Remote OpenClaw
Menu
SkillsMCPPluginsGuideDigestSubmit MCPSkillPluginMCPMCP, plugin, or skillAdvertise
Remote OpenClaw
SkillsMCPPluginsGuideDigestSubmit MCPSkillPluginMCPMCP, plugin, or skillAdvertise

Featured

Launch your own OpenClaw agent in one click logoLaunch your own OpenClaw agent in one click

A live, always-on OpenClaw agent that handles your tasks around the clock. No servers, no setup — pick a model, connect Telegram, and it starts working.

Try it for free →
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it — secured from day one.

Get it set up for you →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free →
CLN.Work — Stop prompting, start hiring AI employees logoCLN.Work — Stop prompting, start hiring AI employees

Turn your Claude agents into a real team — onboard them, assign tasks, and manage them like staff.

Hire AI employees →
Launch OpenClaw or Hermes on Hostinger in 60 seconds logoLaunch OpenClaw or Hermes on Hostinger in 60 seconds

Your OpenClaw or Hermes agent, live around the clock on a Hostinger VPS. Set up in about 60 seconds, from a few dollars a month, with 20% off through this link.

Launch on Hostinger →
Launch your OpenClaw wrapper and start making money today logoLaunch your OpenClaw wrapper and start making money today

Auth, billing, and AI already wired in. Skip months of boilerplate and get paying customers now, not next quarter.

See the kit →
Launch your own OpenClaw agent in one click logoLaunch your own OpenClaw agent in one click

A live, always-on OpenClaw agent that handles your tasks around the clock. No servers, no setup — pick a model, connect Telegram, and it starts working.

Try it for free →
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it — secured from day one.

Get it set up for you →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free →
CLN.Work — Stop prompting, start hiring AI employees logoCLN.Work — Stop prompting, start hiring AI employees

Turn your Claude agents into a real team — onboard them, assign tasks, and manage them like staff.

Hire AI employees →
Launch OpenClaw or Hermes on Hostinger in 60 seconds logoLaunch OpenClaw or Hermes on Hostinger in 60 seconds

Your OpenClaw or Hermes agent, live around the clock on a Hostinger VPS. Set up in about 60 seconds, from a few dollars a month, with 20% off through this link.

Launch on Hostinger →
Launch your OpenClaw wrapper and start making money today logoLaunch your OpenClaw wrapper and start making money today

Auth, billing, and AI already wired in. Skip months of boilerplate and get paying customers now, not next quarter.

See the kit →
Launch your own OpenClaw agent in one click logoLaunch your own OpenClaw agent in one click

A live, always-on OpenClaw agent that handles your tasks around the clock. No servers, no setup — pick a model, connect Telegram, and it starts working.

Try it for free →
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it — secured from day one.

Get it set up for you →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free →
CLN.Work — Stop prompting, start hiring AI employees logoCLN.Work — Stop prompting, start hiring AI employees

Turn your Claude agents into a real team — onboard them, assign tasks, and manage them like staff.

Hire AI employees →
Launch OpenClaw or Hermes on Hostinger in 60 seconds logoLaunch OpenClaw or Hermes on Hostinger in 60 seconds

Your OpenClaw or Hermes agent, live around the clock on a Hostinger VPS. Set up in about 60 seconds, from a few dollars a month, with 20% off through this link.

Launch on Hostinger →
Launch your OpenClaw wrapper and start making money today logoLaunch your OpenClaw wrapper and start making money today

Auth, billing, and AI already wired in. Skip months of boilerplate and get paying customers now, not next quarter.

See the kit →
Skills/dontbesilent2025/dbskill/dbs-script-flow
dbs-script-flow logo

dbs-script-flow

dontbesilent2025/dbskill
683 installs8K stars

Installation

npx skills add https://github.com/dontbesilent2025/dbskill --skill dbs-script-flow

Summary

|

SKILL.md

dbs-script-flow — 逻辑延续检查

版本:v1.1 适用场景:检查短视频逐字稿的段落衔接、信息密度和口播流畅度,找出"观众会在哪一秒划走"的风险点

---

触发条件

当用户:

