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.
npx skills add zenstory-ai/oh-story-dsh --skill short-drama-editgit clone --depth 1 https://github.com/zenstory-ai/oh-story-dshWrote 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.
[](https://agentmods.dev/skills/zenstory-ai/oh-story-dsh/short-drama-edit)<a href="https://agentmods.dev/skills/zenstory-ai/oh-story-dsh/short-drama-edit"><img src="https://agentmods.dev/badge/skills/zenstory-ai/oh-story-dsh/short-drama-edit/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.
<a href="https://agentmods.dev/skills/zenstory-ai/oh-story-dsh/short-drama-edit"><img src="https://agentmods.dev/badge/skills/zenstory-ai/oh-story-dsh/short-drama-edit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00069 | $0.04587 |
| Opus 5.5 | $0.00028 | $0.01835 |
| Sonnet 5.5 | $0.00014 | $0.00917 |
| Haiku 4.5 | $0.00007 | $0.00459 |
Grade A, and why
short-drama-edit 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 today.
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.
This is a copy
100% identical to short-drama-edit — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
短剧剪辑与成片
把 剧集/<EP>/制作成果/ 里的逐镜素材装配成一条成片,取舍写进 剧集/<EP>/剪辑单.md。
每段使用二级标题 ## CUT-...,各自绑定一个来源 ID 和一个真实媒体文件:视频段是 MOTION-...,
静态漫剧的关键帧段是 SHOT-... 或 IMG-...。
根据实际素材选择可用片段,按剧本与分镜核对叙事。素材与意图不一致时,记录取舍和缺口。
Quick Start
用 $short-drama-edit 把 EP001 已生产的镜头剪成成片
入口
进入条件是素材已经存在且可读:剧集/<EP>/制作成果/ 里有本次要用的视频文件;
静态漫剧是已接受的关键帧和配音文件。
先确认本次素材文件可打开,不能仅凭提示词、生产确认或 adapter 成功回执开始剪辑。
素材不全时可以先剪已有连续段落;用户要求完整成片时,将这一版标为片段并列出缺口。 在「未采用镜头」说明缺文件、质量不可用或叙事取舍。
剧集/<EP>/分镜.md 与 视频提示词.md 是镜序和职责的来源。剪辑可以取舍它们,不能改写
它们:删一镜、缩一镜、换顺序都属于本阶段;改台词、改镜头职责、改起终状态要回上游发修订请求。
内置渲染直接拼接编码后的分段,输入素材的画幅与帧率须一致。check 在可探测媒体时核对;
不同规格先通过外部工具按交付要求统一,保留构图并记录裁切或留边,再更新剪辑单的路径与时间。
渲染与测量需要 ffmpeg / ffprobe 在 PATH 上。没有时 edit_tool.py 直接失败并说明,
不用别的手段近似,也不把「没测」写成「通过」。
工作流
- 逐段看完整素材,先标可用带,再谈剪辑。 每个文件从头到尾看一遍,写下它实际能用的时间 区间,以及区间之外发生了什么(起势静止、结尾漂移、发白、动作回弹、多余的重复表演)。 这一步的产出是事实,不是决定。做法见 生成素材的可用带。
- 有台词的镜先定位发声区间。 保留完整字音和所需停顿。视频自带声音随画面同步裁切;
独立配音文件可用
配音行跨切点播放,分离或替换原视频音轨则先用外部工具处理。 - 在可用区间内选叙事入出点。 按动作、反应或停顿的需要选择入点,出点取信息完成之后、缺陷 开始之前。逐段写清入点理由和出点理由。做法见 入出点与镜序。
- 排镜序并检查相邻关系。 检查动作、空间、揭示与声音是否连贯;重复信息没有新增作用时再删。
- 比较相邻段的画面。 render 会在同一场景内自动接镜;按同场景、同光态比较可比区域,
自动接镜不够或不该动的段写
画面。做法见 接镜与色彩一致性。 - 处理声音接缝与响度。 拼接后回听;需要混音时通过外部工具执行并记录。 做法见 声音、字幕与音乐。
- 写字幕、画面文字与音效。 字幕的每一个字都取自
剧本.md的台词原文,不取自转写结果; 标点照抄剧本,字不能改。转写只用来定位时间。画面留白给后期的[画面文字]写成画面文字行, 需要落在画面文字出现时的提示音写成音效行。 - 写出
剪辑单.md,再渲染。 取舍、时间与后期处理先落进文档,成片按这份记录生成。 - 按可测项验收成片,再交付。 见 交付与验收。
剪辑单要求
-
正文开头写交付规格:
成片目标时长、画幅与帧率、交付响度、字幕。目标时长是意图, 实际时长与目标的差写在报告里。用户明确要求固定时长时,应满足要求或报告缺少的素材。 -
每段一个
## CUT-<EP>-<序号> · <中文名称>,块内逐行写:- 来源:<MOTION-...> · <项目相对路径>——MOTION-...必须是视频提示词.md里真实存在 的条目,路径必须是当前可读的文件。静帧段写- 来源:<SHOT-...> · <图片路径>(分镜.md的镜头) 或<IMG-...> · <图片路径>(图片提示词.md的条目),图片为 png / jpg / jpeg / webp; 入点写0.00,出点等于时长,至少0.50秒。静帧按交付规格的画幅与帧率铺满出画, 有静帧时交付规格必须写画幅与帧率。- 入点:<秒>/- 出点:<秒>/- 时长:<秒>——三者必须自洽,出点 - 入点 == 时长。 全部用秒,保留两位小数,不写时间码,不写帧号。- 取舍:入点=<理由>;出点=<理由>——说明画面上的具体变化及其叙事作用,不只写「节奏需要」。- 声音:<本段声音怎么处理>——记录保留原声或外部处理。此行不驱动内置 render 的混音。- 画面:<接镜校正>、- 画面:无或- 画面:不校——校正是「亮度 <数>」「饱和 <数>」「色温 <数>」 三项的任意组合,用;分隔,写了就替代这一段的自动接镜;无表示不另写校正;不校表示连自动接镜 也不做。详见 接镜与色彩一致性。- 字幕:<逐字台词原文>或- 字幕:无。本段有多句台词时改用编号写法, 每句自带时间:- 字幕 1:0.20-1.50 请进、- 字幕 2:2.30-4.30 门没有锁。 编号从 1 连续,时间相对本 CUT 入点,且不得重叠;止可以超过本段时长(跨切点见 静帧段)。句末可加(重点:<词>|<词>), 这些词须出现在本句里,烧录时标黄。字色按剧本.md里这句的来源决定:对白白色,[VO] 系统:青色,其他[VO]浅青,剪辑单里不另写。- 画面文字 N:<起>-<止> <样式> <项>|<项>…——视频模型写不对字,系统面板、倒计时、屏幕上的 粉丝数在画面里留白,由 render 叠上去。每一项都要能在剧本.md的[画面文字]行里找到。 单条可不编号;编号与时间规则同字幕。三种面板共用画面顶部,角标在右上角,同一位置不得重叠。
What ships with it
