scene-asset

scene-asset is a skill for Codex from 62656456/ai-film-skills. It costs 129 tokens per session (6,328 once invoked), scanned A, original, Apache-2.0.

A scene-reference image generator that turns a described place or environment into a structured asset brief and image-generation task.

In plain words
What is it for?
Use it to define reusable scene assets, generate reference-image instructions, record locked features, and prepare prompts for supported image or video workflows.
Why use it?
It helps keep locations, materials, lighting, perspective, and approved visual details consistent across later images and video.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it to define reusable scene assets, generate reference-image instructions, record locked features, and prepare prompts for supported image or video workflows.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/62656456/ai-film-skills/scene-asset
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 62656456/ai-film-skills --skill scene-asset
Clone the repo
git clone --depth 1 https://github.com/62656456/ai-film-skills

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 scene-asset

README.md
[![agentmods](https://agentmods.dev/badge/skills/62656456/ai-film-skills/scene-asset/github.svg)](https://agentmods.dev/skills/62656456/ai-film-skills/scene-asset)
Your own site
<a href="https://agentmods.dev/skills/62656456/ai-film-skills/scene-asset"><img src="https://agentmods.dev/badge/skills/62656456/ai-film-skills/scene-asset/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 scene-asset

Your own site · 80×15
<a href="https://agentmods.dev/skills/62656456/ai-film-skills/scene-asset"><img src="https://agentmods.dev/badge/skills/62656456/ai-film-skills/scene-asset.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 129 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,328 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 $0.00129 $0.06328
Opus 5.5 $0.00052 $0.02531
Sonnet 5.5 $0.00026 $0.01266
Haiku 4.5 $0.00013 $0.00633

Measured 19d ago against content hash 900902c53eb5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

scene-asset 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 19d 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.

skills/scene-asset/SKILL.md · 236 lines

How it starts

The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.

场景资产参考图生成预设

当前包已经包含全部运行规则、参数依据和质量门;不使用未经用户确认的人脸或生物特征。

0. 加载规则与映射表

先确定本次媒介与改动范围。首次建立或重设计资产按下方剧本依据、描述、状态、材质/光影/几何和适用模板完成;局部修改只执行受影响部分,编号/文件查询直接回答。同一上下文已完整读取且未变的材料复用,不为改一处重新跑全流程。资产编号:S01–S99,已确认编号不得复用。

节 独立输出 用途
1–5 空间描述、锁定规则 确定地理和可拍性
6–7 平台任务与提示词字段 直接生成参考图
8–9 验收和防崩 独立质量检查
10 JSON 合同 供后续制作直接读取
11 类型适配字段 注入成片提示词的对应段落

剧本先行与设计依据

首次建立或重新设定资产且用户提供剧本时,通读所提供的完整正文,理解世界规则、身份关系、剧情因果和时间线,再回到资产出现的场次设计。长剧本可分段读完并留简短连续性记录。局部修订复用本轮已读且未变的依据,只补读受影响原文、当前场次与必要前后状态;跨上下文或源文本变化时核对实际来源。不能只搜名称或读摘要就声称通读;只有片段时说明覆盖范围,未给剧本时依据当前描述设计。

内部保留简短设计依据:正文来源与阅读范围、相关场次、故事风格与成像方式、已确认事实、设计推定、关键未知。设计要能解释“为什么这个资产在此时此地是这个样子”;后文信息可帮助理解时代、身份与伏笔,但不能把后续损坏、受伤、天气或揭示结果提前带入当前场次。

用户与当前项目已经明确的画风优先;未指定成像方式时默认摄影写实,以可信结构、材质和光影呈现。悬疑、喜剧、奇幻等故事类型不自动等于某种画风。未提供细节或参考图时,从剧本与用途主动提出合理设计;影响剧情、身份、既有锁定事实的关键未知才需确认。一般颜色、材料、陈设、维护与使用细节可作有依据的设计推定,不一律退回待确认;推定不能冒充原文或用户已确认事实。

交付与成像模式

常规新场景或完整场景设计默认交付一张主图+一张反打图,共两张独立图片;提示词阶段对应交付这两张的设计/提示词。用户明确只要单图、某个角度、局部修订或指定其他数量/版式时按该要求,不补齐套餐。九宫格及超出这两张的多机位,只在用户提出需要时展开,不能因为房间复杂或技能具备能力就自动添加。