  • 说「检查逻辑延续」「看看逻辑有没有断」「有没有啰嗦的地方」
  • 说「帮我看看这个稿子顺不顺」「这个稿子能不能一直看下去」
  • 说「检查完播率风险」「哪里会划走」
  • 使用 /dbs-script-flow 或 /逻辑延续

---

与其他 Skill 的区别

Skill检查什么类比
/检查文稿宏观结构:有没有开场、高潮、结论检查房子有没有缺楼层
/dbs-script-flow微观衔接:每段到下段是否丝滑检查每层楼梯有没有断掉
/文稿分析整体优化报告 + 标题方案给房子做全面体检

---

核心原则

完播率的敌人不是内容差,而是某一个瞬间观众跟不上了。

观众划走只有三个原因:

  1. 逻辑断裂:前一段讲 A,下一段突然跳到 C,中间缺 B
  2. 信息密度掉了:某一段在重复已经说过的东西,或者绕圈子
  3. 口播卡壳:句子太长、太书面、自问自答,念不出来

---

检查流程

第一步:分段

把逐字稿按自然段落(话题切换点)分成若干段,每段标注:

  • 段号
  • 段落主题(一句话概括这段在讲什么)
  • 段落功能(开场 / 背景铺垫 / 论证 / 案例 / 转场 / 高潮 / 结尾)

第二步:逐段扫描三个维度

对每一段,依次检查:

维度 1:逻辑衔接(前后段之间)

问自己:

  • 上一段的最后一句,和这一段的第一句之间,有没有逻辑跳跃?
  • 观众听完上一段,能不能自然地理解为什么要讲这一段?
  • 如果不能,缺的那个承上启下的信息是什么?

常见问题:

  • 从个案突然跳到宏观分析,中间缺一句过渡
  • 从解释原因突然跳到另一个话题,前一个话题没收束
  • 从数据跳到观点,中间缺一句「所以」

修复方法:

  • 加一句过渡句(通常一句话就够)
  • 在前一段末尾加一句收束
  • 调整段落顺序
维度 2:信息密度(段落内部)

问自己:

  • 这一段有没有在重复前面已经说过的信息?
  • 这一段有没有绕圈子(用了 5 句话说了一个 1 句话就能说清的事)?
  • 如果把这一段删掉,观众会不会 miss 掉关键信息?

常见问题:

  • 同一个意思换了三种说法反复讲
  • 解释一个概念时举了太多例子,观众已经懂了还在举
  • 某一段是「正确的废话」——说了等于没说

修复方法:

  • 删减重复的表述,只保留最有力的一种
  • 合并冗余段落
  • 标注「可删」让用户决定
维度 3:口播流畅度(句子级别)

问自己:

  • 这句话能一口气念出来吗?(超过 30 字的单句要警惕)
  • 有没有书面语?(「针对」「鉴于」「基于以上分析」)
  • 有没有自问自答?(「你以为 X 吗?其实 Y」——偶尔可以,连续用会烦)
  • 有没有生造的概念?(观众听不懂的术语,且没有即时解释)

常见问题:

  • 定语套定语,一句话里塞太多信息
  • 用了一个术语但没有马上解释
  • 连续几个短句节奏太碎,或连续几个长句节奏太闷

修复方法:

  • 长句拆成两句
  • 术语后面紧跟一句大白话解释
  • 调整长短句交替的节奏

第三步:标注风险等级

对每个发现的问题标注风险等级:

等级含义说明
🔴 高风险观众大概率在这里划走逻辑断裂、信息密度严重下降
🟡 中风险观众可能走神但不一定划走衔接不够顺、稍有啰嗦
🟢 小建议改了更好,不改也行口播微调、用词优化

---

输出格式

## 逻辑延续检查报告

### 段落结构

| 段号 | 主题 | 功能 | 状态 |
|-----|------|------|------|
| 1 | [主题] | 开场 | ✅ |
| 2 | [主题] | 背景铺垫 | ✅ |
| 3 | [主题] | 论证 | 🟡 |
| ... | ... | ... | ... |

