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 03git 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/03)<a href="https://agentmods.dev/skills/ddcat-ai/open-ai-canvas/03"><img src="https://agentmods.dev/badge/skills/ddcat-ai/open-ai-canvas/03/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/03"><img src="https://agentmods.dev/badge/skills/ddcat-ai/open-ai-canvas/03.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 | $0.00083 | $0.03681 |
| Opus 5.5 | $0.00033 | $0.01472 |
| Sonnet 5.5 | $0.00017 | $0.00736 |
| Haiku 4.5 | $0.00008 | $0.00368 |
Grade A, and why
影视剧作工坊-03-渲染表现 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
渲染表现（模块 03）
主链定位：风格→路径路由。把 02 定下的"这部片是什么调子"翻译成"这条画面用什么生产路径实现"，产出可交付的渲染档案。
做什么
确立每个镜头（或每条风格档位）的视觉生产路径与渲染属性，产出 SHOT_RENDER_PROFILE ——它是 12 技术语言转换选择 UE5 / Arnold 通道时的唯一依据。
本模块回答四个问题：用什么做（载体 / 美术方向）→ 做到多真（写实度）→ 怎么算（渲染策略）→ 谁去算（渲染器），以及画面侧的六维 DNA（构图 / 光影 / 色彩 / 质感 / 场景 / 动作）。
方法边界：
- 02 定整片影调与调色（调色情绪、调色板、胶片型号、60/30/10）；本模块定生产路径与材质光学响应。选了某种调色板不等于选了某个渲染器。
- 06 定单镜的景别、机位、灯光物理；本模块的构图轴与光影系只给风格侧取值倾向，落地参数以 06 为准。
- 08 定镜头运动形式与参数；本模块只在五轴的 E 轴上判断"动静强度"。
- 12 定技术词→画面语言的转换；本模块产出的是技术字段本身，技术词不进最终提示词。
双引擎
- 渲染智能 —— 本模块内的固定链前半段（意图解析 → 路由 → profile 生成）。
- 语义转换 —— 12 技术语言转换（UE5 / Arnold 通道）：UE5 通道（实时渲染：Lumen / Nanite / Substrate / VSM）与 Arnold 通道（离线渲染：Path Tracer / Standard Surface / Atmosphere Volume）。二次元 / 赛璐璐不走渲染通道，走独立风格化输出。
两者通过 SHOT_RENDER_PROFILE 衔接：渲染智能产出字段，语义转换消费字段。
基础引擎
本模块的底层方法论源：engine/E03-渲染表现.md（本模块目录内，12 条，来自 book02）。
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。
其中两条对本模块最关键：介质选择参与质感定义（换介质即换全片气质）、让光可见：先给光一个介质（体积光必须有灰尘 / 蒸汽 / 水珠承载）。
渲染层（render/）
| 文件 | 管什么 |
|---|---|
render/01-视觉意图四维本体.md |
四维正交定义——视觉生产体系 A / 写实度 B / 渲染策略 C / 渲染器 D；常见说法的组合解析表（"次世代超写实 3D，Arnold"怎么拆）+ 三条防越权约束 |
render/02-风格组合矩阵.md |
九轴矩阵（载体 / 美术方向 / 写实度 / 摄影提示 / 色彩 / 灯光 / 机位运动 / 渲染策略 / 渲染器）+ 七条兼容原则 + 典型组合 + 路径别名（虚幻五 / 阿诺德 / 国漫 3D / 好莱坞级 ↔ 轴组合） |
render/03-渲染智能路由.md |
固定链、渲染智能内部能力 15 项、处理顺序九步、SHOT_RENDER_PROFILE 交付契约（含 locked_fields / derived_fields 分离）、禁止反向污染、四维轴与六维 DNA 的单向关系 |
render/04-融合执行规则.md |
十条执行规则：风格不是标签 / 五轴融合 / 风格剂量 / 冲突不得静默删除 / 视频动态五维 / 负面约束分类 / 参数化不丢真相 / 字段级映射 / 回到主链路 |
render/05-六维视觉DNA与控制轴.md |
通用提示词骨架与四段式、六维 DNA（构图与镜头 / 色彩与光影 / 质感与氛围 / 经典场景 / 角色与动作 / 色调细节）+ 构图轴 15 控制项 + 情绪→构图选择逻辑 |
render/06-光影与色彩系统.md |
三大光影系（柔和自然 / 冷峻压迫 / 戏剧化人工光）+ 色彩八字段 + 四种色彩策略（少色多阶 / 高饱和符号色 / 冷暖对冲 / 低饱和生活流） |
render/07-质感组件与剂量.md |
