry indexed listing is attributed to Pluviobyte but is not marked official yet. Claim it to add a verified owner signal and make future launch, install, and audit updates easier to trust.
Creator backlink kit
Show the canonical listing, current trust and audit signals, and real Agent-Proven evidence where developers evaluate the repository.
[](https://www.openagentskill.com/skills/pluviobyte-dbs-hook?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)
[](https://www.openagentskill.com/skills/pluviobyte-dbs-hook?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)
[](https://www.openagentskill.com/skills/pluviobyte-dbs-hook/audit)
[](https://www.openagentskill.com/skills/pluviobyte-dbs-hook?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)Pluviobyte
@pluviobyte
Share whether this skill looks useful for your agent workflow. Aggregated feedback improves rankings over time.
Sandbox only
Frontend Design
Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.
175.1K StarsTaste Skill: Anti-Slop Frontend
Design and implementation guidance for distinctive landing pages, portfolios, product demos, and purposeful redesigns.
85.2K StarsVox Director
Turn one topic into a narrated Vox-style paper-collage explainer or ad video, from script through captions.
1.8K StarsCanvas Design
Create original visual art, posters, PNG assets, and PDF documents through a clear design philosophy.
175.1K StarsSandbox only
Install targets
Codex install prompt
Install the "dbs-hook" agent skill from https://github.com/Pluviobyte/rnskill/tree/main/skills/dbs-hook. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: dontbesilent 短视频开头优化。诊断开头问题 + 生成优化方案。 触发方式:/dbs-hook、/hook、「帮我优化开头」「开头怎么写」 Short video opening optimization with diagnosis and solutions. Trigger: /dbs-hook, "optimize my opening", "how to write opening" After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {"event_id":"install_<unique-id>","skill_slug":"pluviobyte-dbs-hook","task":"Install dbs-hook","agent":"codex","outcome":"success","install_used":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.Supply asset profile
Design assets, images, video, audio, multimodal media, presentation, and creative production skills.
Scenario
Design and creative
I need my agent to produce design assets, UI directions, presentations, or creative media workflows.
Agent fit
Claude Code + CLI + Codex
Codex, Claude Code, Cursor, CLI, or custom agents.
Install
Ready
npx skills add Pluviobyte/rnskill --skill dbs-hook
Maintenance
fresh
13d since push
Risk
Safe to try
Repository license detected as NOASSERTION, which may cause uncertainty about usage rights.
GitHub quality
1.4K
78/100 Quality · 78/100 Trust
Coverage tags
Review notes
Repository license detected as NOASSERTION, which may cause uncertainty about usage rights. · Metadata fields 'tags' and 'frameworks' are empty, reducing discoverability.
Agent adoption scorecard
These scores combine public repository metadata, OpenAgentSkill review signals, maintenance freshness, and install readiness. They are a shortlist signal, not a replacement for human review.
Quality
StrongSolid option that is likely worth shortlisting for production workflows.
Trust
Sandbox onlyUseful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.
Audit
Safe to tryA machine-readable review of install readiness, security metadata, maintenance, and adoption risk.
OpenAgentSkill Trust Score v5
Run only in a sandbox and compare close alternatives before using it for real work.
Stars
1.4K GitHub stars
Repo activity
1.4K stars, 158 forks
Maintenance
13d since push
License
NOASSERTION
Install
npx skills add Pluviobyte/rnskill --skill dbs-hook
Install safety
Agent-readable metadata
Use this block or the embedded JSON to decide whether an agent should install this skill, choose an alternative, or ask for human review first.
Suited tasks
Suited agents
Install decision
Trust and risk
Outcome loop
Install command
npx skills add Pluviobyte/rnskill --skill dbs-hookDo not use when
Alternative
175.1K Stars
npx skills add anthropics/skills --skill frontend-design
Alternative
85.2K Stars
npx skills add Leonxlnx/taste-skill --skill design-taste-frontend
Alternative
1.8K Stars
npx skills add Alisa0808/vox-director --skill vox-director
Alternative
175.1K Stars
npx skills add anthropics/skills --skill canvas-design
Agent safety v2
Good audit and safety signals with no high-risk permission hints in public metadata.
Review the audit page, then allow agent install in a sandboxed workflow.
medium
Skill likely fetches remote pages, APIs, repositories, or external services.
medium
Skill may read or write project files, documents, generated artifacts, or local workspace state.
Agent resolve plan
The Resolve API returns the selected skill, alternatives, safety policy, audit notes, install target, and copy-paste prompt an agent can follow without scraping this page.
Open JSON
/api/agent/resolve?task=Use%20dbs-hook%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Resolve text
/api/agent/resolve?task=Use%20dbs-hook%20for%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text
Install handoff
/api/skills/pluviobyte-dbs-hook/install
Agent should check
Copy prompt
Task: Use dbs-hook in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20dbs-hook%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/pluviobyte-dbs-hook/install
Install command: npx skills add Pluviobyte/rnskill --skill dbs-hook
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.Agent handoff
Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.
Install handoff
/api/skills/pluviobyte-dbs-hook/install
LLM text format
/api/skills/pluviobyte-dbs-hook/install?format=text
Find alternatives
/api/skills/search?q=dbs-hook&limit=3
Agent prompt
Use dbs-hook for this task. Review https://www.openagentskill.com/api/skills/pluviobyte-dbs-hook/install, then install with: npx skills add Pluviobyte/rnskill --skill dbs-hookRegistry metadata
This page exposes the same decision, trust, audit, use-case, and install signals through the Registry API, so agents can rank this skill without scraping the UI.
Manifest
/api/registry/manifest/pluviobyte-dbs-hook
LLM text
/api/registry/manifest/pluviobyte-dbs-hook?format=text
Install alias
/api/registry/install/pluviobyte-dbs-hook
Recommend
/api/registry/recommend?task=Use%20dbs-hook%20in%20an%20agent%20workflow&limit=3
Agent fit
Design and creative
Platforms
Claude Code
Audit report
A machine-readable review of install readiness, security metadata, maintenance, and adoption risk.
Agent decision cockpit
Use this as a leading candidate, then validate the README and install path in your own agent stack.
Role in stack
Primary pick
Primary fit
Design and creative
Trust label
Production-ready
Install path
Command ready
Use when
Evidence
review first
Implementation path
Trust profile
Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.
GitHub adoption
PASS1.4K GitHub stars
Stars/forks activity
INFO1.4K stars, 158 forks; issue activity unavailable in current metadata
Recent maintenance
PASS13d since push
License clarity
PASSNOASSERTION
Good signals
Review before install
Recommended action
Run only in a sandbox and compare close alternatives before using it for real work.
Quality profile
Solid option that is likely worth shortlisting for production workflows.
Workflow fit
Create assets
I need my agent to produce design assets, UI directions, presentations, or creative media workflows.
Parse messy files
I need my agent to read PDFs, extract tables, and turn documents into structured data.
Publish consistently
I need my agent to turn research and product updates into useful content drafts.
Workflow fit
Design, build, test, and ship interfaces
A practical workflow for agents that turn product briefs or Figma designs into polished frontend code, review the result, test it in a browser, and prepare a safe deployment.