### 问题清单

**🔴 问题 1:第 X 段 → 第 Y 段,逻辑断裂**

> 原文(第 X 段末尾):「……」
> 原文(第 Y 段开头):「……」

**问题**:[具体描述为什么这里会让观众跟不上]

**修复建议**:在第 X 段末尾加一句过渡:
> 「[具体的过渡句]」

---

**🟡 问题 2:第 Z 段,信息密度下降**

> 原文:「……」

**问题**:[具体描述为什么这里观众会走神]

**修复建议**:
> 改为:「[精简后的文本]」

---

**🟢 问题 3:第 W 段第 N 句,口播不顺**

> 原文:「……」

**问题**:[具体描述为什么这句话念不出来]

**修复建议**:
> 改为:「[改写后的句子]」

---

### 整体评估

- **逻辑衔接**:[一句话总结]
- **信息密度**:[一句话总结]
- **口播流畅度**:[一句话总结]
- **总结**:[整体判断,需要改几处,改完可以发]

### 询问是否改稿

输出整体评估之后,必须主动问用户:

> 要直接帮你标记式改稿吗?改的时候保留你的原文,用删除线和 🆕 emoji 标出改动。

**不要等用户主动要求**——大部分时候用户做检查的目的就是改稿,主动问省一次往返。
但**也不要不问就改**——保留主动权给用户,他可能想自己改。

---

标记式改稿流程(用户确认后执行)

当用户回复「改」「帮我改」「直接改吧」「改原文」时,启动标记式改稿。

核心原则

永不抹除用户原文。改稿是在原文上叠加标记,不是用新版本替换旧版本。用户必须能一眼看出:

  1. 哪些是他自己写的
  2. 哪些是 AI 删除/替换建议
  3. 哪些是 AI 新增的内容
  4. 哪些是 AI 之前改过又被还原的(避免在多轮反馈里弄丢历史)

三种标记符(视觉对比强)

符号用途示例
~~删除线~~标记建议删除或被替换的原文~~重点是在于,这里划重点啊~~
🆕标记新增/改写的内容🆕 这里有个关键点
⚠️标记 AI 自己撤回判断、还原原文⚠️ 上面的删除判断错了,已还原。这三段不是跑题,是在拆解……

改稿规则

  1. 改的过程直接在原文位置操作——不要写一个完整的新版本贴在底部,要原地标记
  2. 每个改动都成对出现——~~原文~~ 紧跟着 🆕 新版本,让对照关系一目了然
  3. 整段删除时:保留原段落用删除线,下面用 🆕 解释为什么删(或给压缩版替代)
  4. 改完末尾给一个改动清单——表格形式,列出每处改动的位置、类型、原因,让用户快速 review
  5. 多轮反馈要追加不要覆盖——如果用户指出某处改错了,用 ⚠️ 标注还原,不要直接改回去当作没发生过

改完输出格式

[原文 + 标记式改动,原地操作]

---

### 改动清单

| 位置 | 类型 | 说明 |
|---|---|---|
| 开头 | 🟢 替换 | [简短说明] |
| 第 X 段 | 🔴 整块删除 | [原因] |
| 结尾 | 🟡 新增 | [新增了什么、为什么] |

末尾给一句话决断(哪几处一定要改、哪几处改不改都行),让用户知道优先级。

---

注意事项

  1. 不要改内容观点:这个 skill 只管"怎么说",不管"说什么"。不要改用户的论点、案例、数据
  2. 修复建议要口语化:给出的过渡句和改写必须能直接念出来,不能是书面语
  3. 不要过度诊断:如果稿子整体很顺,就说"没什么问题",不要强行找茬
  4. 优先标高风险:宁可漏掉一个小建议,也不要把高风险问题淹没在一堆小问题里
  5. 保持用户的语气:改写时要保持用户自己的说话风格,不要把用户的话改成"AI味"
  6. 给出具体位置:每个问题都要引用原文,让用户一眼就能找到
  7. 改稿前先确认拍摄方式:是否白板视频会改变判断标准——白板视频里并列清单是视觉优势、「划重点啊」「看这里」是和板上动作配套的提示词,不该改。如果用户没说,问一句「这是白板视频还是纯口播」
  8. 判断"跑题"前先问一句:如果删掉这段,观众在前一个关键节点能不能靠自己脑补出具体含义?如果脑补不出来,那这段就是必要的论证肉,不是赘肉。不要只看"话题字面上偏不偏",要看"这段话在服务哪个论点"

---

实战案例

案例:「小红书被告了」逐字稿(2026-04-09)

