short-video-copywriter

short-video-copywriter is a skill for Claude Code from wpsnote/wpsnote-skills. It costs 169 tokens per session (3,911 once invoked), scanned A, original, MIT.

A skill that turns an existing article, news item, or other long text into a short-video spoken script, with optional scene directions and AI-generated illustrations. It also loads and updates short-video preferences stored in WPS Notes.

In plain words
What is it for?
Use it to create short-video copy, voice-over scripts, and storyboards from pasted source material, including illustrations for scenes.
Why use it?
It helps when long written material needs to be reshaped into a spoken, scene-based video format instead of written as a new piece from scratch.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the content-skills plugin — 10 skills shipped together

Good fit Use it to create short-video copy, voice-over scripts, and storyboards from pasted source material, including illustrations for scenes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wpsnote/wpsnote-skills/short-video-copywriter
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.

Any agent
npx skills add wpsnote/wpsnote-skills --skill short-video-copywriter
Clone the repo
git clone --depth 1 https://github.com/wpsnote/wpsnote-skills

Made for: Claude Code.

Or install content-skills, the plugin that ships this one along with the rest of its 10 skills.

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 short-video-copywriter

README.md
[![agentmods](https://agentmods.dev/badge/skills/wpsnote/wpsnote-skills/short-video-copywriter/github.svg)](https://agentmods.dev/skills/wpsnote/wpsnote-skills/short-video-copywriter)
Your own site
<a href="https://agentmods.dev/skills/wpsnote/wpsnote-skills/short-video-copywriter"><img src="https://agentmods.dev/badge/skills/wpsnote/wpsnote-skills/short-video-copywriter/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for short-video-copywriter

Your own site · 80×15
<a href="https://agentmods.dev/skills/wpsnote/wpsnote-skills/short-video-copywriter"><img src="https://agentmods.dev/badge/skills/wpsnote/wpsnote-skills/short-video-copywriter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 169 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,911 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00169 $0.03911
Opus 5.5 $0.00068 $0.01564
Sonnet 5.5 $0.00034 $0.00782
Haiku 4.5 $0.00017 $0.00391

Measured 1mo ago against content hash 4e4335cb1cd6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

short-video-copywriter 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 1mo ago.

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.

skills/short-video-copywriter/SKILL.md · 323 lines

How it starts

The opening of the file, as written. The whole thing — 323 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Short Video Copywriter - 短视频文案生成工作流

将原稿改写为短视频口播文案,结合用户的个性化偏好,确保风格一致、平台适配。


铁律(最高优先级)

1. 必须通过工具写入笔记,绝对禁止在对话中输出文案内容

AI 不允许在对话消息里输出任何文案、分镜脚本或生图结果,无论任何情况,无一例外。

  • 禁止在对话中输出文案正文、分镜表格、BGM 建议的具体内容
  • 禁止以「以下是文案内容」「分镜如下」等任何形式在消息里直接输出结果
  • 唯一合法的输出方式:调用 create_note + batch_edit / edit_block 将内容写入 WPS 笔记
  • 写入成功后,对话中只允许出现:笔记标题、字数、一句话摘要、「已写入笔记」
  • 违反以上任一条,即为执行错误,必须立刻停止并重新通过工具写入

2. 提问必须附备选项

对话中只能做两件事:提问 + 状态通知。

  • 提问时必须附上 2-4 个备选选项,不让用户面对空白
  • 状态通知:调用工具前一句话告知正在做什么

核心流程

加载偏好 → 接收原稿 → 生成文案(+分镜脚本)→ [可选] 分镜生图 → 确认是否更新偏好

Step 1:加载偏好

执行:使用 search_notes 搜索关键词 短视频脚本偏好。

  • 找到偏好笔记 → 读取笔记内容,提取表格中的偏好参数,以如下格式告知用户:
    已加载短视频偏好:平台={平台} | 时长={时长} | 风格={风格} | CTA={类型}
    
  • 未找到偏好笔记 → 进入 首次配置流程

偏好笔记标题约定为:短视频脚本偏好


Step 2:接收原稿

如果用户还没有粘贴原稿,提示:

"请把原稿贴过来,我来帮你改写成短视频文案。"

原稿接收后,快速分析:

  • 原稿核心信息(1句话)
  • 原稿字数和信息密度
  • 建议视频时长(根据偏好中的默认时长或原稿量推算)