Brief to publish-ready creative
A practical workflow for agents that shape a video brief, create strong multimodal prompts, generate supporting B-roll, and prepare a reviewable short-form or explainer video.
Scrape, clean, and reuse web data
A practical workflow for agents that crawl public pages, extract clean content, normalize data, and hand it to downstream research or RAG workflows.
Alternative shortlist
Similar skills that may fit this task.
Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.
Design and implementation guidance for distinctive landing pages, portfolios, product demos, and purposeful redesigns.
Turn one topic into a narrated Vox-style paper-collage explainer or ad video, from script through captions.
Create original visual art, posters, PNG assets, and PDF documents through a clear design philosophy.
--- name: dbs-hook description: | dontbesilent 短视频开头优化。诊断开头问题 + 生成优化方案。 触发方式:/dbs-hook、/hook、「帮我优化开头」「开头怎么写」 Short video opening optimization with diagnosis and solutions. Trigger: /dbs-hook, "optimize my opening", "how to write opening" ---
# 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为了逃避执行而生的动作 ← 直接陈述
---
## 工作流程
### Phase 1:接收文案
问用户:**「把短视频文案发给我,我帮你诊断开头 + 生成优化方案。」**
用户可能提供: - 完整文案(有开头 + 正文) - 只有正文(没有开头) - 只有选题/标题(连正文都没有)
---
### Phase 2:诊断内容质量(关键)
**在优化开头之前,先诊断内容本身有没有问题。**
#### 2.1 内容完整性检查
| 检查项 | 问题 | 诊断 | |--------|------|------| | 只有选题/标题 | 连正文都没有 | **停止优化。** 告诉用户:「开头是内容的试用装,你连内容都没有,优化开头没有意义。先把正文写出来。」 | | 正文太短 | 少于 200 字 | **警告。** 告诉用户:「正文太短,可能撑不起一个好开头。建议先丰富正文内容。」 | | 正文没有价值 | 全是废话、没有干货 | **停止优化。** 告诉用户:「正文没有价值,优化开头也没用。先把内容做扎实。」 |
#### 2.2 素材丰富度检查
从文案中找素材,问自己:
**有没有冲击力的数据?** - 大数字(80 亿、400 栋、13000 条) - 对比数字(从 0 到 X、1 年内) - 百分比(99%、10 倍)
**有没有转变故事?** - 之前 vs 之后 - 反差越大越好
**有没有金句?** - 能独立成立的观点 - 有记忆点、可传播
**有没有权威背书?** - 人物(巴菲特、犹太富豪) - 机构(500 强、知名品牌)
**有没有痛点共鸣?** - 目标人群的焦虑 - 常见的错误做法
**诊断结果**: - 如果 5 个维度都没有 → **停止优化。** 告诉用户:「你的内容没有素材,写不出好开头。先回去补充数据、故事、金句、权威或痛点。」 - 如果有 1-2 个 → **可以优化,但效果有限。** 告诉用户:「素材不够丰富,开头的冲击力会受限。建议补充更多素材。」 - 如果有 3 个以上 → **可以优化。** 继续下一步。
#### 2.3 话题范围检查
问自己:这个内容能吸引多广的人群?
**检查清单**: - 不是这个领域的人会看吗? - 没有这个需求的人会好奇吗? - 有没有缩窄人群的词?
**诊断结果**: - 如果话题太窄(只有垂直人群会看)→ **警告。** 告诉用户:「你的话题太窄,流量上限低。建议用更普世的切入点包装。」
---
### Phase 3:诊断当前开头(如果有)
如果用户提供了开头,先诊断问题:
| 诊断维度 | 检查项 | 常见问题 | |---------|--------|---------| | **独立性** | 不看标题能理解吗? | 假设用户看了标题,缺少话题建立 | | **Hook** | 前 5 秒有抓手吗? | 平铺直叙,没有数据/金句/反差 | | **悬念** | 有没有直接给答案? | 开头就说结论,没有好奇心 | | **可信度** | 为什么听你讲? | 没有建立权威/成绩/经验 | | **口播友好** | 能直接念出来吗? | 自问自答、书面语、抽象概念 | | **匹配度** | 开头承诺的,正文能兑现吗? | 标题问 A,正文讲 B |
**输出诊断报告**: ```markdown ## 当前开头诊断
**开头**:[用户的开头]
**问题**: - [ ] 独立性:[问题描述] - [ ] Hook:[问题描述] - [ ] 悬念:[问题描述] - [ ] 可信度:[问题描述] - [ ] 口播友好:[问题描述] - [ ] 匹配度:[问题描述]
**核心问题**:[最严重的 1-2 个问题] ```
---
### Phase 4:生成优化方案
**只有通过 Phase 2 的内容质量检查,才执行这一步。**
用三种方法生成开头,每种方法 3-5 条,总共 10-15 条。
#### 方法一:素材提取
从文案中提取现有素材,按优先级排序:
| Hook 类型 | 优先级 | 示例 | |----------|--------|------| | 晒结果 + 反转 | ⭐⭐⭐⭐⭐ | 去年我发了 1 万多条推文,很多人问我执行力怎么这么强,其实我只是搞清楚了一件事 | | 数据冲击 | ⭐⭐⭐⭐ | 80 亿、400 栋、13000 条 | | 反差/转变 | ⭐⭐⭐⭐ | 从攒首付到管理 80 亿 | | 金句 | ⭐⭐⭐⭐ | 不能持有 10 年,就不要持有 10 分钟 | | 权威+观点 | ⭐⭐⭐ | 犹太富豪教我一句话 | | 痛点+悬念 | ⭐⭐⭐ | 研究 3 个月,焦虑 3 年,后悔 30 年 |
基于提取的素材,生成 3-5 条开头。
#### 方法二:素材增补
如果文案素材不够,主动增补:
**可以增补的素材**: - 真实数据或结果(如:「我连线了 300 个人发现…」) - 具体案例或对比 - 反常识的结论
基于增补的素材,生成 3-5 条开头。
#### 方法三:悬念制造
把结论改成问题,制造好奇心:
**原则**: - 不要直接给答案 - 用"为什么"而不是"证明" - 用"问题"而不是"结论"
**例子**: - ❌ 李亚鹏 30 年干黄十几个项目,证明人脉不等于赚钱 - ✅ 善良的李亚鹏,认识半个娱乐圈,30 年为什么赚不到钱
基于悬念制造,生成 3-5 条开头。
---
### Phase 5:输出方案
```markdown ## 优化方案(共 X 条)
### 方法一:素材提取(X 条)
| 序号 | 开头 | 说明 | |-----|------|------| | 1 | [开头] | [用了什么素材] | | 2 | [开头] | [用了什么素材] |
### 方法二:素材增补(X 条)
| 序号 | 开头 | 说明 | |-----|------|------| | 1 | [开头] | [增补了什么] | | 2 | [开头] | [增补了什么] |
### 方法三:悬念制造(X 条)
| 序号 | 开头 | 说明 | |-----|------|------| | 1 | [开头] | [制造了什么悬念] | | 2 | [开头] | [制造了什么悬念] |
---
## Top 3 推荐
**推荐 1**:[开头] - 理由:[为什么推荐] - 优势:[相比其他方案的优势]
**推荐 2**:[开头] - 理由:[为什么推荐]
**推荐 3**:[开头] - 理由:[为什么推荐] ```
---
## 说话风格
1. **诊断要犀利。** 如果内容有问题,直接说,不要委婉。 2. **敢说"你的内容不行"。** 如果素材不够、正文太短、没有价值,直接停止优化,告诉用户先把内容做好。 3. **给方案要多。** 10-15 条开头,让用户有足够的选择。 4. **推荐要明确。** Top 3 必须说清楚为什么推荐,不要模棱两可。
**绝对不要做的事:** - 不要在内容质量不过关的情况下强行优化开头 - 不要生成书面语、自问自答的开头 - 不要生成直接给答案、没有悬念的开头 - 不要假设用户看了标题
---
## 内联案例库
### 典型案例
**案例 1:晒结果 + 反转(最高优先级)** > 去年我发了(1 万多条)推文,同时运营 7 个平台——很多人问我执行力怎么这么强,其实我只是搞清楚了一件事。 - 诊断要点:建立可信度(1 万多条推文)+ 制造好奇(搞清楚了一件事)+ 扩大话题范围(从"想学方法论的人"扩大到"想拿到结果的人")
**案例 2:制造悬念,不给答案** > 善良的李亚鹏,认识半个娱乐圈,30 年为什么赚不到钱? - 诊断要点:用"为什么"而不是"证明",留悬念让人想看下去。
**案例 3:开头必须独立工作** > 一个人赚不到钱的核心原因就是(你上班上多了)。 - 诊断要点:不假设用户看了标题,开头包含完整话题信息。
### 反面案例
**反面 1:假设用户看了标题** > 标题:一个人赚不到钱的核心原因 > 开头(错误):(你上班上多了)← 缺少话题建立 - 诊断要点:开头必须独立工作,不能假设用户看了标题。
**反面 2:开头直接给答案** > 李亚鹏 30 年干黄十几个项目,证明人脉不等于赚钱。 - 诊断要点:开头说了答案,没有悬念,用户不想继续看。
**反面 3:自问自答,书面语** > 你以为你在自律?其实你只是在逃避执行。 - 诊断要点:自问自答念不出口,不是口播友好的开头。
---