🟡 问题 1:第 5 段第 46 行,口播绕

原文:「你就会进入另外一个类似叫商家流量池的一个区间」

问题:「另外一个类似叫……的一个区间」连续两个「一个」,念起来会卡。而且「商家流量池」是术语,观众不一定懂。

修复建议:

改为:「你就没什么流量了,也不是完全没有,但是会很差」 直接说结果,不引入概念。

---

🟡 问题 2:第 7 段 → 第 8 段,缺过渡

原文(第 7 段末尾):「所以接下来就是你违规引流,平台给你封号。」 原文(第 8 段开头):「然后接下来更有意思的事情就发生了」

问题:从"律师被封号"直接跳到"庭审发言",中间缺一个收束。观众还在消化"律师被封号"的信息,突然被拉到了庭审现场。

修复建议:把第 7 段末尾改为:

「所以这个律师接下来被限流的遭遇,其实就是这套流程的标准结局。」 「标准结局」收住前面的分析,再打开新信息。

---

版本历史

  • v1.0 (2026-04-09):初始版本,基于「小红书被告了」逐字稿的实战经验
  • v1.1 (2026-05-04):追加标记式改稿流程;诊断完默认主动问「要不要标记式改稿」;注意事项加 2 条(白板视频判断标准、跑题判断前先看论点服务)

Score

0–100
57/ 100

Grade

C

Popularity17/30

683 installs — growing adoption. Source repo has 7,504 GitHub stars.

Completeness19/30

Documented: full SKILL.md body, one-line install. Missing: description, category/license metadata.

Trust15/25

Community skill with a public GitHub source repository you can review.

Freshness6/15

No update timestamp is tracked for this skill in our catalog.

Scored automatically from popularity, completeness, trust, and freshness — computed only from data in our catalog, never fabricated.

Proud of your score? Add this badge to your README.

Paste a snippet into your GitHub README. The badge updates automatically and links back to this page.

Dbs Script Flow skill score badge previewScore badge

Markdown

[![Dbs Script Flow skill](https://www.remoteopenclaw.com/skills/dontbesilent2025/dbskill/dbs-script-flow/badges/score.svg)](https://www.remoteopenclaw.com/skills/dontbesilent2025/dbskill/dbs-script-flow)

HTML

<a href="https://www.remoteopenclaw.com/skills/dontbesilent2025/dbskill/dbs-script-flow"><img src="https://www.remoteopenclaw.com/skills/dontbesilent2025/dbskill/dbs-script-flow/badges/score.svg" alt="Dbs Script Flow skill"/></a>

Dbs Script Flow FAQ

How do I install the Dbs Script Flow skill?

Run “npx skills add https://github.com/dontbesilent2025/dbskill --skill dbs-script-flow” in your terminal. The skill is added to your agent's skills directory and picked up automatically on the next run — no restart or extra configuration needed.

What does the Dbs Script Flow skill do?

| The full SKILL.md on this page shows the exact instructions the skill gives your agent.

Is the Dbs Script Flow skill free?

Yes. Dbs Script Flow is a free, open-source skill published from dontbesilent2025/dbskill. As with any third-party skill, review the source repository before installing it into an agent with sensitive access.

Does Dbs Script Flow work with Claude Code and OpenClaw?

Yes. Skills use the portable SKILL.md format, so Dbs Script Flow works with Claude Code, OpenClaw, Codex, Hermes, and any other agent that reads SKILL.md skills.

Featured

Launch your own OpenClaw agent in one click logoLaunch your own OpenClaw agent in one click

A live, always-on OpenClaw agent that handles your tasks around the clock. No servers, no setup — pick a model, connect Telegram, and it starts working.

Try it for free →
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it — secured from day one.

Get it set up for you →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free →
CLN.Work — Stop prompting, start hiring AI employees logoCLN.Work — Stop prompting, start hiring AI employees

Turn your Claude agents into a real team — onboard them, assign tasks, and manage them like staff.

Hire AI employees →
Launch OpenClaw or Hermes on Hostinger in 60 seconds logoLaunch OpenClaw or Hermes on Hostinger in 60 seconds

Your OpenClaw or Hermes agent, live around the clock on a Hostinger VPS. Set up in about 60 seconds, from a few dollars a month, with 20% off through this link.

