short-drama-storyboard

short-drama-storyboard is a skill for Codex from sutchan/Agent-Skills-Hub. It costs 102 tokens per session (5,914 once invoked), scanned A, a copy of short-drama-storyboard, MIT.

A storyboard guide that turns a script and visual facts into numbered shots with clear purposes, continuity, and frozen starting frames. A storyboard is a plan for what the viewer sees at each moment.

In plain words
What is it for?
Planning shots for a short drama, defining camera views and durations, locking character and object positions, and writing prompts for each shot's starting frame.
Why use it?
It helps prevent missing story information, repeated shots, broken screen direction, and impossible transitions between shots. It also records which visual details must stay fixed.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: $skill-name invocation.

Good fit Planning shots for a short drama, defining camera views and durations, locking character and object positions, and writing prompts for each shot's starting frame.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sutchan/agent-skills-hub/short-drama-storyboard
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 sutchan/Agent-Skills-Hub --skill short-drama-storyboard
Clone the repo
git clone --depth 1 https://github.com/sutchan/Agent-Skills-Hub

Made for: 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 short-drama-storyboard

README.md
[![agentmods](https://agentmods.dev/badge/skills/sutchan/agent-skills-hub/short-drama-storyboard/github.svg)](https://agentmods.dev/skills/sutchan/agent-skills-hub/short-drama-storyboard)
Your own site
<a href="https://agentmods.dev/skills/sutchan/agent-skills-hub/short-drama-storyboard"><img src="https://agentmods.dev/badge/skills/sutchan/agent-skills-hub/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.

agentmods 80×15 button for short-drama-storyboard

Your own site · 80×15
<a href="https://agentmods.dev/skills/sutchan/agent-skills-hub/short-drama-storyboard"><img src="https://agentmods.dev/badge/skills/sutchan/agent-skills-hub/short-drama-storyboard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,914 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 88% copy Near-identical to another mod 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 $0.00102 $0.05914
Opus 5.5 $0.00041 $0.02366
Sonnet 5.5 $0.00020 $0.01183
Haiku 4.5 $0.00010 $0.00591

Measured 5d ago against content hash fec0a090c48b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 5d 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.

Origin

This is a copy

88% identical to short-drama-storyboard — 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.

skills/short-drama-storyboard/SKILL.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 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; 需要时另加 ### 收尾关键帧提示词 写终点正文。

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。 同时读取 short-drama.json#/creator_authority/rhythm_profile:status 为 accepted 时,镜长按 镜长从哪来 由声音事件与 target_avg_shot_seconds 推出, 全集近景类镜头占比不低于 close_shot_share_min;档案缺失或未接受时不核对这些数值。

冻结关键帧成稿后,再按画面中的可见内容填写视觉依据、图片提示词项和输入参考图, 避免只按镜头意图列资产而漏掉实际入画的人物或物件。

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。

项目里没有所需图片时,一次向创作者说明三条可选路径: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

  1. 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。
  2. 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。
  3. 每镜写清唯一职责、来源、时长、景别/机位、运镜、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。 数一下这一镜要观众看清的事,按镜长判断每件有没有足够的时间被看清;放不下时先删、合并或拆镜,见 短镜头的动作量:视频模型不会删掉多出来的动作,而是把它们压到看不清。 「运镜」按本镜目的逐镜选,写行为和理由,固定也写理由,见 运镜逐镜选。 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。 对白场先按 对白覆盖默认 放切点;镜长不按剧本字数折算。
  4. 一场戏拍成多镜时,先在《分镜.md》开头写这场的「场景站位」:固定锚点、各人相对锚点与彼此的位置、轴线与 working side、哪一镜改变站位。再逐镜锁定朝向、位置、视线、持物、出入口和必要状态,与「场景站位」一致;起点、终点里的位置写锚点和人物关系,视线写看向谁或什么;冻结关键帧再把它翻成本镜机位下的前后景、朝向、中间隔着什么和画面左右,见 站位先写锚点和关系。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。
  5. 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。 镜头的职责落在收尾那一下时,另写 ### 收尾关键帧提示词 投影终点——同一格画面的 另一端,规则完全对称:删除起点才有、终点已经不在的东西。它是可选的,写法与取舍见 首尾成对。
  6. 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:

Read the full file on GitHub · 184 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. 5d ago Changed · -4 lines fec0a090c48b
  2. 9d ago Changed · -2 lines 0894672c45aa
  3. 26d ago Changed · +23 lines 0cffebff9659
  4. 1mo ago Changed · +82 lines a253b3555c0c
  5. 1mo ago First seen · 85 lines · 102 tokens per session scan A 6c2bb6695c21

Subscribe to this mod's changes

short-drama-storyboard is a skill published in the GitHub repository sutchan/Agent-Skills-Hub (2 stars, last pushed 4d ago), licensed MIT. It adds 102 tokens to every session and 5,914 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 88% identical to short-drama-storyboard, differing in 0 lines, and is treated as a copy.