影策 is an open-source workspace for AI film and short-video production, using a freeform canvas and structured workflows to organize scripts, characters, scenes, storyboards, media assets, and generated text, images, video, and audio. It is for creators who manage audiovisual projects through local or trusted deployments, with features for task tracking, asset management, timelines, and AI-agent workflows.
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 ddcat-ai/open-ai-canvas --skill 04git clone --depth 1 https://github.com/ddcat-ai/open-ai-canvasWrote 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/ddcat-ai/open-ai-canvas/04)<a href="https://agentmods.dev/skills/ddcat-ai/open-ai-canvas/04"><img src="https://agentmods.dev/badge/skills/ddcat-ai/open-ai-canvas/04/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/ddcat-ai/open-ai-canvas/04"><img src="https://agentmods.dev/badge/skills/ddcat-ai/open-ai-canvas/04.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 | $0.00164 | $0.08179 |
| Opus 5.5 | $0.00066 | $0.03272 |
| Sonnet 5.5 | $0.00033 | $0.01636 |
| Haiku 4.5 | $0.00016 | $0.00818 |
Grade A, and why
影视剧作工坊-04-场景与人物设计 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
场景与人物设计（模块 04）
主链定位：开发层 / 人物资产层 / 场景资产层 / 全场景物理约束 / 都市场景库。
核心信条
- 人物：技术词翻成画面词、抽象词翻成具象词、参考图翻成锚定词——模型不认识"次世代 PBR 皮肤"，它认识"皮肤通透有血色、可见毛孔与干纹"。
- 场景：场景不是"放个背景"，是搭一个可信的空间——有尺度、有材质、有光影、有氛围。
唯一入口：单帧图触发流程
本模块不再单独触发。所有调用一律走单帧图触发流程——无论触发来自全链路的自动带起，还是来自 05 表演 / 06 景别 / 07 分镜 / 10 组接的调用。
| 项 | 定义 |
|---|---|
| 入口 | 单帧图触发流程（唯一） |
| 产出 | 单帧图——单张、一个时刻、一个完整画面 |
| 格式 | characters/19：①–⑦ 七要素 + 负面约束；不带声音层 |
| 同时供出 | 人物锚定段与场景世界观约束，供 05/06/07/10 复用 |
没有「单独出人物 / 单独出场景」这条入口。要人物就出人物单帧图，要场景就出场景单帧图——都是单帧图，只是主体不同；两者的资产层（characters/ 七层设定卡、scenes/ 六维）照常调用。
链内三个实例：常规单帧图 · 首帧图 · 尾帧图（后两者走首帧 / 首尾帧生视频时出，见下节）。
取景（不由本模块自定，走 06 景别）
取景 = 该镜的景别，由 06 景别构图机位灯光（shotlang/01-景别.md）按叙事需要决定：大远景 / 全景 / 全身 / 中景 / 中近景 / 近景 / 特写 / 大特写 / 插入镜。
**本模块不再自设「出图形态」档位。**原四档（默认全身图 / 三视图 / 半身图 / 局部特写图）已退役：
| 原档位 | 处置 |
|---|---|
| 全身图 / 半身图 / 局部特写图 | 本就是景别，改由 ⑥镜头景别承载（06 shotlang/01） |
| 三视图 / 多格设定稿 | 不是单帧图（多格、多时刻），不再产出 |
渲染要求不变：任何取景都逐字带通用渲染要求与全局负面词（见 characters/06 §2）——取景只改构图与取景范围，不改画风与质量基线。
人物单帧图与场景单帧图走同一条流程，只是主体不同：人物单帧图取 ④ 人物外观状态，场景单帧图取 ③ 环境场景为主。
单帧图提示词（本模块的唯一产出）
**本模块走进全链路时的产出：单帧图。**单张、完整画面、带场景与光影，标准格式 = characters/19：
② 画幅 + ⑥ 景别（前置，先定画框）
→ ④ 人物外观状态（九层：身份/年龄/体型体态/皮肤质感/面部/发型/头饰/服装/辨识标记）
→ ⑤ 人物动作（可见动作 + 微表情 + 呼吸与身体微节拍）
→ ③ 环境场景 → ⑦ 光影色彩（六条）→ ⑥ 镜头运镜
→ ① 渲染规格 → ② 画幅画质 → 负面约束
