video-script-collaborial

video-script-collaborial is a skill for Claude Code, Codex from nicepkg/ai-workflow. It costs 83 tokens per session (1,942 once invoked), scanned A, original, MIT.

A workflow for turning formal video scripts into natural spoken language. It replaces written-sounding phrases with expressions that are easier to say and hear.

In plain words
What is it for?
Reworking scripts before recording, especially when the wording feels stiff, overly formal, or unnatural.
Why use it?
It helps recordings sound like real speech rather than text being read aloud.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/nicepkg/ai-workflow/video-script-collaborial
Any agent
npx skills add nicepkg/ai-workflow --skill video-script-collaborial
Clone the repo
git clone --depth 1 https://github.com/nicepkg/ai-workflow

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for video-script-collaborial

README.md
[![agentmods](https://agentmods.dev/badge/skills/nicepkg/ai-workflow/video-script-collaborial.svg)](https://agentmods.dev/skills/nicepkg/ai-workflow/video-script-collaborial)
Your own site
<a href="https://agentmods.dev/skills/nicepkg/ai-workflow/video-script-collaborial"><img src="https://agentmods.dev/badge/skills/nicepkg/ai-workflow/video-script-collaborial.svg" alt="Measured on agentmods" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,942 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00083 $0.01942
Opus 5 $0.00042 $0.00971
Sonnet 5 $0.00017 $0.00388
Haiku 4.5 $0.00008 $0.00194

Measured yesterday against content hash cfb664c1f591, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

video-script-collaborial scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

workflows/video-creator-workflow/.claude/skills/video-script-collaborial/SKILL.md · 210 lines

What it actually says

视频脚本口语化审校

何时使用此Skill

当用户出现以下任一需求时,使用此技能:

  • 审校"视频脚本"、"录制脚本"
  • 要求"口语化"、"自然一点"、"像说话一样"
  • 觉得脚本"太书面了"、"太正式"、"不自然"
  • 希望脚本"更适合录制"、"说出来更顺"
  • 需要增加"亲和力"、"生活化"的表达

核心目标

将正式的书面脚本转换为自然流畅的口语化表达,让视频听起来更像是真实对话而不是照本宣科,显著提升视频的亲和力和观看体验。

执行流程

第一遍:书面化词汇替换 (P0级转换)

目标:去除明显的书面化表达

重点替换

  1. 动词替换

    • ❌ "进行" → ✅ "做"、"搞"、"弄"
    • ❌ "实现" → ✅ "做到"、"完成"
    • ❌ "提供" → ✅ "给"、"提供给大家"
    • ❌ "导致" → ✅ "造成"、"所以"
    • ❌ "面临" → ✅ "遇到"、"碰到"
  2. 连接词替换

    • ❌ "因此" → ✅ "所以"、"这样"
    • ❌ "然而" → ✅ "但是"、"不过"
    • ❌ "此外" → ✅ "而且"、"另外"
    • ❌ "综上所述" → ✅ "总的来说"、"所以说"
  3. 名词替换

    • ❌ "该产品" → ✅ "这个产品"、"它"
    • ❌ "此方法" → ✅ "这个方法"、"这种方法"
    • ❌ "用户" → ✅ "大家"、"你们"、"我们"

第二遍:句式结构调整 (P1级转换)

目标:让句式更符合口语表达习惯

句式优化

  1. 长短句结合

    • 避免过长的复合句
    • 使用更多短句表达
    • 保持自然的说话节奏
  2. 倒装和省略

    • 使用"是...的"强调结构
    • 适当省略主语或宾语
    • 使用插入语增加自然感
  3. 语气词添加

    • 适当使用"啊"、"呀"、"呢"、"吧"
    • 增加感叹词"哇"、"哎呀"、"嗯"
    • 使用"对了"、"其实"、"说真的"等

第三遍:对话感增强 (P2级优化)

目标:增加互动感和真实对话感

互动元素

  1. 设问句使用

    • "大家猜猜看结果怎么样?"
    • "你们有没有遇到过这种情况?"
    • "是不是很简单?"
  2. 反问句表达

    • "这很困难吗?其实一点也不难。"
    • "你学会了吗?我相信你已经会了。"
  3. 直接称呼

    • "朋友们"、"大家好"、"各位小伙伴"
    • "我想告诉大家..."
    • "你们一定要记住..."