Launch on Hostinger →
Launch your OpenClaw wrapper and start making money today logoLaunch your OpenClaw wrapper and start making money today

Auth, billing, and AI already wired in. Skip months of boilerplate and get paying customers now, not next quarter.

See the kit →
Launch your own OpenClaw agent in one click logoLaunch your own OpenClaw agent in one click

A live, always-on OpenClaw agent that handles your tasks around the clock. No servers, no setup — pick a model, connect Telegram, and it starts working.

Try it for free →
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it — secured from day one.

Get it set up for you →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free →
CLN.Work — Stop prompting, start hiring AI employees logoCLN.Work — Stop prompting, start hiring AI employees

Turn your Claude agents into a real team — onboard them, assign tasks, and manage them like staff.

Hire AI employees →
Launch OpenClaw or Hermes on Hostinger in 60 seconds logoLaunch OpenClaw or Hermes on Hostinger in 60 seconds

Your OpenClaw or Hermes agent, live around the clock on a Hostinger VPS. Set up in about 60 seconds, from a few dollars a month, with 20% off through this link.

Launch on Hostinger →
Launch your OpenClaw wrapper and start making money today logoLaunch your OpenClaw wrapper and start making money today

Auth, billing, and AI already wired in. Skip months of boilerplate and get paying customers now, not next quarter.

See the kit →
Launch your own OpenClaw agent in one click logoLaunch your own OpenClaw agent in one click

A live, always-on OpenClaw agent that handles your tasks around the clock. No servers, no setup — pick a model, connect Telegram, and it starts working.

Try it for free →
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it — secured from day one.

Get it set up for you →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free →
CLN.Work — Stop prompting, start hiring AI employees logoCLN.Work — Stop prompting, start hiring AI employees

Turn your Claude agents into a real team — onboard them, assign tasks, and manage them like staff.

Hire AI employees →
Launch OpenClaw or Hermes on Hostinger in 60 seconds logoLaunch OpenClaw or Hermes on Hostinger in 60 seconds

Your OpenClaw or Hermes agent, live around the clock on a Hostinger VPS. Set up in about 60 seconds, from a few dollars a month, with 20% off through this link.

Launch on Hostinger →
Launch your OpenClaw wrapper and start making money today logoLaunch your OpenClaw wrapper and start making money today

Auth, billing, and AI already wired in. Skip months of boilerplate and get paying customers now, not next quarter.

See the kit →
View on GitHub

Recommended skills

Browse all →
LW

lark-workflow-meeting-summary

open.feishu.cn

379K installsInstall
LW

lark-workflow-standup-report

open.feishu.cn

379K installsInstall
lark-workflow-meeting-summary logo

lark-workflow-meeting-summary

larksuite/cli

331K installsInstall
lark-workflow-standup-report logo

lark-workflow-standup-report

larksuite/cli

331K installsInstall
find-skills logo

find-skills

vercel-labs/skills

2.4M installsInstall
frontend-design logo

frontend-design

anthropics/skills

645K installsInstall

Browse

Skills by category

Frontend250Git198Data154Testing120Design105Docs103Security96Automation87Backend76Devops37Productivity29Mcp23

Related guides

Hand-picked reading to help you choose, install, and use agent skills.

GuideBest Openclaw Skills 2026GuideHow To Evaluate Openclaw Skill Before InstallingGuideOpenclaw Skills Complete Guide

Remote OpenClaw

AI agent skills directory, marketplace, and workflow hub for OpenClaw, Hermes Agent, Claude Code, Codex, and MCP-powered operator stacks.

The Agent Stack: weekly agent tooling digest, free.

Explore

  • Home
  • Skills Directory
  • Claude Code Skills
  • Codex Skills
  • MCP Clients
  • Marketplace
  • Hermes Ecosystem
  • Guide
  • Learn
  • Blog
  • The Agent Stack (Digest)

More

  • Submit a Tool
  • Advertise
  • Playbook
  • Free Tools
  • API
  • Shipping
  • Contact
  • Terms
  • Privacy
© 2026 Remote OpenClaw
Fazier badgeFeatured on Twelve ToolsFeatured on Wired BusinessRemote OpenClaw - Featured on AI Agents DirectoryListed on Turbo0