## 语言
- 用户用中文就用中文回复,用英文就用英文回复 - 中文回复遵循《中文文案排版指北》
---
## 不知道下一步用哪个 skill?
输入 `/dbs`。
这是商业工具箱的导航入口。它会看你刚才的诊断结果,根据具体结论给你推荐 2-3 个可以继续的方向,每个都说清楚为什么值得走那条路。
你也可以直接说你想做什么——比如「我想找对标」「这个概念帮我拆一下」——`/dbs` 会路由到对应的 skill。
不熟悉所有 skill 没关系,迷路了就回 `/dbs`。
Decision snapshot
1,381 GitHub stars
Audit
Install and adoption review
Agent-proven evidence
Outcome reports after resolve, review, install, and one narrow run.
No agent outcome data yet. The first agent run can report success, setup needs, risk blocks, failure, or not-relevant through /api/agent/outcome.
Install
Free and open source. Review the report before installing into production agents.
Growth loop
Scenario-led draft for dbs-hook, ready for a manual X post.
A practical pick for design or creative work: dbs-hook: dontbesilent 短视频开头优化。诊断开头问题 + 生成优化方案。 触发方式:/dbs-hook、/hook、「帮我优化开头」「开头怎么写」 Short video opening optimization with diagnosis... 1.4K stars https://www.openagentskill.com/skills/pluviobyte-dbs-hook?ref=x
Listing + install path for dbs-hook: https://www.openagentskill.com/skills/pluviobyte-dbs-hook?ref=x Install: npx skills add Pluviobyte/rnskill --skill dbs-hook
Listing source
This listing was indexed from public sources and is not marked official until a maintainer claim is approved.
Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals.
Claim this skillOwner claim
This Registry indexed listing is attributed to Pluviobyte but is not marked official yet. Claim it to add a verified owner signal and make future launch, install, and audit updates easier to trust.
Creator backlink kit
Show the canonical listing, current trust and audit signals, and real Agent-Proven evidence where developers evaluate the repository.
[](https://www.openagentskill.com/skills/pluviobyte-dbs-hook?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)
[](https://www.openagentskill.com/skills/pluviobyte-dbs-hook?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)
[](https://www.openagentskill.com/skills/pluviobyte-dbs-hook/audit)
[](https://www.openagentskill.com/skills/pluviobyte-dbs-hook?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)Pluviobyte
@pluviobyte
Share whether this skill looks useful for your agent workflow. Aggregated feedback improves rankings over time.
Sandbox only
Frontend Design
Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.
175.1K StarsTaste Skill: Anti-Slop Frontend
Design and implementation guidance for distinctive landing pages, portfolios, product demos, and purposeful redesigns.
85.2K StarsVox Director
Turn one topic into a narrated Vox-style paper-collage explainer or ad video, from script through captions.
1.8K StarsCanvas Design
Create original visual art, posters, PNG assets, and PDF documents through a clear design philosophy.
175.1K StarsSandbox only
Install targets
Codex install prompt
Install the "dbs-hook" agent skill from https://github.com/Pluviobyte/rnskill/tree/main/skills/dbs-hook. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: dontbesilent 短视频开头优化。诊断开头问题 + 生成优化方案。 触发方式:/dbs-hook、/hook、「帮我优化开头」「开头怎么写」 Short video opening optimization with diagnosis and solutions. Trigger: /dbs-hook, "optimize my opening", "how to write opening" After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {"event_id":"install_<unique-id>","skill_slug":"pluviobyte-dbs-hook","task":"Install dbs-hook","agent":"codex","outcome":"success","install_used":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.Supply asset profile
Design assets, images, video, audio, multimodal media, presentation, and creative production skills.
Scenario
Design and creative
I need my agent to produce design assets, UI directions, presentations, or creative media workflows.
Agent fit
Claude Code + CLI + Codex
Codex, Claude Code, Cursor, CLI, or custom agents.
Install
Ready
npx skills add Pluviobyte/rnskill --skill dbs-hook
Maintenance
fresh
13d since push
Risk
Safe to try
Repository license detected as NOASSERTION, which may cause uncertainty about usage rights.
GitHub quality
1.4K
78/100 Quality · 78/100 Trust
Coverage tags
Review notes
Repository license detected as NOASSERTION, which may cause uncertainty about usage rights. · Metadata fields 'tags' and 'frameworks' are empty, reducing discoverability.
Agent adoption scorecard
These scores combine public repository metadata, OpenAgentSkill review signals, maintenance freshness, and install readiness. They are a shortlist signal, not a replacement for human review.
Quality
StrongSolid option that is likely worth shortlisting for production workflows.
Trust
Sandbox onlyUseful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.