**⚠️ 单帧图不带声音层。**单帧图只取 ①–⑦ 七要素 + 负面约束；⑧对白 / ⑨背景音 / ⑩BGM 属视频与交付文件层，由 12 装配（见 12 prompt/32-三模式标准交付模板.md），不进单帧图。
「单帧图」的判定：一张、一个时刻、一个完整画面。 不是三视图，不是多格宫格，不是纯白设定稿——那些已随「出图形态」退役，本模块不再产出。
单帧图在链内的三个实例
| 实例 | 何时出 | 数量 |
|---|---|---|
| 常规单帧图 | 链内任一需要画面定稿的节点 | 每镜 1 张 |
| 首帧图 | 该镜走首帧 / 首尾帧生视频 | 1 张 = 视频第 1 帧 |
| 尾帧图 | 该镜走首尾帧生视频 | 1 张 = 视频最后 1 帧 |
三个实例共用同一套格式（characters/19 十槽位）；首帧图与尾帧图额外受三条硬性衔接条件约束：
- 两张图必须同一画幅比例 —— 比例不一致在视频提交阶段直接失败；比例在出图阶段就定死，视频阶段补救不了。做 9:16 竖屏成片，两张图就必须都是 9:16。
- 两张图必须是同一连续动作的起止状态 —— 不是两个无关画面。起止状态不连续时，中段会漂移到"能同时接住两端"的折中画面。
- 两张图的人物/场景锚定段逐字一致 —— 只有状态与姿态不同；外貌描述必须完全相同，否则两端人物对不上。
What ships with it
42 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.
- advertising/01-广告与商业图工作流(手册第十三章).md 14 KB
- characters/01-角色引擎七层设定与锚定词.md 8.0 KB
- characters/02-标准角色设定卡模板.md 5.7 KB
- characters/03-人物逻辑四维弧光.md 6.5 KB
- characters/04-角色原型库.md 7.3 KB
- characters/05-UE5次世代角色资产库214个.md 47 KB
- characters/06-版式基准.md 16 KB
- characters/07-风格族基准.md 8.2 KB
- characters/08-解剖与服装词汇.md 7.1 KB
- characters/09-角色动作交互词汇.md 6.7 KB
- characters/10-角色库速查.md 6.8 KB
- characters/11-人像案例库.md 147 KB
- characters/12-风格通道词库.md 31 KB
- characters/13-参考图解析规则.md 5.6 KB
- characters/14-输出模板.md 6.7 KB
- characters/15-风格基准库.md 119 KB
- characters/16-人物资产补齐.md 40 KB
- characters/17-微表情基准-100组面部表情.md 17 KB
- characters/18-角色一致性与设定表工程(手册第七八章).md 28 KB
- characters/19-标准角色提示词输出模板.md 13 KB
- dev/01-开发层资产表.md 26 KB
- dev/02-前期开发-故事圣经增量(手册第十二章).md 13 KB
- engine/E04-场景与人物设计.md 16 KB
- references/01-组织纪律与引用清单.md 8.7 KB
- references/02-源模块结构与路由.md 5.7 KB
- references/jimeng-seedream-adaptation.md 7.6 KB
- scenes/00-世界观视觉宪法.md 7.0 KB
- scenes/01-场景风格通道.md 4.1 KB
- scenes/02-场景类型库.md 3.2 KB
- scenes/03-全气候光照库.md 5.7 KB
- scenes/04-场景取景视角.md 3.7 KB
- scenes/05-场景元素维度库.md 3.2 KB
- scenes/06-都市环境全气候四季库.md 13 KB
- scenes/07-材质与灯光词汇.md 6.0 KB
- scenes/08-竖屏场景构图.md 2.0 KB
- scenes/09-经典配色组合.md 2.2 KB
- scenes/10-建模基准-3D生产流程与验收.md 16 KB
- scenes/11-场景提示词模板.md 3.4 KB
- scenes/12-物理引擎约束全方案.md 73 KB
- scenes/13-都市场景-穿搭-首饰-车辆-饮食精要.md 20 KB
- scenes/14-场景资产补齐.md 25 KB
- scenes/15-全场景物理约束规范(山川河流建筑动作).md 33 KB
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.
- 11d ago First seen · 235 lines · 164 tokens per session scan A 936da65e433e
影视剧作工坊-04-场景与人物设计 is a skill published in the GitHub repository ddcat-ai/open-ai-canvas (1,391 stars, last pushed 2d ago), licensed MIT. It adds 164 tokens to every session and 8,179 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 2026-10-14.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.