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-storyboardgit 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-storyboard)<a href="https://agentmods.dev/skills/zenstory-ai/oh-story-dsh/short-drama-storyboard"><img src="https://agentmods.dev/badge/skills/zenstory-ai/oh-story-dsh/short-drama-storyboard/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-storyboard"><img src="https://agentmods.dev/badge/skills/zenstory-ai/oh-story-dsh/short-drama-storyboard.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 | $0.00102 | $0.04960 |
| Opus 5 | $0.00051 | $0.02480 |
| Sonnet 5 | $0.00020 | $0.00992 |
| Haiku 4.5 | $0.00010 | $0.00496 |
Grade A, and why
short-drama-storyboard 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.
This is a copy
100% identical to short-drama-storyboard — 16 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
短剧分镜与冻结关键帧
把剧本和视觉事实转成有镜头职责、空间连续性和可冻结起点的 剧集/<EP>/分镜.md。
每镜使用二级标题 ## SHOT-...,同镜下用 ### 冻结关键帧提示词 写起始帧正文。
Quick Start
用 $short-drama-storyboard 完成 EP001 的正式分镜和每镜冻结关键帧
入口
当前剧本加必要视觉事实即可直接进入。资产图片提示词与分镜是兄弟分支,不互相等待。只有关键场次 真的存在多个成立导演方案时,才在上下文比较覆盖方案;普通场次直接设计。
创作者可读说明跟随项目语言;冻结关键帧的可复制正文跟随
short-drama.json#/format/prompt_language。没有 short-drama.json 时正文默认使用 en。
分配镜头时长前读取
short-drama.json#/creator_authority/production_profile/choices/native_duration_seconds。已声明目标模型但
没有原生时长时先补这一个选择;目标模型也未声明时照常按叙事节奏设计,不猜供应商限制。
冻结关键帧写完之前,谁会出现在这一格画面里还没有定下来。所以三条依据都在关键帧之后回填, 读的是成稿画面,不是镜头意图。
用户没有手工点名参考图,不等于选择文生视频。冻结关键帧后先根据本镜可见人物、地点、关键道具与 起始构图判断一致性需求,再检查项目中已有的真实图片。只有当前可读、内容与用途可核对的图片才能自动绑定; 文件名像某个角色但内容未核对时,仍视为未准备好。
项目里一张都没有时,创作者有三条路,一次把三条都说清楚再让他选,不要只给「先生成参考图」和
「改成文生视频」两个:把手上已有的图片放进项目再绑成 REF-...;在自己的工具里出图、本轮先用
PLAN-... 写出挂图计划;或者明确改走文生视频。用本套件的生产技能出图只是第一条路的一种做法,
需要项目外的 adapter 与凭据,不是唯一入口。
开始分镜前读 剧集/<EP>/剧本.md 的当前内容。创作者说「剧本已确认采用」指的是那个文件,
不是对话里更早的草稿;两者不一致时以文件为准,并把差异说出来。
工作流
-
读取已接受的目标模型原生时长区间,再确认每个场景动作、对白、声音、画面文字和转折由哪些镜头承载。
-
确定观众何时知道什么、对齐谁、空间如何揭示、转折落在哪个可见动作。 剧本或 Brief 用“前半段 / 后半段 / 前三分之一 / 最后 N 秒”等相对时间限定首次出现、释放或禁止时, 先用已接受集长换成明确时间边界再分镜;例如 60 秒作品的“后半段首次出现”不得早于 30 秒。
-
每镜写清唯一职责、来源、时长、景别/机位、起点、唯一主要动作、终点和声音;用
起点 → 唯一动作 → 终点直接说明人物、双手与持物怎样完成本镜状态转换。三条依据留到第 6 步。 有对白、VO 或 OS 时,先按原文和人物说话方式估算完整发声时间,再安排不能重叠的动作、停顿与 末尾反应;把估时依据简写在本镜「声音」里。具体做法见 对白估时。 -
锁定人物朝向、位置、视线、持物、出入口、屏幕方向和必要状态;上游已有会限制动作空间的持续关系时,把关系投影进本镜起点与终点。
-
冻结关键帧只投影镜头起点;删除终点才出现的文字、动作、姿态或道具状态。
-
关键帧成稿后,先从成稿正文读出这一格里需要保持身份、造型或地理的人物、地点和道具, 再用同一份清单一次填满三条依据:
- 视觉依据:清单里每一项写成《视觉设定.md》的条目引用,这是必写字段;
- 图片提示词项:清单里已有合适
IMG-...条目的写上,没有的留「无」; - 输入参考图:按清单在用户提供的输入、
剧集/<EP>/制作成果/和文档已指向的其他可见媒体中查找匹配图片; 命中就写入REF-...。一张都没命中时写「无(待补参考图:<本镜缺失的起始帧、人物、地点、道具>)」; 只命中一部分时,在已有REF-...后追加「;待补参考图:<仍缺的图片>」,缺口之间只用、分隔。 创作者说图片由他自己在别处准备时,把这份清单写成PLAN-...槽位,本镜即告就绪; 只有创作者明确表示不用图时,才写「无(创作者已明确选择文生视频)」。
三条依据读的是同一格画面,所以不能互相矛盾:关键帧里点名的人物或道具,一定出现在视觉依据里。
-
整集请求完成整集,末端一次报告覆盖、节奏和真实未决选择。
What ships with it
21 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 273 B
- assets/coverage-audition.example.jsonl 1.9 KB
- assets/coverage-template.json 1.2 KB
- assets/keyframe-prompts.md 1.8 KB
- assets/keyframe-template.jsonl 2.3 KB
- assets/revision-lineage.fragment.json 277 B
- assets/scene-visual-plan.example.jsonl 2.8 KB
- assets/shot-template.jsonl 3.5 KB
- references/blocking-playbooks.md 12 KB
- references/comic-keyframe-lexicon.md 11 KB
- references/coverage-audition.md 2.1 KB
- references/keyframe-craft.md 10 KB
- references/production-shot-grammar.md 21 KB
- references/review-and-fixtures.md 3.2 KB
- references/scene-visual-plan.md 1.8 KB
- references/screenplay-to-keyframe-example.md 7.7 KB
- references/shot-craft.md 14 KB
- references/shot-revision-identity.md 1.7 KB
- references/stage-contract.md 10 KB
- scripts/selftest.py 6.8 KB runs code
- scripts/storyboard_check.py 30 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.
- yesterday Changed · +7 lines 7a7ff4c83981
- 7d ago Changed · +82 lines 187b38c3f177
- 12d ago First seen · 83 lines · 102 tokens per session scan A ebb6383d86bd
short-drama-storyboard is a skill published in the GitHub repository zenstory-ai/oh-story-dsh (338 stars, last pushed today), licensed MIT. It adds 102 tokens to every session and 4,960 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to short-drama-storyboard, differing in 16 lines, and is treated as a copy.
Other skills, from other repositories
story-import
A tool for turning an existing novel into a structured writing project. It analyzes the book and organizes its characters, settings, plot plans, chapters, and tracking data for later writing.
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.
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-short-analyze
A Chinese-language guide for analysing short popular web fiction, such as stories published on 番茄, 故事会, or 知乎盐选. It examines the core premise, plot structure, emotional arc, twists, writing techniques, and reader appeal.
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…
novel-language-style
A guide to choosing and controlling the writing style of online fiction. It covers narration, word choice, figurative language, dialogue, and techniques for making scenes easier to picture.