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 08git 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/08)<a href="https://agentmods.dev/skills/ddcat-ai/open-ai-canvas/08"><img src="https://agentmods.dev/badge/skills/ddcat-ai/open-ai-canvas/08/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/08"><img src="https://agentmods.dev/badge/skills/ddcat-ai/open-ai-canvas/08.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 | $0.00090 | $0.03018 |
| Opus 5.5 | $0.00036 | $0.01207 |
| Sonnet 5.5 | $0.00018 | $0.00604 |
| Haiku 4.5 | $0.00009 | $0.00302 |
Grade A, and why
影视剧作工坊-08-运镜设计 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
运镜设计（模块 08）
主链定位：意图→镜头参数映射 / 镜头契约与运镜物理。
做什么
把叙事意图翻译成镜头运动参数，并落成生成层可识别的英文预设名。
- 06 管"画面里有什么、怎么摆、怎么打光"，本模块管"镜头怎么动"。
- 07 管"用几个镜、每镜讲什么"，本模块管"每镜的运动形式与参数"。
核心原则（五条运镜规则）
- 一个镜头一个主运动（单动规则）—— 叠加多个运镜是抖动、意外旋转与生成失败的头号原因；需要多个动作就拆成多个镜头，或写成带时序的先后阶段。
- 运动必须可测量 —— 总行程、时长、速度都给单位（"在整整 7 秒里只后拉 10–15 厘米"）；"快"这类形容词是劣化最严重的提示词之一。
- 运动由情绪驱动 —— 镜头是焦点人物的情绪替身；移动方式、焦段与时长都应当由角色的情绪状态决定，而不是由抽象的"有电影感"决定。
- 组合必须兼容 —— 推近与拉远、上升与下降不能同镜出现；多段运动写成"0–3 秒上升，停住，然后 4–8 秒推近"的离散阶段。
- 复杂运动优先克隆 —— 从视频参考迁移镜头运动，绕开文字解释的失真。
术语约定：静帧里的运动是暗示（动态模糊、暗示运动的构图、运动中途凝固）；视频里的运动是指令。[img 1] / @Image1 指第一张参考图；@Video1 指第一段视频参考。
基础引擎
本模块的底层方法论源：engine/E08-运镜设计.md（本模块目录内，60 条，来自 book01/book02/book04）。
执行本模块前先查阅该引擎，取其判断依据、创作准则与反模式清单；引擎为只读源层，本模块负责执行流程。
运镜层（moves/）
| 文件 | 管什么 |
|---|---|
moves/01-运镜词汇总表.md |
视频运镜词汇：推轨 / 摇臂垂直 / 环绕弧线 / 变焦 / 跟随动作 / 特殊电影感 / 时间类 / 穿物转场 / 特殊载具——控制项、作用、最佳用例、示例短语 |
moves/02-静帧暗示与组合运镜.md |
静帧中的运动暗示（动态模糊、暗示性构图、运动中途凝固）+ 组合运镜兼容规则 |
moves/03-运镜纪律.md |
单动规则、微动需要精确距离、可测量语言 |
moves/04-运动语言五支柱.md |
运动语言五支柱——运动层级四层（主体/内部/摄影机/环境）分开点名、镜头契约三式（先写摄影机行为再写主体）、运动物理锚（物理类比/时间测量取代"慢/快"）、运动质感（运动的性格）、镜头行为序列（对焦事件写成触发→转移→状态→回归→重复的叙事） |
moves/05-情绪同步与题材预设.md |
镜头-情绪同步（镜头是情绪替身，含摄影 × 表演速查对照）+ 按题材的运镜预设 |
moves/06-可靠短语库.md |
经验证的可靠运镜提示短语，可直接取用 |
moves/07-视频参考迁移.md |
镜头迁移、双视频参考、智能模式、视频参考能力边界 |
moves/08-运动失败图谱.md |
运镜失败的症状 → 成因 → 修复对照表（多运动过载、帧率漂移、动作被截断） |
moves/09-镜头运动预设库.md |
数据层——命名镜头预设资产库：Dolly / Crane / Orbit / Zoom / Follow / Specialty / Time-Based / Through-Object / Vehicle / Pitch 的英文预设名与组合合法性校验 |
moves/10-镜头控制全库.md |
镜头控制权威表（Higgsfield higgsfield-camera v3.5.0）——推轨 / 摇臂垂直 / 环绕弧线 / 变焦 / 跟随动作 / 特殊电影感 / 时间类 / 穿物转场 / 特殊载具 / 俯仰与透视（机位角度） / 景别 / 组合镜头控制；每项含作用·最佳用例·示例提示短语。另含 Camera-Emotion Sync（按焦点人物情绪选镜头运动、单镜内情绪弧线、按镜头用途选焦段与光圈、按类型划分的镜头时长）、One-Move Rule、按题材划分的镜头预设、可靠短语库、视频参考迁移与双视频参考 |
moves/11-运镜词汇参考.md |
术语词典——运镜术语按族罗列（线性 / 垂直 / 环绕弧线 / 变焦 / 跟随沉浸 / 电影感技法 / 机位角度 / 基于时间…），中英对照，供查名与选词 |
moves/12-运动预设.md |
具名运动/VFX 预设表（Higgsfield higgsfield-motion v3.2.1）——变身与身体效果（Animalization / Werewolf / Cyborg / Disintegration / Clone Explosion…）、元素效果（Air/Water Bending、Fire Element…）、转场、以及各预设的适用题材与模型兼容性 |
moves/13-运镜总清单.md |
运镜总索引——视频 9 族 38 预设 / Director Panel 18+1 / 静帧暗示运动 20 的清单式总览，用于快速选族与点数 |
moves/14-全镜头转换-镜头运动.md |
《全镜头类型精准转换总规范》第 4 章——镜头运动逐类转换：固定 / 推 / 拉 / 摇 / 俯仰摇 / 横移 / 跟 / 升降 / 环绕 / 手持 / 斯坦尼康，以及变焦铁律与运镜三大合法动机 |
moves/15-运镜四维编码.md |
运镜四维编码（seedance2.0-prompt-skill）——运镜按 X/Y/Z 轴 + 时间四维编码，含推拉摇移规范，供程序化组合与校验 |
What ships with it
16 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.
- engine/E08-运镜设计.md 22 KB
- moves/01-运镜词汇总表.md 7.7 KB
- moves/02-静帧暗示与组合运镜.md 4.9 KB
- moves/03-运镜纪律.md 2.2 KB
- moves/04-运动语言五支柱.md 4.1 KB
- moves/05-情绪同步与题材预设.md 3.9 KB
- moves/06-可靠短语库.md 921 B
- moves/07-视频参考迁移.md 3.2 KB
- moves/08-运动失败图谱.md 3.0 KB
- moves/09-镜头运动预设库.md 34 KB
- moves/10-镜头控制全库.md 30 KB
- moves/11-运镜词汇参考.md 34 KB
- moves/12-运动预设.md 22 KB
- moves/13-运镜总清单.md 3.6 KB
- moves/14-全镜头转换-镜头运动.md 14 KB
- moves/15-运镜四维编码.md 20 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 · 88 lines · 90 tokens per session scan A b92edca497c1
影视剧作工坊-08-运镜设计 is a skill published in the GitHub repository ddcat-ai/open-ai-canvas (1,391 stars, last pushed 2d ago), licensed MIT. It adds 90 tokens to every session and 3,018 once invoked, about $0.0004 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.