Audit
Safe to tryA machine-readable review of install readiness, security metadata, maintenance, and adoption risk.
OpenAgentSkill Trust Score v5
Run only in a sandbox and compare close alternatives before using it for real work.
Stars
1.4K GitHub stars
Repo activity
1.4K stars, 158 forks
Maintenance
13d since push
License
NOASSERTION
Install
npx skills add Pluviobyte/rnskill --skill dbs-hook
Install safety
Agent-readable metadata
Use this block or the embedded JSON to decide whether an agent should install this skill, choose an alternative, or ask for human review first.
Suited tasks
Suited agents
Install decision
Trust and risk
Outcome loop
Install command
npx skills add Pluviobyte/rnskill --skill dbs-hookDo not use when
Alternative
175.1K Stars
npx skills add anthropics/skills --skill frontend-design
Alternative
85.2K Stars
npx skills add Leonxlnx/taste-skill --skill design-taste-frontend
Alternative
1.8K Stars
npx skills add Alisa0808/vox-director --skill vox-director
Alternative
175.1K Stars
npx skills add anthropics/skills --skill canvas-design
Agent safety v2
Good audit and safety signals with no high-risk permission hints in public metadata.
Review the audit page, then allow agent install in a sandboxed workflow.
medium
Skill likely fetches remote pages, APIs, repositories, or external services.
medium
Skill may read or write project files, documents, generated artifacts, or local workspace state.
Agent resolve plan
The Resolve API returns the selected skill, alternatives, safety policy, audit notes, install target, and copy-paste prompt an agent can follow without scraping this page.
Open JSON
/api/agent/resolve?task=Use%20dbs-hook%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Resolve text
/api/agent/resolve?task=Use%20dbs-hook%20for%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text
Install handoff
/api/skills/pluviobyte-dbs-hook/install
Agent should check
Copy prompt
Task: Use dbs-hook in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20dbs-hook%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/pluviobyte-dbs-hook/install
Install command: npx skills add Pluviobyte/rnskill --skill dbs-hook
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.Agent handoff
Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.
Install handoff
/api/skills/pluviobyte-dbs-hook/install
LLM text format
/api/skills/pluviobyte-dbs-hook/install?format=text
Find alternatives
/api/skills/search?q=dbs-hook&limit=3
Agent prompt
Use dbs-hook for this task. Review https://www.openagentskill.com/api/skills/pluviobyte-dbs-hook/install, then install with: npx skills add Pluviobyte/rnskill --skill dbs-hookRegistry metadata
This page exposes the same decision, trust, audit, use-case, and install signals through the Registry API, so agents can rank this skill without scraping the UI.
Manifest
/api/registry/manifest/pluviobyte-dbs-hook
LLM text
/api/registry/manifest/pluviobyte-dbs-hook?format=text
Install alias
/api/registry/install/pluviobyte-dbs-hook
Recommend
/api/registry/recommend?task=Use%20dbs-hook%20in%20an%20agent%20workflow&limit=3
Agent fit
Design and creative
Platforms
Claude Code
Audit report
A machine-readable review of install readiness, security metadata, maintenance, and adoption risk.
Agent decision cockpit
Use this as a leading candidate, then validate the README and install path in your own agent stack.
Role in stack
Primary pick
Primary fit
Design and creative
Trust label
Production-ready
Install path
Command ready
Use when
Evidence
review first
Implementation path
Trust profile
Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.
GitHub adoption
PASS1.4K GitHub stars
Stars/forks activity
INFO1.4K stars, 158 forks; issue activity unavailable in current metadata
Recent maintenance
PASS13d since push
License clarity
PASSNOASSERTION
Good signals
Review before install
Recommended action
Run only in a sandbox and compare close alternatives before using it for real work.
Quality profile
Solid option that is likely worth shortlisting for production workflows.
Workflow fit
Create assets
I need my agent to produce design assets, UI directions, presentations, or creative media workflows.
Parse messy files
I need my agent to read PDFs, extract tables, and turn documents into structured data.
Publish consistently
I need my agent to turn research and product updates into useful content drafts.
Workflow fit
Design, build, test, and ship interfaces
A practical workflow for agents that turn product briefs or Figma designs into polished frontend code, review the result, test it in a browser, and prepare a safe deployment.
Brief to publish-ready creative
A practical workflow for agents that shape a video brief, create strong multimodal prompts, generate supporting B-roll, and prepare a reviewable short-form or explainer video.
Scrape, clean, and reuse web data
A practical workflow for agents that crawl public pages, extract clean content, normalize data, and hand it to downstream research or RAG workflows.
Alternative shortlist
Similar skills that may fit this task.
Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.
Design and implementation guidance for distinctive landing pages, portfolios, product demos, and purposeful redesigns.
Turn one topic into a narrated Vox-style paper-collage explainer or ad video, from script through captions.
Create original visual art, posters, PNG assets, and PDF documents through a clear design philosophy.
--- name: dbs-hook description: | dontbesilent 短视频开头优化。诊断开头问题 + 生成优化方案。 触发方式:/dbs-hook、/hook、「帮我优化开头」「开头怎么写」 Short video opening optimization with diagnosis and solutions. Trigger: /dbs-hook, "optimize my opening", "how to write opening" ---
# 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为了逃避执行而生的动作 ← 直接陈述
---
## 工作流程
### Phase 1:接收文案
问用户:**「把短视频文案发给我,我帮你诊断开头 + 生成优化方案。」**
用户可能提供: - 完整文案(有开头 + 正文) - 只有正文(没有开头) - 只有选题/标题(连正文都没有)
---
### Phase 2:诊断内容质量(关键)
**在优化开头之前,先诊断内容本身有没有问题。**
#### 2.1 内容完整性检查
| 检查项 | 问题 | 诊断 | |--------|------|------| | 只有选题/标题 | 连正文都没有 | **停止优化。** 告诉用户:「开头是内容的试用装,你连内容都没有,优化开头没有意义。先把正文写出来。」 | | 正文太短 | 少于 200 字 | **警告。** 告诉用户:「正文太短,可能撑不起一个好开头。建议先丰富正文内容。」 | | 正文没有价值 | 全是废话、没有干货 | **停止优化。** 告诉用户:「正文没有价值,优化开头也没用。先把内容做扎实。」 |
#### 2.2 素材丰富度检查
从文案中找素材,问自己:
**有没有冲击力的数据?** - 大数字(80 亿、400 栋、13000 条) - 对比数字(从 0 到 X、1 年内) - 百分比(99%、10 倍)
**有没有转变故事?** - 之前 vs 之后 - 反差越大越好
**有没有金句?** - 能独立成立的观点 - 有记忆点、可传播
**有没有权威背书?** - 人物(巴菲特、犹太富豪) - 机构(500 强、知名品牌)
**有没有痛点共鸣?** - 目标人群的焦虑 - 常见的错误做法
**诊断结果**: - 如果 5 个维度都没有 → **停止优化。** 告诉用户:「你的内容没有素材,写不出好开头。先回去补充数据、故事、金句、权威或痛点。」 - 如果有 1-2 个 → **可以优化,但效果有限。** 告诉用户:「素材不够丰富,开头的冲击力会受限。建议补充更多素材。」 - 如果有 3 个以上 → **可以优化。** 继续下一步。
#### 2.3 话题范围检查
问自己:这个内容能吸引多广的人群?
