Agent skill

Light Fresh Short Film

by JGRFW in JGRFW/comfyui-AICG3D

根据用户提供的人物、场景、剧情、参考画面或续写要求,直接生成5—30秒“光感小清新短片”视频提示词。固定输出整体场景与氛围、多分镜时间轴、画面风格、统一环境动态、统一环境音、负面提示词和语言锁,重点保证清透冷调、自然光感、人物细微状态与前后光线连续。

GPL-3.0Auto-check passedMedia & Creative

Install Light Fresh Short Film

skills CLI
$ npx skills add JGRFW/comfyui-AICG3D --skill light-fresh-short-film -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install JGRFW/comfyui-AICG3D light-fresh-short-film --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/JGRFW/comfyui-AICG3D.git skills-src && mkdir -p .claude/skills && cp -r skills-src/'skills/光感小清新skilllight-fresh-short-film-skill/light-fresh-short-film' .claude/skills/light-fresh-short-film && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
light-fresh-short-film
GitHub stars
187
Token cost
~926 tokens
SKILL.md length
148 words
Files
2
Skills in repo
6
Repo updated
First seen
Licence
GPL-3.0

At a glance

根据用户提供的人物、场景、剧情、参考画面或续写要求,直接生成5—30秒“光感小清新短片”视频提示词。固定输出整体场景与氛围、多分镜时间轴、画面风格、统一环境动态、统一环境音、负面提示词和语言锁,重点保证清透冷调、自然光感、人物细微状态与前后光线连续。

  • Tasks that involve AI video generation
  • SKILL.md covers 任务定位, 项目隔离, 核心词汇体系 and 光感连续规则, plus 9 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Light Fresh Short Film is an agent skill from JGRFW/comfyui-AICG3D. 根据用户提供的人物、场景、剧情、参考画面或续写要求,直接生成5—30秒“光感小清新短片”视频提示词。固定输出整体场景与氛围、多分镜时间轴、画面风格、统一环境动态、统一环境音、负面提示词和语言锁,重点保证清透冷调、自然光感、人物细微状态与前后光线连续。

Its SKILL.md is about 930 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `meta.yaml`).

It sits in Media & Creative, covering AI video generation. It works with ComfyUI. The repository describes itself as: 短剧工作台 | 无限时长视频的 MiniMax H3 工作流 | ComfyUI 本地短剧与长视频生成插件. The licence is GPL-3.0.

When your agent uses it

  • Tasks that involve AI video generation

Example prompts

  • “光感小清新短片”
  • “/light-fresh-short-film”

What it can do on your machine

Read from SKILL.md and the folder at commit d123f29. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Light Fresh Short Film loads about 926 tokens when it runs. Until then it costs about 37 tokens; SKILL.md has 148 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~37
When it runs · the whole SKILL.md, loaded when a task matches
~926

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from JGRFW/comfyui-AICG3D at commit d123f29, republished under its GPL-3.0 licence (© JGRFW). 148 words, ~926 tokens.

Download SKILL.mdSave it as .claude/skills/light-fresh-short-film/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
light-fresh-short-film
description
根据用户提供的人物、场景、剧情、参考画面或续写要求,直接生成5—30秒“光感小清新短片”视频提示词。固定输出整体场景与氛围、多分镜时间轴、画面风格、统一环境动态、统一环境音、负面提示词和语言锁,重点保证清透冷调、自然光感、人物细微状态与前后光线连续。

光感小清新短片

任务定位

根据用户当前提供的人物、场景、剧情、参考画面或续写要求,直接编写可用于视频生成的完整提示词。

重点表现:

  • 明亮清透的自然光感
  • 冷白中性的色彩关系
  • 发丝、皮肤、服装与环境表面的受光层次
  • 树影、光斑、浮尘、水面反光与空气流动
  • 人物真实、克制、可见的细微动作与表情变化
  • 轻剧情、弱叙事、慵懒、安静、青春、夏日气息