28 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 254 B
- assets/remotion/package.json 464 B
- assets/remotion/README.md 5.2 KB
- assets/remotion/remotion.config.ts 219 B runs code
- assets/remotion/src/font.ts 2.2 KB runs code
- assets/remotion/src/index.ts 109 B runs code
- assets/remotion/src/Overlay.tsx 1.0 KB
- assets/remotion/src/Root.tsx 931 B
- assets/remotion/src/rules.mjs 7.6 KB runs code
- assets/remotion/src/schema.ts 1.2 KB runs code
- assets/remotion/src/screen/Card.tsx 2.8 KB
- assets/remotion/src/screen/chrome.tsx 5.7 KB
- assets/remotion/src/screen/CornerChip.tsx 1.6 KB
- assets/remotion/src/screen/ScreenText.tsx 1.2 KB
- assets/remotion/src/screen/SystemPanel.tsx 1.8 KB
- assets/remotion/src/screen/TaskPanel.tsx 4.0 KB
- assets/remotion/src/screen/tokens.ts 2.4 KB runs code
- assets/remotion/src/Subtitles.tsx 3.1 KB
- assets/remotion/tsconfig.json 276 B
- assets/剪辑单.md 2.1 KB
- references/cut-craft.md 2.6 KB
- references/delivery-verify.md 2.2 KB
- references/generated-footage.md 3.5 KB
- references/sound-and-subtitles.md 4.2 KB
- references/stage-contract.md 6.0 KB
- references/still-cuts.md 5.8 KB
- scripts/edit_tool.py 129 KB runs code
- scripts/selftest.py 26 KB runs code
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.
- today Changed 38946a741e12
- 12d ago Changed · -3 lines dc3a81a98da0
- 24d ago Changed · +20 lines 3a8c8e52f6d6
- 29d ago Changed · +23 lines c6f62bb505d5
- 1mo ago Changed · -2 lines · -73 tokens per session 2e53700bceae
- 1mo ago First seen · 149 lines · 142 tokens per session scan A ff27a30ed5fd
short-drama-edit is a skill published in the GitHub repository zenstory-ai/oh-story-dsh (629 stars, last pushed today), licensed MIT. It adds 69 tokens to every session and 4,587 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to short-drama-edit, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
story-deslop
A writing editor for Chinese web novels that detects writing patterns often associated with AI-generated text and makes the prose feel more natural.
story-long-analyze
A long-form fiction analysis workflow for breaking down a novel’s opening chapters, characters, pacing, turning points, relationships, and overall structure.
browser-cdp
Use this skill when you need to control a Chrome browser via CDP (Chrome DevTools Protocol) to reuse existing login sessions. Covers: launching Chrome in debug mode, opening URLs, waiting for page load, evaluating JavaScript, taking snapshots, and extracting auth tokens. Trigger phrases: browser automation, CDP…
workflow-manager
A writing workflow tracker for chapter-based projects. It records whether each chapter is being assembled, drafted, reviewed, confirmed, polished, or archived.
review-chapter
A six-part review of a manuscript chapter. It compares the chapter with the outline and reports quality, coverage, review status, and problems supported by evidence from the text.
revise-span
A revision workflow for changing selected passages in a manuscript. It shows the original and proposed text, then applies changes only after the author confirms them.