PMS-3D 质感层五组组件（胶片 / 光学 / 工艺 / 环境 / 运动）+ 剂量纪律 2–4 个 + 过度堆叠反模式 |
render/08-导演视觉DNA库.md |
15 位导演 / 摄影组合的可调用视觉 DNA，用作风格锚点而非提示词内容 |
render/09-视觉风格DNA库.md |
15 种通用影视视觉风格 + 12 个具体流派 DNA（日系青春 / 娄烨都市 / 王家卫港风 / 徐克武侠 / 李安诗意 / 戏曲 / 90 年代华语 / 英伦田园 / 巨物 / 超现实 / 纪实…） |
render/10-风格融合与冲突检测.md |
五轴融合（构图 / 光影 / 色彩 / 质感 / 动作与运镜）+ 七组冲突检测判决规则（主导 + 点缀；明确要求时保留冲突） |
render/11-图片转视频与调用模板.md |
图片→视频结构、基础运镜词、视频动作五维原则、模板 A/B/C（导演 DNA / 类型风格 / 融合风格）、最终生成公式 |
render/12-负面约束与迭代规则.md |
七条执行规则（Rule 01–07）、通用反向约束与按目标风格生成的示例、来源使用原则 |
render/13-视觉风格调用接口.md |
visual_style YAML 字段结构（anchor / composition / lighting / color / texture / environment / performance / cinematography / negative_constraints）+ 字段级映射规则 |
render/14-视觉风格融合层.md |
视觉风格融合层——视觉 DNA 引擎说明与运行时位置、风格融合规则 5.0（完整保留 / 风格不是单标签 / 五轴融合 / 剂量 / 冲突 / 视频优先增动态 / 负面约束 / 参数化不丢真相 / 统一 IR 映射 / 最终输出）、Style Composition Matrix 5.0（九轴 + 七条兼容原则 + 典型组合）、VISUAL_DNA_REGISTRY、HOLLYWOOD_STYLE_REGISTRY、visual_style_dna_engine 运行时接口、完整熔炼映射（逐章对应关系）。⚠️ 原文件中的《影视视觉风格精华熔炼模块》一节与本模块 render/05–render/09 已有内容重复（66.6%），未收录 |
render/15-导演plus渲染层-新增件.md |
DirectorPlus 5.0 渲染层的新增节——RENDER_INTELLIGENCE 渲染智能层（内容/后端/硬规则）、RENDER_INTELLIGENCE_ROUTING 路由（内部能力 + 九步处理顺序 + 禁止反向污染）、VISUAL_INTENT_ONTOLOGY 视觉意图本体（A 生产体系 / B 写实度 / C 渲染策略 / D 渲染器 + 组合解析 + 约束）、05_VISUAL_RENDER 融合规则（Visual hierarchy / Human lock / Render Intelligence / Arnold·UE5 / QC）等。⚠️ 原文 129 节中，组合矩阵轴与兼容原则、融合规则各条、熔炼映射各节、15 位导演 DNA、15 种视觉风格 DNA 等与 render/01–render/14 重合 60–100%，已剔除 |
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/E03-渲染表现.md 4.0 KB
- render/01-视觉意图四维本体.md 3.5 KB
- render/02-风格组合矩阵.md 3.2 KB
- render/03-渲染智能路由.md 4.1 KB
- render/04-融合执行规则.md 3.0 KB
- render/05-六维视觉DNA与控制轴.md 3.7 KB
- render/06-光影与色彩系统.md 3.0 KB
- render/07-质感组件与剂量.md 2.2 KB
- render/08-导演视觉DNA库.md 3.2 KB
- render/09-视觉风格DNA库.md 5.2 KB
- render/10-风格融合与冲突检测.md 2.5 KB
- render/11-图片转视频与调用模板.md 2.9 KB
- render/12-负面约束与迭代规则.md 3.2 KB
- render/13-视觉风格调用接口.md 2.2 KB
- render/14-视觉风格融合层.md 31 KB
- render/15-导演plus渲染层-新增件.md 24 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 · 105 lines · 83 tokens per session scan A c084d7ba33a2
影视剧作工坊-03-渲染表现 is a skill published in the GitHub repository ddcat-ai/open-ai-canvas (1,391 stars, last pushed 2d ago), licensed MIT. It adds 83 tokens to every session and 3,681 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 2026-10-14.
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.