第四遍:情感色彩添加 (细节优化)

目标:增加情感表达和个性化色彩

情感元素

  1. 情绪词汇

    • "真的很棒"、"超级有用"
    • "太神奇了"、"简直不敢相信"
    • "有点小失望"、"挺意外的"
  2. 个人表达

    • "我觉得"、"在我看来"、"说实话"
    • "我个人的经验是..."
    • "让我印象最深的是..."
  3. 比喻和拟人

    • 使用生活化的比喻
    • 增加拟人化的表达
    • 让抽象概念更具体

具体转换示例

示例1:产品介绍类

原文(书面化)

本产品采用了先进的人工智能技术,能够为用户提供高效的解决方案。
该产品具备以下特点:操作简便、功能强大、性能稳定。
用户可以通过简单的操作实现复杂的功能需求。

转换后(口语化)

今天给大家介绍的这个产品,真的让我很惊喜!
它用的是最先进的人工智能技术,但是用起来超级简单。
你们猜怎么着?很多复杂的功能,点几下就搞定了!
操作简单、功能强大、用起来还很稳定,简直就是神器啊!

示例2:教程类

原文(书面化)

首先,我们需要进行准备工作。其次,按照步骤执行操作。
最后,对结果进行验证。此方法适用于大多数场景。

转换后(口语化)

好,那我们现在就开始!
第一步,我们先做一些准备工作,这个很重要哦。
然后呢,跟着我一步一步来操作,很简单的。
最后,我们看看结果怎么样。这个方法基本上什么情况都能用!```

### 示例3:观点分享类
**原文(书面化)**:

根据我的观察,这种现象具有普遍性。 我认为,解决这个问题需要多方面的努力。 因此,我们应该采取更加积极的应对策略。


**转换后(口语化)**:

说真的,我最近发现这个问题真的很普遍。 我觉得要解决这个问题,光靠一个人可不行。 所以啊,我们得换个思路,用更积极的方法来应对。


## 分场景优化建议

### 1. 知识科普类视频
**口语化重点**:
- 多用设问和互动
- 增加生活化比喻
- 保持专业性的同时增加亲和力

### 2. 生活分享类视频
**口语化重点**:
- 强调个人感受和体验
- 使用更多语气词和感叹
- 增加与观众的直接对话

### 3. 教程演示类视频
**口语化重点**:
- 强调步骤的清晰性
- 增加鼓励和引导性语言
- 保持节奏的轻快感

### 4. 产品评测类视频
**口语化重点**:
- 突出真实使用感受
- 增加对比和评价
- 保持客观性的同时表达观点

## 质量检查标准

### 流畅度检查
- [ ] 读起来不拗口
- [ ] 说话节奏自然
- [ ] 没有长难句
- [ ] 句式多样化

### 自然度检查
- [ ] 像真实对话
- [ ] 没有书面化痕迹
- [ ] 语气词使用恰当
- [ ] 情感表达真实

### 亲和力检查
- [ ] 有互动感
- [ ] 有个人特色
- [ ] 观众容易产生共鸣
- [ ] 表达有温度

## 特殊注意事项

### 1. 保持原意不变
- 确保核心信息不丢失
- 关键数据和事实要准确
- 逻辑关系要保持清晰

### 2. 避免过度口语化
- 不要使用过于随意的表达
- 保持基本的语言规范
- 避免使用不合适的网络用语

### 3. 考虑录制场景
- 考虑视频的整体风格
- 适配目标观众的接受度
- 保持个人风格的一致性

---
*最后更新:2024年*
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 210 lines · 83 tokens per session scan A cfb664c1f591

Subscribe to this mod's changes

video-script-collaborial is a skill published in the GitHub repository nicepkg/ai-workflow (282 stars, last pushed 7mo ago), licensed MIT. It adds 83 tokens to every session and 1,942 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.