Step 3:生成文案与分镜脚本

根据偏好参数和原稿,调用 create_note 新建笔记(标题:{原稿标题/主题} - 短视频文案),再用 batch_edit 写入以下结构:

写入笔记的内容结构

<h1>{原稿标题} - 短视频文案</h1>
<p><tag>#短视频</tag></p>
<p>平台:{平台} | 时长:{预估时长} | 风格:{风格}</p>
<h2>开场钩子(0-3秒)</h2>
<p>{吸引注意力的开场白,提出悬念/冲突/利益点}</p>
<h2>主体内容</h2>
<p>{核心信息,分段口播,每段约15-20字}</p>
<h2>结尾 CTA</h2>
<p>{引导点赞/关注/评论/购买}</p>
<p>预估字数:{N}字 | 预估时长:{T}秒</p>
<h2>BGM 建议</h2>
<p>情绪:{情绪关键词}</p>
<p>搜索关键词:{词1} / {词2} / {词3}</p>

写入完成后,对话中只说:「文案已写入笔记《{笔记标题}》,共 {N} 字,预估 {T} 秒。需要我帮你拆分镜脚本并生成配图吗?」

不得在对话中展示任何文案内容。

生成原则

  1. 钩子优先:开场3秒必须抓住眼球,直接切入最有价值的信息
  2. 口语化:去掉书面语,用说话的方式重组句子
  3. 短句节奏:每句不超过20字,适合口播停顿
  4. 信息提炼:原稿可能有大量背景/铺垫,只保留核心信息
  5. 平台适配:根据平台特点调整语气(抖音更强势,视频号更温和)

BGM 关键词对照表

视频风格 情绪 推荐 BGM 关键词
干货直给 专注/高效 lo-fi hip hop / 轻电子 / 专注背景音乐
情绪带动 励志/热血 励志纯音乐 / epic orchestral / 燃向剪辑
轻松幽默 轻快/趣味 轻松欢快 / ukulele / 搞笑bgm
严肃专业 沉稳/权威 企业宣传音乐 / 商务背景音乐 / corporate

Step 3.5:分镜脚本与生图

Read the full file on GitHub · 323 lines

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. 1mo ago First seen · 323 lines · 169 tokens per session scan A 4e4335cb1cd6

Subscribe to this mod's changes

short-video-copywriter is a skill published in the GitHub repository wpsnote/wpsnote-skills (183 stars, last pushed yesterday), licensed MIT. It adds 169 tokens to every session and 3,911 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-08-30.

Related

Other skills, from other repositories

gap-to-topic

Turn a research area into a go/no-go decision dossier for candidate thesis/proposal topics (zero or multiple justified options) — a 3-gate verdict (is the gap open? is it a contribution? is it feasible?) with the evidence laid out so the researcher can verify it. Use when the user asks "is this gap worth pursuing"…

WenyuChiou/research-hub · 188 tokens

manage-taskboard

Manage work in the native DeepSeek Harness Taskboard with exact task ids and optimistic versions. Use when an Agent must inspect project work, claim an eligible todo, record progress or blockers, verify an implementation, submit it for human review, or release its own claim; also use when a human asks how to accept…

shengsheng90/DSH-taskboard · 88 tokens

research-workflow-orchestrator

Run a resumable end-to-end research workflow that automates low-risk work, pauses at explicit human decision gates, records provenance, and routes each stage to the appropriate research-hub skill or MCP tool.

WenyuChiou/research-hub · 48 tokens

literature-triage-matrix

Turn a list of papers (Zotero collection, Obsidian cluster, manual list) into a compact comparison matrix written to .research/literaturematrix.md, instead of generic per-paper summaries. Use when the user asks to "make a literature matrix", "compare these papers by method/data/limitations", or "decide which papers…

WenyuChiou/research-hub · 162 tokens

company-research-method

A documented process for researching a company using supplied files and selected public sources. It produces a company overview with business details, sourced financial figures, and stated risks.

PerryLink/dsh-industry-research · 83 tokens

ccgui-plugin-creator

A plugin-building workflow for CC GUI, a desktop client that can be extended with plugins written as configuration or JavaScript modules.

zhukunpenglinyutong/desktop-cc-gui · 132 tokens