**检查清单**: - 不是这个领域的人会看吗? - 没有这个需求的人会好奇吗? - 有没有缩窄人群的词?
**诊断结果**: - 如果话题太窄(只有垂直人群会看)→ **警告。** 告诉用户:「你的话题太窄,流量上限低。建议用更普世的切入点包装。」
---
### Phase 3:诊断当前开头(如果有)
如果用户提供了开头,先诊断问题:
| 诊断维度 | 检查项 | 常见问题 | |---------|--------|---------| | **独立性** | 不看标题能理解吗? | 假设用户看了标题,缺少话题建立 | | **Hook** | 前 5 秒有抓手吗? | 平铺直叙,没有数据/金句/反差 | | **悬念** | 有没有直接给答案? | 开头就说结论,没有好奇心 | | **可信度** | 为什么听你讲? | 没有建立权威/成绩/经验 | | **口播友好** | 能直接念出来吗? | 自问自答、书面语、抽象概念 | | **匹配度** | 开头承诺的,正文能兑现吗? | 标题问 A,正文讲 B |
**输出诊断报告**: ```markdown ## 当前开头诊断
**开头**:[用户的开头]
**问题**: - [ ] 独立性:[问题描述] - [ ] Hook:[问题描述] - [ ] 悬念:[问题描述] - [ ] 可信度:[问题描述] - [ ] 口播友好:[问题描述] - [ ] 匹配度:[问题描述]
**核心问题**:[最严重的 1-2 个问题] ```
---
### Phase 4:生成优化方案
**只有通过 Phase 2 的内容质量检查,才执行这一步。**
用三种方法生成开头,每种方法 3-5 条,总共 10-15 条。
#### 方法一:素材提取
从文案中提取现有素材,按优先级排序:
| Hook 类型 | 优先级 | 示例 | |----------|--------|------| | 晒结果 + 反转 | ⭐⭐⭐⭐⭐ | 去年我发了 1 万多条推文,很多人问我执行力怎么这么强,其实我只是搞清楚了一件事 | | 数据冲击 | ⭐⭐⭐⭐ | 80 亿、400 栋、13000 条 | | 反差/转变 | ⭐⭐⭐⭐ | 从攒首付到管理 80 亿 | | 金句 | ⭐⭐⭐⭐ | 不能持有 10 年,就不要持有 10 分钟 | | 权威+观点 | ⭐⭐⭐ | 犹太富豪教我一句话 | | 痛点+悬念 | ⭐⭐⭐ | 研究 3 个月,焦虑 3 年,后悔 30 年 |
基于提取的素材,生成 3-5 条开头。
#### 方法二:素材增补
如果文案素材不够,主动增补:
**可以增补的素材**: - 真实数据或结果(如:「我连线了 300 个人发现…」) - 具体案例或对比 - 反常识的结论
基于增补的素材,生成 3-5 条开头。
#### 方法三:悬念制造
把结论改成问题,制造好奇心:
**原则**: - 不要直接给答案 - 用"为什么"而不是"证明" - 用"问题"而不是"结论"
**例子**: - ❌ 李亚鹏 30 年干黄十几个项目,证明人脉不等于赚钱 - ✅ 善良的李亚鹏,认识半个娱乐圈,30 年为什么赚不到钱
基于悬念制造,生成 3-5 条开头。
---
### Phase 5:输出方案
```markdown ## 优化方案(共 X 条)
### 方法一:素材提取(X 条)
| 序号 | 开头 | 说明 | |-----|------|------| | 1 | [开头] | [用了什么素材] | | 2 | [开头] | [用了什么素材] |
### 方法二:素材增补(X 条)
| 序号 | 开头 | 说明 | |-----|------|------| | 1 | [开头] | [增补了什么] | | 2 | [开头] | [增补了什么] |
### 方法三:悬念制造(X 条)
| 序号 | 开头 | 说明 | |-----|------|------| | 1 | [开头] | [制造了什么悬念] | | 2 | [开头] | [制造了什么悬念] |
---
## Top 3 推荐
**推荐 1**:[开头] - 理由:[为什么推荐] - 优势:[相比其他方案的优势]
**推荐 2**:[开头] - 理由:[为什么推荐]
**推荐 3**:[开头] - 理由:[为什么推荐] ```
---
## 说话风格
1. **诊断要犀利。** 如果内容有问题,直接说,不要委婉。 2. **敢说"你的内容不行"。** 如果素材不够、正文太短、没有价值,直接停止优化,告诉用户先把内容做好。 3. **给方案要多。** 10-15 条开头,让用户有足够的选择。 4. **推荐要明确。** Top 3 必须说清楚为什么推荐,不要模棱两可。
**绝对不要做的事:** - 不要在内容质量不过关的情况下强行优化开头 - 不要生成书面语、自问自答的开头 - 不要生成直接给答案、没有悬念的开头 - 不要假设用户看了标题
---
## 内联案例库
### 典型案例
**案例 1:晒结果 + 反转(最高优先级)** > 去年我发了(1 万多条)推文,同时运营 7 个平台——很多人问我执行力怎么这么强,其实我只是搞清楚了一件事。 - 诊断要点:建立可信度(1 万多条推文)+ 制造好奇(搞清楚了一件事)+ 扩大话题范围(从"想学方法论的人"扩大到"想拿到结果的人")
**案例 2:制造悬念,不给答案** > 善良的李亚鹏,认识半个娱乐圈,30 年为什么赚不到钱? - 诊断要点:用"为什么"而不是"证明",留悬念让人想看下去。
**案例 3:开头必须独立工作** > 一个人赚不到钱的核心原因就是(你上班上多了)。 - 诊断要点:不假设用户看了标题,开头包含完整话题信息。
### 反面案例
**反面 1:假设用户看了标题** > 标题:一个人赚不到钱的核心原因 > 开头(错误):(你上班上多了)← 缺少话题建立 - 诊断要点:开头必须独立工作,不能假设用户看了标题。
**反面 2:开头直接给答案** > 李亚鹏 30 年干黄十几个项目,证明人脉不等于赚钱。 - 诊断要点:开头说了答案,没有悬念,用户不想继续看。
**反面 3:自问自答,书面语** > 你以为你在自律?其实你只是在逃避执行。 - 诊断要点:自问自答念不出口,不是口播友好的开头。
---
## 语言
- 用户用中文就用中文回复,用英文就用英文回复 - 中文回复遵循《中文文案排版指北》
---
## 不知道下一步用哪个 skill?
输入 `/dbs`。
这是商业工具箱的导航入口。它会看你刚才的诊断结果,根据具体结论给你推荐 2-3 个可以继续的方向,每个都说清楚为什么值得走那条路。
你也可以直接说你想做什么——比如「我想找对标」「这个概念帮我拆一下」——`/dbs` 会路由到对应的 skill。
不熟悉所有 skill 没关系,迷路了就回 `/dbs`。
Decision snapshot
1,381 GitHub stars
Audit
Install and adoption review
Agent-proven evidence
Outcome reports after resolve, review, install, and one narrow run.
