zenstory-ai/drama-skills is a collection of AI coding-agent skills for producing short dramas and animated stories from an idea or source material, covering scripts, visual assets, storyboards, and image, video, and audio prompts. It is intended for screenwriters, animation studios, and directors using Claude Code, Codex, or other agents that support the Agent Skill format. The catalogue skills are the project's own workflow for planning, reviewing, and producing these projects.
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/drama-skills --skill short-drama-editgit clone --depth 1 https://github.com/zenstory-ai/drama-skillsWrote 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/drama-skills/short-drama-edit)<a href="https://agentmods.dev/skills/zenstory-ai/drama-skills/short-drama-edit"><img src="https://agentmods.dev/badge/skills/zenstory-ai/drama-skills/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/drama-skills/short-drama-edit"><img src="https://agentmods.dev/badge/skills/zenstory-ai/drama-skills/short-drama-edit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
- Snyk pass
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 7d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- short-drama-edit — 100% identical, 0 lines differ
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.
- 7d ago Changed 38946a741e12
- 12d ago Changed · -3 lines dc3a81a98da0
- 29d ago Changed · +20 lines 3a8c8e52f6d6
- 1mo 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/drama-skills (3,439 stars, last pushed 7d ago), 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. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-10.
Other skills, from other repositories
seedance-prompt
This skill should be used when the user asks to write, improve, translate, compress, or debug a Seedance 2.x video prompt; mentions T2V, I2V, V2V, R2V, camera direction, prompt quality, or provides reference assets for a production-ready prompt. Model profile, duration, request fields, and reference tokens must come…
drama-skills
A collection of AI skills for creating short dramas and animated comics, from an idea or long source material to scripts and visual-production instructions. It covers episode scripts, story assets, image prompts, storyboard frames, and video prompts.
cinematic-director
A prompt generator for image models that turns a scene description into an English cinematic photography prompt and a negative prompt, which lists details to avoid.
happiness-skill
A Chinese-language guide to happiness based on reducing unmet wants, focusing on the present, and treating happiness as a trainable skill.
tapcanvas-prop-card
A visual-asset skill for creating reusable cards that define a prop such as a weapon, tool, or important object. It records the object's stable identity, parts, usable features, and visible condition changes, then places the result on a TapCanvas canvas.
aesthetic-audit
A commercial visual and user-experience review workflow for websites, product pages, landing pages, and visual assets. It examines clarity, hierarchy, spacing, typography, color, trust signals, conversion paths, and mobile behavior.