影视剧作工坊-12-技术语言转换与模型自然语言

影视剧作工坊-12-技术语言转换与模型自然语言 is a skill for Claude Code, Codex from ddcat-ai/open-ai-canvas. It costs 151 tokens per session (9,321 once invoked), scanned A, original, MIT.

A translation guide that converts film and rendering instructions into plain visual prompts for the Jimeng image and video platform. It separates the source technical details from the final language given to the model.

In plain words
What is it for?
Use it to translate shot instructions, route prompts for different visual or rendering styles, structure prompts by time and visual elements, and adapt them to Jimeng's image and video modes.
Why use it?
Technical terms used by directors or rendering tools may not produce the intended picture when copied directly into a generation prompt. This guide maps those terms to visible descriptions and applies platform-specific prompt formats.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to translate shot instructions, route prompts for different visual or rendering styles, structure prompts by time and visual elements, and adapt them to Jimeng's image and video modes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ddcat-ai/open-ai-canvas/12
About the project

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.

ddcat-ai/open-ai-canvas · 1,391 stars · on GitHub · yingce.tv

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 ddcat-ai/open-ai-canvas --skill 12
Clone the repo
git clone --depth 1 https://github.com/ddcat-ai/open-ai-canvas

Made for: Claude Code, 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 影视剧作工坊-12-技术语言转换与模型自然语言

README.md
[![agentmods](https://agentmods.dev/badge/skills/ddcat-ai/open-ai-canvas/12/github.svg)](https://agentmods.dev/skills/ddcat-ai/open-ai-canvas/12)
Your own site
<a href="https://agentmods.dev/skills/ddcat-ai/open-ai-canvas/12"><img src="https://agentmods.dev/badge/skills/ddcat-ai/open-ai-canvas/12/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 影视剧作工坊-12-技术语言转换与模型自然语言

Your own site · 80×15
<a href="https://agentmods.dev/skills/ddcat-ai/open-ai-canvas/12"><img src="https://agentmods.dev/badge/skills/ddcat-ai/open-ai-canvas/12.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 151 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 9,321 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 original No closer match found 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 $0.00151 $0.09321
Opus 5.5 $0.00060 $0.03728
Sonnet 5.5 $0.00030 $0.01864
Haiku 4.5 $0.00015 $0.00932

Measured 11d ago against content hash 5938c3da1f59, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

影视剧作工坊-12-技术语言转换与模型自然语言 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.

backend/builtin/影视剧作工坊/影视剧作工坊-12-技术语言转换与模型自然语言/SKILL.md · 278 lines

How it starts

The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.

技术语言转换与模型自然语言(模块 12)

主链定位:ST 唯一语义出口 + 平台适配。把导演与渲染层技术语言翻译成模型可直接执行的画面语言。

做什么

把导演和渲染层的技术语言,翻译成即梦能直接执行的画面语言。只做语言转换,不生产内容,不做技术决策。

底层逻辑

逐秒六维是转换的基本单位。每个镜头按时间轴拆成逐秒行,每一秒从六个维度描述:主体状态、动作节拍、机位运动、资产状态、光影变化、声音点。

六维是内部工作台,用来拆解每一秒。拆完后聚合成八要素。六维行不进入交付文件,不进模型提示词。

三层路由

模块的路由由三层串联组成:风格解析 → 通道决定 → 子模块调度。数据层(channels/)存放各通道的术语映射表,逻辑层(本节)负责解析与调度。同一镜头只走一条通道、只激活该风格词需要的子模块组合。

构建原则:子通道按「渲染器自身技术文档类目」划分

各渲染器通道内部,按其技术文档自身的类目体系划分子通道(UE5 用 光照与全局光照/材质与着色/后期处理/体积效果/毛发与织物/角色与皮肤/程序化纹理/色彩管理/灯光滤镜;Arnold 用 光照/标准表面着色器/标准毛发着色器/皮肤/眼睛/体积与大气/置换与细分/程序化纹理/灯光滤镜/色彩管理)。各通道类目可不同,但映射目标一致——全部转为即梦可直接执行的纯画面语言。

  • 通道类目以「渲染环节 + 画面元素」混合组织(如光照、材质、后期为一类;角色与皮肤、毛发与织物为元素类),不强制跨渲染器同名。
  • 跨渲染器的同名元素(皮肤/眼睛/毛发)目标画面一致,映射到同一批视觉词条;不同通道的同名子通道在词表层面各自维护。
  • 好处:子通道即技术文档的天然章节,新增渲染器时直接照其文档类目建子通道,映射不漏项。

第一层:风格解析层

用户输入风格词时,先解析它指向什么视觉目标。风格词分两类:

  • 指向画面对象:真人质感、超写实3D、国漫风格、二次元、半写实3D。这类词决定画面「像什么」,触发对应的画面对象子模块。
  • 指向渲染环节:极致光影、电影感、体积感、氛围感。这类词决定画面「怎么渲染」,触发对应的渲染环节子模块。

第二层:通道路由层

风格解析完成后,决定走哪条渲染通道。

  • 有明确渲染器技术词 → 按技术词走:出现 Lumen/流明、Nanite/纳米、Substrate/基底材质、VSM/虚拟阴影贴图 → UE5 通道(实时渲染);出现 Path Tracer、Standard Surface、Subsurface Weight、Atmosphere Volume → Arnold 通道(离线渲染)。
  • 出现渲染模式词 → 按渲染模式走:出现「实时渲染」→ UE5 通道;出现「离线渲染」→ Arnold 通道。实时渲染与离线渲染是通道的渲染模式属性:UE5 = 实时渲染通道,Arnold = 离线渲染通道。
  • 只有风格词、无渲染器技术词 → 按风格词默认路由:
    • 真人质感、超写实3D、国漫风格、半写实3D → 默认 UE5 通道。理由:UE5 的 MetaHuman 生态覆盖皮肤、毛发、眼睛、微表情的完整参数体系;风格化材质(国漫、半写实)在 Substrate 材质系统里也有对应表达。
    • 极致光影、电影感 → 看场景:室内封闭空间走 Arnold(Path Tracer 间接光照与焦散更精确);室外开阔空间走 UE5(Lumen 动态全局光照更高效)。
    • 二次元、赛璐璐风格 → 不走任何渲染通道。这类风格排斥写实渲染,直接走独立的风格化输出,不调用 UE5 或 Arnold 的子模块。

第三层:子模块调度层

通道确定后,按风格词激活对应的子模块组合(子模块即 channels/ 下的画面对象子通道):

  • 真人质感:激活 皮肤、毛发、眼睛、微表情 四个子模块。皮肤调 Burley SSS 或 Subsurface Weight;毛发调 Groom 或 Standard Hair;眼睛调 Cornea 或 Cornea Shader;微表情调 FACS 或 Displacement;光照调 Lumen 或 Skydome Light;后期调 色调映射、胶片颗粒。
  • 超写实3D:激活 材质、光照、后期 三个子模块。材质调 Substrate 或 Standard Surface;光照调 Lumen 或 Physical Sky;后期调 ACES 色调映射、景深。皮肤调次表面散射,但不调微表情和眼睛的精细参数——超写实3D 追求整体画面像 CG 电影,不是人物面部特写。
  • 国漫风格:激活 材质、光照、后期 三个子模块,映射方向不同。材质排斥 PBR 写实,调「皮肤通透但非真人质感,发丝成束不单根可见,布料有手绘感」;光照调「主次光分明,高光受控,暗部有风格化色块」;后期调「色彩浓郁,暗部偏蓝或偏紫,高光偏暖」;皮肤调「肤色均匀,有淡淡红晕,无毛孔无雀斑」。
  • 极致光影:激活 光照、体积、后期 三个子模块。光照调 Lumen 硬件光线追踪或 Path Tracer;体积调 体积雾、体积云;后期调 泛光、镜头光晕、色调映射。不激活皮肤、毛发、眼睛子模块——极致光影追求光线本身的物理表现,人物是光的载体,不是细节主体。
  • 电影感:激活 光照、后期、体积 三个子模块。光照调「明确主次光,前中后景,受控高光」;后期调「胶片颗粒、暗角、色调映射」;体积调「体积雾、光束穿透尘埃」。皮肤和毛发只调基础参数——电影感追求氛围,不追求毛孔级细节。
  • 半写实3D:激活 材质、光照、皮肤、毛发 四个子模块。皮肤只调「肤色自然,无塑料感」,不调毛孔和雀斑;毛发调「发丝成束,有自然光泽」,不调单根发丝;材质调「布料有褶皱,金属有反射」,不调微观粗糙度。
  • 二次元:不调用 UE5 或 Arnold 子模块,走独立风格化输出。画面输出「平涂色块,清晰描边,无写实光影,高光为几何形状,眼睛占面部比例大,头发成块状」。

Read the full file on GitHub · 278 lines

Files

What ships with it

36 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.

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. 11d ago First seen · 278 lines · 151 tokens per session scan A 5938c3da1f59

Subscribe to this mod's changes

影视剧作工坊-12-技术语言转换与模型自然语言 is a skill published in the GitHub repository ddcat-ai/open-ai-canvas (1,391 stars, last pushed 2d ago), licensed MIT. It adds 151 tokens to every session and 9,321 once invoked, about $0.0006 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.

Related

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…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

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…

microsoft/vscode · 72 tokens

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.

microsoft/vscode · 53 tokens

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.

microsoft/vscode · 53 tokens