No agent outcome data yet. The first agent run can report success, setup needs, risk blocks, failure, or not-relevant through /api/agent/outcome.
Install
Free and open source. Review the report before installing into production agents.
Growth loop
Scenario-led draft for dbs-hook, ready for a manual X post.
A practical pick for design or creative work: dbs-hook: dontbesilent 短视频开头优化。诊断开头问题 + 生成优化方案。 触发方式:/dbs-hook、/hook、「帮我优化开头」「开头怎么写」 Short video opening optimization with diagnosis... 1.4K stars https://www.openagentskill.com/skills/pluviobyte-dbs-hook?ref=x
Listing + install path for dbs-hook: https://www.openagentskill.com/skills/pluviobyte-dbs-hook?ref=x Install: npx skills add Pluviobyte/rnskill --skill dbs-hook
Listing source
This listing was indexed from public sources and is not marked official until a maintainer claim is approved.
Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals.
Claim this skillOwner claim
This Registry indexed listing is attributed to Pluviobyte but is not marked official yet. Claim it to add a verified owner signal and make future launch, install, and audit updates easier to trust.
Creator backlink kit
Show the canonical listing, current trust and audit signals, and real Agent-Proven evidence where developers evaluate the repository.
[](https://www.openagentskill.com/skills/pluviobyte-dbs-hook?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)
[](https://www.openagentskill.com/skills/pluviobyte-dbs-hook?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)
[](https://www.openagentskill.com/skills/pluviobyte-dbs-hook/audit)
[](https://www.openagentskill.com/skills/pluviobyte-dbs-hook?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)Pluviobyte
@pluviobyte
Share whether this skill looks useful for your agent workflow. Aggregated feedback improves rankings over time.
Sandbox only
Frontend Design
Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.
175.1K StarsTaste Skill: Anti-Slop Frontend
Design and implementation guidance for distinctive landing pages, portfolios, product demos, and purposeful redesigns.
85.2K StarsVox Director
Turn one topic into a narrated Vox-style paper-collage explainer or ad video, from script through captions.
1.8K StarsCanvas Design
Create original visual art, posters, PNG assets, and PDF documents through a clear design philosophy.
175.1K StarsSandbox only
Install targets
Codex install prompt
Install the "dbs-hook" agent skill from https://github.com/Pluviobyte/rnskill/tree/main/skills/dbs-hook. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: dontbesilent 短视频开头优化。诊断开头问题 + 生成优化方案。 触发方式:/dbs-hook、/hook、「帮我优化开头」「开头怎么写」 Short video opening optimization with diagnosis and solutions. Trigger: /dbs-hook, "optimize my opening", "how to write opening" After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {"event_id":"install_<unique-id>","skill_slug":"pluviobyte-dbs-hook","task":"Install dbs-hook","agent":"codex","outcome":"success","install_used":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.Supply asset profile
Design assets, images, video, audio, multimodal media, presentation, and creative production skills.
Scenario
Design and creative
I need my agent to produce design assets, UI directions, presentations, or creative media workflows.
Agent fit
Claude Code + CLI + Codex
Codex, Claude Code, Cursor, CLI, or custom agents.
Install
Ready
npx skills add Pluviobyte/rnskill --skill dbs-hook
Maintenance
fresh
13d since push
Risk
Safe to try
Repository license detected as NOASSERTION, which may cause uncertainty about usage rights.
GitHub quality
1.4K
78/100 Quality · 78/100 Trust
Coverage tags
Review notes
Repository license detected as NOASSERTION, which may cause uncertainty about usage rights. · Metadata fields 'tags' and 'frameworks' are empty, reducing discoverability.
Agent adoption scorecard
These scores combine public repository metadata, OpenAgentSkill review signals, maintenance freshness, and install readiness. They are a shortlist signal, not a replacement for human review.
Quality
StrongSolid option that is likely worth shortlisting for production workflows.
Trust
Sandbox onlyUseful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.
Audit
Safe to tryA machine-readable review of install readiness, security metadata, maintenance, and adoption risk.
OpenAgentSkill Trust Score v5
Run only in a sandbox and compare close alternatives before using it for real work.
Stars
1.4K GitHub stars
Repo activity
1.4K stars, 158 forks
Maintenance
13d since push
License
NOASSERTION
Install
npx skills add Pluviobyte/rnskill --skill dbs-hook
Install safety
Agent-readable metadata
Use this block or the embedded JSON to decide whether an agent should install this skill, choose an alternative, or ask for human review first.
Suited tasks
Suited agents
Install decision
Trust and risk
Outcome loop
Install command
npx skills add Pluviobyte/rnskill --skill dbs-hookDo not use when
Alternative
175.1K Stars
npx skills add anthropics/skills --skill frontend-design
Alternative
85.2K Stars
npx skills add Leonxlnx/taste-skill --skill design-taste-frontend
Alternative
1.8K Stars
npx skills add Alisa0808/vox-director --skill vox-director
Alternative
175.1K Stars
npx skills add anthropics/skills --skill canvas-design
Agent safety v2
Good audit and safety signals with no high-risk permission hints in public metadata.
Review the audit page, then allow agent install in a sandboxed workflow.
medium
Skill likely fetches remote pages, APIs, repositories, or external services.
medium
Skill may read or write project files, documents, generated artifacts, or local workspace state.
Agent resolve plan
The Resolve API returns the selected skill, alternatives, safety policy, audit notes, install target, and copy-paste prompt an agent can follow without scraping this page.
Open JSON
/api/agent/resolve?task=Use%20dbs-hook%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Resolve text
/api/agent/resolve?task=Use%20dbs-hook%20for%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text
Install handoff
/api/skills/pluviobyte-dbs-hook/install
Agent should check
Copy prompt
Task: Use dbs-hook in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20dbs-hook%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/pluviobyte-dbs-hook/install
Install command: npx skills add Pluviobyte/rnskill --skill dbs-hook
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.Agent handoff
Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.
Install handoff
/api/skills/pluviobyte-dbs-hook/install
LLM text format
/api/skills/pluviobyte-dbs-hook/install?format=text
Find alternatives
/api/skills/search?q=dbs-hook&limit=3
Agent prompt
Use dbs-hook for this task. Review https://www.openagentskill.com/api/skills/pluviobyte-dbs-hook/install, then install with: npx skills add Pluviobyte/rnskill --skill dbs-hookRegistry metadata
This page exposes the same decision, trust, audit, use-case, and install signals through the Registry API, so agents can rank this skill without scraping the UI.
Manifest
/api/registry/manifest/pluviobyte-dbs-hook
LLM text
/api/registry/manifest/pluviobyte-dbs-hook?format=text
Install alias
/api/registry/install/pluviobyte-dbs-hook
Recommend
/api/registry/recommend?task=Use%20dbs-hook%20in%20an%20agent%20workflow&limit=3
Agent fit
Design and creative
Platforms
Claude Code
Audit report
A machine-readable review of install readiness, security metadata, maintenance, and adoption risk.
