scene-asset SKILL.md skillA

scene-asset from 62656456/ai-film-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add 62656456/ai-film-skills/scene-asset@git:20261009.35d071d

Pins git:20261009.35d071d in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
62656456/ai-film-skills
Path
skills/scene-asset/SKILL.md
Versions recorded
5
Latest version
git:20261009.35d071d, committed Oct 9, 2026
First version recorded
Sep 1, 2026
Size
22,715 bytes
Repository stars
117
License
Apache-2.0

根据剧本设计电影场景的美术、构图、光色与氛围,常规场景默认主图加反打图;按用户需要扩展同空间多机位或九宫格,无指定画风时默认摄影写实。用于场景资产、环境图、房间多角度和场景机位设定;输出静态参考图任务说明与资产合同, 本 Skill 独立完成静态参考图任务说明、空间锁定、审核字段、负向约束和可供后续制作直接读取的资产合同。.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# 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。
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add 62656456/ai-film-skills/scene-asset@sha256:900902c53eb529fd

The line at the top of this page pins the label git:20261009.35d071d, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_2l5gkiihbkll2wuv.svg)](https://markdownregistry.com/a/art_2l5gkiihbkll2wuv)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Sep 1, 2026 and Oct 9, 2026, about one every 10 days.

versioncommittedcommitsizeaudit
git:20261009.35d071d latest2026-10-09 35d071d 22,715 BA view · diff
git:20260928.f691a6f2026-09-28 f691a6f 15,284 BA view · diff
git:20260911.4a336282026-09-11 4a33628 14,567 BA view · diff
git:20260907.7d5e0bc2026-09-07 7d5e0bc 10,255 BA view · diff
git:20260901.b714edf2026-09-01 b714edf 8,450 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (22715 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

62656456/ai-film-skills · 117 stars · license Apache-2.0 · pushed 2026-11-06 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_2l5gkiihbkll2wuv
GET https://markdownregistry.com/api/v1/resolve?ref=62656456/ai-film-skills/scene-asset
GET https://markdownregistry.com/api/v1/blob/900902c53eb529fddab7275d76d037ee5fafad2832c9d56858e663e366424601

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from 62656456/ai-film-skills

guofeng-visual-director SKILL.md skill
62656456/ai-film-skills · experimental/guofeng-visual-director/SKILL.md · 为中国古风题材设计完整的视觉语言,并编写、优化或诊断图像提示词;覆盖人物服饰、建筑空间、器物陈设、色彩光线、构图、故事关键帧与系列连续性。用于古风视觉设计、古装电影美术、历史或架空古代场景、古风人像、古风视觉圣经及明确的古风出图请求。区分历…
v0.1.1 · audit A · 117 stars
hard-sci-fi-visual-director SKILL.md skill
62656456/ai-film-skills · experimental/hard-sci-fi-visual-director/SKILL.md · Script-first visual design for original hard-science-fiction worlds, scenes, film stills, visual bibles, nonhuman life…
git:20260928.f691a6f · audit A · 117 stars
whitebox-previs-executor SKILL.md skill
62656456/ai-film-skills · experimental/whitebox-previs-executor/SKILL.md · 在用户明确要求3D白模预演时,将已有视频提示词、镜头描述或分镜编译为可播放的机位与基础走位预演;创意镜头思路、方案讨论或Skill测试本身不触发渲染。动作密集打斗必须通过骨骼、武器约束、共享接触点和单动作门,否则拒绝或标为诊断,不用体块位移…
git:20260928.f691a6f · audit A · 117 stars
llms.txt llms.txt file
62656456/ai-film-skills · llms.txt
git:20260901.b714edf · audit A · 117 stars
ai-short-drama-production SKILL.md skill
62656456/ai-film-skills · skills/ai-short-drama-production/SKILL.md · 将 AI 短剧、漫剧、剧情短视频从故事意图独立编排为可控生产任务。适用于剧本钩子、人物/场景/道具资产、场面调度图、布光图、打戏、草图转镜头与生成前 QC;全部必要合同随本 Skill 打包。
git:20260928.f691a6f · audit A · 117 stars
ai-storyboard-director SKILL.md skill
62656456/ai-film-skills · skills/ai-storyboard-director/SKILL.md · 根据剧本与已定导演方案设计观看顺序、人物调度、电影摄影和剪辑,编写或修订分镜与视频提示词;支持创意镜头思路、打戏和运镜诊断。创意思路可单独交付或并列于主分镜,采用后才纳入;分镜、提示词与实际生成按当前阶段分别执行。
git:20261018.f1fee05 · audit A · 117 stars
character-asset SKILL.md skill
62656456/ai-film-skills · skills/character-asset/SKILL.md · 根据剧本与人物身份设计角色资产,固定三视图加中景;支持女性角色魅力、气质与肖像设计。用于人物、角色设计、人物设定、人物资产、女性魅力、character、角色图;输出静态参考图任务说明与资产合同, 本 Skill…
git:20260928.f691a6f · audit A · 117 stars
cyberpunk-design SKILL.md skill
62656456/ai-film-skills · skills/cyberpunk-design/SKILL.md · 赛博朋克类型视觉设计预设。触发词:赛博、霓虹、黑客、未来都市、义体。用于明确需要此类型的画面设计、图像/视频提示词、视觉参数查询与诊断;保留摄影、光色、空间、动作、材质、连续性及 style_route/style_module 接口。
git:20260928.f691a6f · audit A · 117 stars
d-data-analysis-semantic-layer SKILL.md skill
62656456/ai-film-skills · skills/d-data-analysis-semantic-layer/SKILL.md · 审核并版本化写入 D|数据分析知识语义层,只用于用户在看到正式报告和候选内容后明确回复“同意吸纳”“写入D”“加入数据分析知识库”“确认进入知识库”或“批准更新D”的场景。用于验证候选结论、来源、有效期、复查日期、冲突和历史版本;不得因“调…
git:20260928.f691a6f · audit A · 117 stars
d-official-market-analysis SKILL.md skill
62656456/ai-film-skills · skills/d-official-market-analysis/SKILL.md · 基于可验证的官方和权威来源分析影视、微短剧、漫剧、AI影视、网络动画与剧情短视频市场。用于“调用D”“用D分析”、题材趋势、平台对比、指标解释、项目市场评估与完整市场研究;按本次问题确定范围与交付,不把单项咨询自动扩成全市场报告。
git:20260928.f691a6f · audit A · 117 stars
director-agent SKILL.md skill
62656456/ai-film-skills · skills/director-agent/SKILL.md · Create, revise, or diagnose screenplays and develop director treatments or pre-storyboard decisions covering causality…
git:20261014.846dcaa · audit A · 117 stars
epic-design SKILL.md skill
62656456/ai-film-skills · skills/epic-design/SKILL.md · 史诗类型视觉设计预设。触发词:史诗、宏大、全景、奇观、帝国、王朝。用于明确需要此类型的画面设计、图像/视频提示词、视觉参数查询与诊断;保留摄影、光色、空间、动作、材质、连续性及 style_route/style_module 接口。
git:20260928.f691a6f · audit A · 117 stars

Every file in 62656456/ai-film-skills

Browse by kind, by grade A, or by owner.