  • 提示词/设计说明:交付当前请求的完整提示词、必要锁定信息与资产合同;尚未生成的参考图用空列表并标为计划,不填写虚构图片路径或声称图片通过。
  • 实际参考图:用户要求出图且有可用能力时按上述数量生成;常规设计先形成主图,再以同一布局和主图美术派生反打。实际看图后记录检查结果,用户批准前保持 pending_review;不把交付两张图片误做成未经要求的双格拼图。
  • 按需扩展机位:只有用户提出更多角度、九宫格或复杂空间覆盖时,才读取并执行 同空间多机位设计 的扩展部分。九宫格是同一空间的九个机位,不是九种装修、九个地点或单张裁切九次。一张九宫格算一张图,九张独立图片算九张,按用户要求交付;常规主图+反打不启动九机位规划。
  • 诊断/局部修改:围绕给定图或提示词指出可见问题、原因假设和对应修正;保留未点名的身份、风格与状态,不默认重做整套资产。

依第0节确定成像方式(无指定时默认摄影写实),再按本包 电影画面关系判断 设计画面关系与负向。新设计、整体改写或整体诊断读取此参考;局部修订仅补读相关判断,已读且未变时复用;编号/文件查询不必加载。模板中的多格、人物尺度、标准布光和材质纹理均按用途选取,不因模板固定成套、写实或宏大。

场景图还须区分用途:场景主图默认是有明确视点、视觉落点与光色气氛的电影环境画面;空间核对图在用户要求布局、反向、平面或结构核对时,优先交代对应空间。两者可以共享同一布局,但不要求主图把每个角落均匀照亮,也不把核对图强行做成戏剧暗场。单图请求只交所需一张;主图信息不足以核对的部分如实标未知,不自动加图。纯空场景的画面主体可以是空间、通道或光照区域,不靠加人、加事件制造电影感。

1. 描述维度表

设计依据按用途覆盖:空间类型与用途、时代/地点、使用者与活动状态、尺度、布局与必要设施、维护程度、材质、时间、天气、光照、色彩、空间层次、固定场景标志及使用痕迹。这些维度用于完成设计,不要求逐项印成清单或全部挤入提示词。

规则:按第0节区分剧本事实、设计推定与关键未知;只把用户或剧本已确认的维度写入 locked_features,待审设计不冒充已锁定。描述按从整体到局部、从外观到材质、从静态到状态组织,并对应当前剧情节点。

Read the full file on GitHub · 236 lines

Files

What ships with it

4 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. 19d ago Changed · +30 lines · +31 tokens per session 900902c53eb5
  2. 29d ago Changed 68ef6fdd3755
  3. 1mo ago Changed · +24 lines · +14 tokens per session ee713cacf6c4
  4. 1mo ago Changed · +10 lines c2341db79673
  5. 1mo ago Changed · +10 tokens per session 266d0f60155a
  6. 1mo ago First seen · 172 lines · 74 tokens per session scan A f30a9b27f792

Subscribe to this mod's changes

scene-asset is a skill published in the GitHub repository 62656456/ai-film-skills (92 stars, last pushed 9d ago), licensed Apache-2.0. It adds 129 tokens to every session and 6,328 once invoked, about $0.0005 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 2026-08-31.

Related

Other skills, from other repositories

seedance-20

This skill should be used when creating, improving, or troubleshooting Seedance 2.0 video on any surface — Dreamina, Jimeng, CapCut, Doubao, Volcengine/Ark, BytePlus, Runway's Seedance route, fal, or third-party provider/router surfaces such as EvoLink, OpenRouter, Kie.ai, PiAPI, LaoZhang, Runware, ModelsLab, AI/ML…

LeoYeAI/seedance-skills · 178 tokens

seedance-prompt

This skill should be used when the user asks to write, improve, translate, compress, or debug a Seedance 2.0 video prompt; mentions T2V, I2V, V2V, R2V, camera direction, prompt quality, or provides reference assets for a production-ready prompt.

LeoYeAI/seedance-skills · 68 tokens

miora-video-studio

A video-generation workflow for the Miora and WorkBuddy tools. It checks whether a video was really created by inspecting the saved file, rather than trusting a task response.

kangarooking/director-skills · 176 tokens

travel-skill

A production guide for realistic travel-promotion videos that combine authorised real footage with AI-generated shots.

kangarooking/director-skills · 142 tokens

action-fight-prompt

A guide for writing prompts for AI-generated action and fight videos. It breaks a scene into short timed sections and describes connected movements, camera work, visual continuity, and sound effects.

kangarooking/director-skills · 179 tokens

travel-photo-to-video

A workflow for turning real travel photographs into a storyboard and prompts for short AI-generated video shots. It keeps the photographs' subjects and locations consistent while suggesting restrained camera movement.

kangarooking/director-skills · 90 tokens