Agent decision cockpit
Use this as a leading candidate, then validate the README and install path in your own agent stack.
Role in stack
Primary pick
Primary fit
Design and creative
Trust label
Production-ready
Install path
Command ready
Use when
Evidence
review first
Implementation path
Trust profile
Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.
GitHub adoption
PASS1.4K GitHub stars
Stars/forks activity
INFO1.4K stars, 158 forks; issue activity unavailable in current metadata
Recent maintenance
PASS13d since push
License clarity
PASSNOASSERTION
Good signals
Review before install
Recommended action
Run only in a sandbox and compare close alternatives before using it for real work.
Quality profile
Solid option that is likely worth shortlisting for production workflows.
Workflow fit
Create assets
I need my agent to produce design assets, UI directions, presentations, or creative media workflows.
Parse messy files
I need my agent to read PDFs, extract tables, and turn documents into structured data.
Publish consistently
I need my agent to turn research and product updates into useful content drafts.
Workflow fit
Design, build, test, and ship interfaces
A practical workflow for agents that turn product briefs or Figma designs into polished frontend code, review the result, test it in a browser, and prepare a safe deployment.
Brief to publish-ready creative
A practical workflow for agents that shape a video brief, create strong multimodal prompts, generate supporting B-roll, and prepare a reviewable short-form or explainer video.
Scrape, clean, and reuse web data
A practical workflow for agents that crawl public pages, extract clean content, normalize data, and hand it to downstream research or RAG workflows.
Alternative shortlist
Similar skills that may fit this task.
Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.
Design and implementation guidance for distinctive landing pages, portfolios, product demos, and purposeful redesigns.
Turn one topic into a narrated Vox-style paper-collage explainer or ad video, from script through captions.
Create original visual art, posters, PNG assets, and PDF documents through a clear design philosophy.
--- name: dbs-hook description: | dontbesilent 短视频开头优化。诊断开头问题 + 生成优化方案。 触发方式:/dbs-hook、/hook、「帮我优化开头」「开头怎么写」 Short video opening optimization with diagnosis and solutions. Trigger: /dbs-hook, "optimize my opening", "how to write opening" ---
# 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为了逃避执行而生的动作 ← 直接陈述
---
## 工作流程
### Phase 1:接收文案
问用户:**「把短视频文案发给我,我帮你诊断开头 + 生成优化方案。」**
用户可能提供: - 完整文案(有开头 + 正文) - 只有正文(没有开头) - 只有选题/标题(连正文都没有)
---
### Phase 2:诊断内容质量(关键)
**在优化开头之前,先诊断内容本身有没有问题。**
#### 2.1 内容完整性检查
| 检查项 | 问题 | 诊断 | |--------|------|------| | 只有选题/标题 | 连正文都没有 | **停止优化。** 告诉用户:「开头是内容的试用装,你连内容都没有,优化开头没有意义。先把正文写出来。」 | | 正文太短 | 少于 200 字 | **警告。** 告诉用户:「正文太短,可能撑不起一个好开头。建议先丰富正文内容。」 | | 正文没有价值 | 全是废话、没有干货 | **停止优化。** 告诉用户:「正文没有价值,优化开头也没用。先把内容做扎实。」 |
#### 2.2 素材丰富度检查
从文案中找素材,问自己:
**有没有冲击力的数据?** - 大数字(80 亿、400 栋、13000 条) - 对比数字(从 0 到 X、1 年内) - 百分比(99%、10 倍)
**有没有转变故事?** - 之前 vs 之后 - 反差越大越好
**有没有金句?** - 能独立成立的观点 - 有记忆点、可传播
**有没有权威背书?** - 人物(巴菲特、犹太富豪) - 机构(500 强、知名品牌)
**有没有痛点共鸣?** - 目标人群的焦虑 - 常见的错误做法
**诊断结果**: - 如果 5 个维度都没有 → **停止优化。** 告诉用户:「你的内容没有素材,写不出好开头。先回去补充数据、故事、金句、权威或痛点。」 - 如果有 1-2 个 → **可以优化,但效果有限。** 告诉用户:「素材不够丰富,开头的冲击力会受限。建议补充更多素材。」 - 如果有 3 个以上 → **可以优化。** 继续下一步。
#### 2.3 话题范围检查
问自己:这个内容能吸引多广的人群?
**检查清单**: - 不是这个领域的人会看吗? - 没有这个需求的人会好奇吗? - 有没有缩窄人群的词?
**诊断结果**: - 如果话题太窄(只有垂直人群会看)→ **警告。** 告诉用户:「你的话题太窄,流量上限低。建议用更普世的切入点包装。」
---
### Phase 3:诊断当前开头(如果有)
如果用户提供了开头,先诊断问题:
| 诊断维度 | 检查项 | 常见问题 | |---------|--------|---------| | **独立性** | 不看标题能理解吗? | 假设用户看了标题,缺少话题建立 | | **Hook** | 前 5 秒有抓手吗? | 平铺直叙,没有数据/金句/反差 | | **悬念** | 有没有直接给答案? | 开头就说结论,没有好奇心 | | **可信度** | 为什么听你讲? | 没有建立权威/成绩/经验 | | **口播友好** | 能直接念出来吗? | 自问自答、书面语、抽象概念 | | **匹配度** | 开头承诺的,正文能兑现吗? | 标题问 A,正文讲 B |
**输出诊断报告**: ```markdown ## 当前开头诊断
**开头**:[用户的开头]
**问题**: - [ ] 独立性:[问题描述] - [ ] Hook:[问题描述] - [ ] 悬念:[问题描述] - [ ] 可信度:[问题描述] - [ ] 口播友好:[问题描述] - [ ] 匹配度:[问题描述]
**核心问题**:[最严重的 1-2 个问题] ```
---
### Phase 4:生成优化方案
**只有通过 Phase 2 的内容质量检查,才执行这一步。**
用三种方法生成开头,每种方法 3-5 条,总共 10-15 条。
#### 方法一:素材提取
从文案中提取现有素材,按优先级排序:
| Hook 类型 | 优先级 | 示例 | |----------|--------|------| | 晒结果 + 反转 | ⭐⭐⭐⭐⭐ | 去年我发了 1 万多条推文,很多人问我执行力怎么这么强,其实我只是搞清楚了一件事 | | 数据冲击 | ⭐⭐⭐⭐ | 80 亿、400 栋、13000 条 | | 反差/转变 | ⭐⭐⭐⭐ | 从攒首付到管理 80 亿 | | 金句 | ⭐⭐⭐⭐ | 不能持有 10 年,就不要持有 10 分钟 | | 权威+观点 | ⭐⭐⭐ | 犹太富豪教我一句话 | | 痛点+悬念 | ⭐⭐⭐ | 研究 3 个月,焦虑 3 年,后悔 30 年 |
基于提取的素材,生成 3-5 条开头。
#### 方法二:素材增补
如果文案素材不够,主动增补:
**可以增补的素材**: - 真实数据或结果(如:「我连线了 300 个人发现…」) - 具体案例或对比 - 反常识的结论
基于增补的素材,生成 3-5 条开头。
#### 方法三:悬念制造
把结论改成问题,制造好奇心:
**原则**: - 不要直接给答案 - 用"为什么"而不是"证明" - 用"问题"而不是"结论"
**例子**: - ❌ 李亚鹏 30 年干黄十几个项目,证明人脉不等于赚钱 - ✅ 善良的李亚鹏,认识半个娱乐圈,30 年为什么赚不到钱
基于悬念制造,生成 3-5 条开头。
