Home / 62656456 / ai-film-skills · GitHub

epic-design SKILL.md skillA

epic-design 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/epic-design@git:20260928.f691a6f

Pins git:20260928.f691a6f 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/epic-design/SKILL.md
Versions recorded: 5
Latest version: git:20260928.f691a6f, committed Sep 28, 2026
First version recorded: Aug 16, 2026
Size: 4,253 bytes
Repository stars: 117
License: Apache-2.0

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。.

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

# 史诗类型视觉设计预设

从当前人物、行动、关系或空间信息决定类型如何帮助表达。保留既有的镜头、色彩、空间、动作、材质与声音能力；色表和场景例按需要采用，不覆盖用户的故事、资产、成像方式或已锁摄影。

## 按任务取用

| 当前任务 | 读取与执行 |
|---|---|
| 只问色值、场景预设、来源或接口 | 读下方对应资料的相关部分，直接回答；不扩成整套设计 |
| 新画面、整体视觉改写或整体图像诊断 | 读 [画面关系判断](references/cinematic-image-direction.md)；需要类型备选时读 [视觉预设库](references/genre-presets.md) |
| 只改已定画面的一个问题 | 先读当前成品与锁定项；只补影响该问题的资料，复核修改区域及必要衔接，不重开整体候选 |
| 分镜/视频的类型适配、动作/连续性/声音或结构化交接 | 读 [执行合同](references/COMMON-12-SECTION-PROTOCOL.md) 中适用部分；新视觉方向另读画面关系，已有摄影直接继承 |
| 需要定位具体失败 | 按问题查 [反面案例](references/NEGATIVE-CASE-BOOK.md)，不默认把十条全部套进成品 |
| 需要说明预设来源或证据等级 | 读 [来源账本](references/SOURCE-LEDGER.md)；普通设计不重复联网追溯已收录规则 |

同一上下文已完整读取且未变的资料复用；任务变化只补相关部分。每个包独立自足，不读取兄弟技能、旧版本或个人知识库。

## 先确定画面，再选择类型手法

从现有输入确定本轮媒介、观看目的、主体/环境关系、成像方式、允许变化和用户锁定项。缺口只有实质改变结果且无法合理推导时才问；已给剧本按实际覆盖的正文理解人物目的与当前状态，不能仅凭类型词补剧情。

- 摄影、构图、光色、材质共同服务观看顺序。固定或复合运镜按行动选择，不把“宏大”“压迫”“浪漫”等词机械换成固定焦段、配色、慢推或航拍。
- 静态画面只容纳同一时刻可共存的信息。视频再处理时间、触发、路径、声音与尾态；分镜请求交镜头设计，提示词请求才编译生成正文。
- 局部修订保留未涉及的人物、外观、数量、动作结果、台词、镜序与摄影；参考图只承担用户指定职责，不自动改变故事或成像方式。
- 光源可在画外，位置与受光可解释；世界规则允许的超自然光有其依据。新物、真实塑料、动画或插画均按目标处理，不强制磨损、雾、湿面或摄影写实。
- 数值用于已给约束、明确设计选择或真实执行需要；没有依据时描述可见关系，不编造色温、暗部占比或成功率。

## 直接交付与接口
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add 62656456/ai-film-skills/epic-design@sha256:b73ddd4b29a56f8e

The line at the top of this page pins the label git:20260928.f691a6f, 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](https://markdownregistry.com/badge/art_gcrornrf7xwxkdwt.svg)](https://markdownregistry.com/a/art_gcrornrf7xwxkdwt)

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

Versions

The registry has recorded 5 versions of this file, between Aug 16, 2026 and Sep 28, 2026, about one every 11 days.

version	committed	commit	size	audit
git:20260928.f691a6f latest	2026-09-28	f691a6f	4,253 B	A	view · diff
git:20260907.7d5e0bc	2026-09-07	7d5e0bc	9,387 B	A	view · diff
git:20260901.b714edf	2026-09-01	b714edf	7,962 B	A	view · diff
git:20260816.4876bb2	2026-08-16	4876bb2	7,922 B	A	view · diff
git:20260816.fb58827	2026-08-16	fb58827	7,877 B	A	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 (4253 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_gcrornrf7xwxkdwt
GET https://markdownregistry.com/api/v1/resolve?ref=62656456/ai-film-skills/epic-design
GET https://markdownregistry.com/api/v1/blob/b73ddd4b29a56f8e53fa449ab3a00cfc4dfe2d211dca5886be8a93dbb26c3ea2

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…