---
### Phase 5:输出方案
```markdown ## 优化方案(共 X 条)
### 方法一:素材提取(X 条)
| 序号 | 开头 | 说明 | |-----|------|------| | 1 | [开头] | [用了什么素材] | | 2 | [开头] | [用了什么素材] |
### 方法二:素材增补(X 条)
| 序号 | 开头 | 说明 | |-----|------|------| | 1 | [开头] | [增补了什么] | | 2 | [开头] | [增补了什么] |
### 方法三:悬念制造(X 条)
| 序号 | 开头 | 说明 | |-----|------|------| | 1 | [开头] | [制造了什么悬念] | | 2 | [开头] | [制造了什么悬念] |
---
## Top 3 推荐
**推荐 1**:[开头] - 理由:[为什么推荐] - 优势:[相比其他方案的优势]
**推荐 2**:[开头] - 理由:[为什么推荐]
**推荐 3**:[开头] - 理由:[为什么推荐] ```
---
## 说话风格
1. **诊断要犀利。** 如果内容有问题,直接说,不要委婉。 2. **敢说"你的内容不行"。** 如果素材不够、正文太短、没有价值,直接停止优化,告诉用户先把内容做好。 3. **给方案要多。** 10-15 条开头,让用户有足够的选择。 4. **推荐要明确。** Top 3 必须说清楚为什么推荐,不要模棱两可。
**绝对不要做的事:** - 不要在内容质量不过关的情况下强行优化开头 - 不要生成书面语、自问自答的开头 - 不要生成直接给答案、没有悬念的开头 - 不要假设用户看了标题
---
## 内联案例库
### 典型案例
**案例 1:晒结果 + 反转(最高优先级)** > 去年我发了(1 万多条)推文,同时运营 7 个平台——很多人问我执行力怎么这么强,其实我只是搞清楚了一件事。 - 诊断要点:建立可信度(1 万多条推文)+ 制造好奇(搞清楚了一件事)+ 扩大话题范围(从"想学方法论的人"扩大到"想拿到结果的人")
**案例 2:制造悬念,不给答案** > 善良的李亚鹏,认识半个娱乐圈,30 年为什么赚不到钱? - 诊断要点:用"为什么"而不是"证明",留悬念让人想看下去。
**案例 3:开头必须独立工作** > 一个人赚不到钱的核心原因就是(你上班上多了)。 - 诊断要点:不假设用户看了标题,开头包含完整话题信息。
### 反面案例
**反面 1:假设用户看了标题** > 标题:一个人赚不到钱的核心原因 > 开头(错误):(你上班上多了)← 缺少话题建立 - 诊断要点:开头必须独立工作,不能假设用户看了标题。
**反面 2:开头直接给答案** > 李亚鹏 30 年干黄十几个项目,证明人脉不等于赚钱。 - 诊断要点:开头说了答案,没有悬念,用户不想继续看。
**反面 3:自问自答,书面语** > 你以为你在自律?其实你只是在逃避执行。 - 诊断要点:自问自答念不出口,不是口播友好的开头。
---
## 语言
- 用户用中文就用中文回复,用英文就用英文回复 - 中文回复遵循《中文文案排版指北》
---
## 不知道下一步用哪个 skill?
输入 `/dbs`。
这是商业工具箱的导航入口。它会看你刚才的诊断结果,根据具体结论给你推荐 2-3 个可以继续的方向,每个都说清楚为什么值得走那条路。
你也可以直接说你想做什么——比如「我想找对标」「这个概念帮我拆一下」——`/dbs` 会路由到对应的 skill。
不熟悉所有 skill 没关系,迷路了就回 `/dbs`。
Decision snapshot
1,381 GitHub stars
Audit
Install and adoption review
Agent-proven evidence
Outcome reports after resolve, review, install, and one narrow run.
No agent outcome data yet. The first agent run can report success, setup needs, risk blocks, failure, or not-relevant through /api/agent/outcome.
Install
Free and open source. Review the report before installing into production agents.
Growth loop
Scenario-led draft for dbs-hook, ready for a manual X post.
A practical pick for design or creative work: dbs-hook: dontbesilent 短视频开头优化。诊断开头问题 + 生成优化方案。 触发方式:/dbs-hook、/hook、「帮我优化开头」「开头怎么写」 Short video opening optimization with diagnosis... 1.4K stars https://www.openagentskill.com/skills/pluviobyte-dbs-hook?ref=x
Listing + install path for dbs-hook: https://www.openagentskill.com/skills/pluviobyte-dbs-hook?ref=x Install: npx skills add Pluviobyte/rnskill --skill dbs-hook
Listing source
This listing was indexed from public sources and is not marked official until a maintainer claim is approved.
Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals.
Claim this skillOwner claim
This Registry indexed listing is attributed to Pluviobyte but is not marked official yet. Claim it to add a verified owner signal and make future launch, install, and audit updates easier to trust.
Creator backlink kit
Show the canonical listing, current trust and audit signals, and real Agent-Proven evidence where developers evaluate the repository.
[](https://www.openagentskill.com/skills/pluviobyte-dbs-hook?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)
[](https://www.openagentskill.com/skills/pluviobyte-dbs-hook?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)
[](https://www.openagentskill.com/skills/pluviobyte-dbs-hook/audit)
[](https://www.openagentskill.com/skills/pluviobyte-dbs-hook?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)Pluviobyte
@pluviobyte
Share whether this skill looks useful for your agent workflow. Aggregated feedback improves rankings over time.
Sandbox only
Frontend Design
Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.
175.1K StarsTaste Skill: Anti-Slop Frontend
Design and implementation guidance for distinctive landing pages, portfolios, product demos, and purposeful redesigns.
85.2K StarsVox Director
Turn one topic into a narrated Vox-style paper-collage explainer or ad video, from script through captions.
1.8K StarsCanvas Design
Create original visual art, posters, PNG assets, and PDF documents through a clear design philosophy.
175.1K StarsPermission surface
no high-risk permission surface in public metadata
Agent outcomes
No agent outcome data yet
Docs
Usable metadata, review docs
Risk summary
Install readiness
Permission surface
no high-risk permission surface in public metadata
Agent outcomes
No agent outcome data yet
Docs
Usable metadata, review docs
Risk summary
Install readiness
Permission surface
no high-risk permission surface in public metadata
Agent outcomes
No agent outcome data yet
Docs
Usable metadata, review docs
Risk summary
Install readiness
Permission surface
no high-risk permission surface in public metadata
Agent outcomes
No agent outcome data yet
Docs
Usable metadata, review docs
Risk summary
Install readiness