不进行前期询问,不输出剧情分析、创作解释和额外建议。信息不足时,只补充完成当前画面所必需的自然环境细节与生活化动作,不擅自加入新人物、强叙事道具或历史项目元素。

项目隔离

每次任务均视为独立项目。只使用当前任务明确出现的人物、服装、动物、道具、场景和事件。

禁止从其他项目自动继承人物关系、固定动物、拍立得、纸箱、旧照片、离别、回忆或其他具有强叙事意义的元素。续写当前短片时,只继承当前短片已经确认的资产与设定。

核心词汇体系

整条提示词必须持续使用同一组视觉词汇,不随意更换为冲突风格:

  • 强逆光发丝透光
  • 冷白银光
  • 高光柔晕但保留层次不死白
  • 高调通透明亮
  • 饱满浓郁冷调
  • 禁发黄
  • 2000s DV清透不褪色不做旧
  • 高光halation晕开
  • 浅焦光斑
  • 35mm颗粒柔焦
  • 低对比暗部不死黑
  • 暗部轻微提亮一档
  • 净化肤色去杂色
  • 收敛过度锐化
  • 明亮下藏着淡淡夏日哀愁

同一条提示词内,形容词、色彩词、光线词和成像词必须保持统一。不得突然转为暖黄金橙、灰蒙褪色、影棚平光、强锐高反差或廉价网感。

光感连续规则

同一段短片及其续写必须延续以下内容:

  • 时间与天气
  • 主光源方向
  • 顺光、侧光或逆光关系
  • 光线色温与强度
  • 高光halation程度
  • 暗部亮度
  • 肤色处理
  • 背景色彩倾向
  • 景深与柔焦程度
  • 风向与环境动态

前一镜头为冷白强逆光时,后一镜头不得无原因切换为暖黄顺光。前一镜头人物面部明亮通透时,后一镜头不得出现背景明亮、人物脸部灰暗。用户明确指定顺光、侧光或室内自然光时,只替换不适用的光线方向词,其余词汇体系与成像质感继续保持一致。

固定输出结构

严格按以下顺序输出:

text
[整体场景与氛围]

[多分镜时间轴]
实时速度,镜间硬切:
……

[画面风格]

[统一环境动态]

[统一环境音]

[负面提示词]

[语言锁]

[整体场景与氛围]

使用一段完整文字统一规定全片环境,不写具体分镜动作。必须明确:

  • 具体时间、天气与地点
  • 人物所在的具体空间位置
  • 主光源来源、方向和光质
  • 环境主要色彩
  • 空气中的光斑、浮尘、雾气、水面反光或树影
  • 画幅比例;用户未指定时默认16:9,明确要求电影宽银幕时使用21:9
  • 35mm胶片与2000s DV数码质感
  • 整体情绪

参考句式:

夏日午后日式庭院缘侧,强逆光从庭院方向大量涌入形成冷白银光,高光halation自然晕开,光斑在深色木质地板上缓慢流动,浮尘在逆光光束中漂浮,庭院绿意浓郁并虚化为柔软浅焦光斑。高调通透明亮,冷调中性绝不发黄,35mm胶片结合2000s DV数码质感,色彩饱满浓郁,低对比暗部不死黑,细腻胶片颗粒与轻微柔焦包裹淡淡夏日哀愁。

场景改变时替换地点、环境物和光源来源,不改变词汇体系与光感逻辑。

[多分镜时间轴]

标题统一写为:

text
[多分镜时间轴]
15秒实时速度,镜间硬切:

时长按用户要求替换。单镜头任务写“单镜头连续完成”;多镜头任务写“镜间硬切”。

每个镜头统一使用以下结构:

text
0—3秒|镜头一

景别与镜头运动:
明确景别、机位高度、拍摄方向和一种具体运镜。

画面、动作与表情:
明确人物、道具和环境的具体位置;按发生顺序写清动作;写清眼神、眉眼、嘴角、呼吸、手指和身体重心的变化。

光影表现:
明确光从哪个方向照来,具体落在人物面部、发丝、手部、服装、道具和环境的什么位置,并写清高光、阴影、光斑和肤色层次。
时间与镜头数量
  • 5—6秒:1个连续镜头,或2个动作明确的短镜头
  • 15秒:通常3—5个镜头
  • 30秒:通常8—10个镜头;生成模型需要分段时拆为两段15秒
  • 不机械平均分配时间,按动作完成速度安排切镜
  • 切镜只使用硬切,不使用溶解、叠化和淡入淡出
镜头编写规则
  • 每个镜头只完成一个核心动作或一个明确的情绪变化
  • 动作必须能在对应秒数内按实时速度自然完成
  • 相邻镜头避免重复景别、机位、人物姿态和动作功能
  • 不连续堆叠正面人物近景
  • 空境必须展示具体环境运动或光影变化,不能只写普通风景
  • 人物、服装、道具和空间位置不得无原因改变
  • 续写时先排除已有镜头中的重复动作、重复构图和重复空境
  • 前后段衔接时,明确保留人物位置、身体朝向、手中道具、光源方向和环境状态
动作写法

动作必须使用明确顺序:

女孩先将透明玻璃杯放在木地板上,停顿半秒,再用右手缓慢顺时针旋转杯身。折射光斑随杯子转动左右晃动。她停止旋转后,右手指尖仍轻轻扶住杯沿。

不得只写“女孩玩杯子”“女孩自然互动”。

表情写法

表情必须写成可见变化:

女孩先低头看向地板上的光斑,眼神轻微放空;光斑开始移动后,她的视线缓慢跟随,眼尾逐渐放松,嘴角出现极浅的笑意,随后恢复自然安静的状态。

表情按照“起始状态—触发原因—眼神变化—眉眼与嘴角变化—最终停留”书写。禁止只写“开心、温柔、难过、惆怅”。

[画面风格]

此栏直接沿用以下原始词汇体系,可根据当前场景删除明显不适用的部分,但不得改写成另一套风格语言,也不得打乱核心词序:

强逆光发丝透光、高光柔晕但保留层次不死白 / 高调通透明亮 / 饱满浓郁冷调(禁发黄,2000s DV清透不褪色不做旧)/ 高光halation晕开 / 浅焦光斑 / 35mm颗粒柔焦 / 明亮下藏着淡淡夏日哀愁。视频肤色:暗部轻微提亮一档、净化肤色去杂色、收敛过度锐化。

用户明确要求顺光时,仅将首项替换为:

明亮冷白顺光、面部均匀受光、高光柔晕但保留层次不死白

用户明确要求侧光时,仅将首项替换为:

冷白侧光塑造面部层次、发丝边缘透光、高光柔晕但保留层次不死白

其余词汇和顺序保持不变。

[统一环境动态]

集中写全段环境运动,不在每个镜头中重复。

必须明确:

  • 风从哪个方向吹来
  • 树叶、发丝、裙摆、窗帘或纸签如何移动
  • 光斑和树影如何移动
  • 浮尘、水珠、海浪、玻璃反光如何变化
  • 所有动态保持同一方向、同一风力和真实速度

参考句式:

微风从庭院方向持续吹向缘侧,树叶保持轻缓低幅度晃动,人物额前碎发、发尾和裙摆随同一方向自然起伏;树叶间隙投下的碎光在人物面部与木质地板上缓慢移动,浮尘持续在逆光光束中漂浮,玻璃杯壁冷凝水缓慢下滑。禁止突然加速、剧烈摆动和无风自动运动。

[统一环境音]

只写当前画面真实存在的环境声和动作声。根据场景选择:

  • 蝉鸣
  • 风声
  • 树叶摩擦声
  • 海浪声
  • 风铃声
  • 木地板轻响
  • 衣料摩擦声
  • 玻璃杯轻响
  • 脚步声
  • 自然呼吸声

统一结尾:

镜头硬切时环境声连续衔接,不随画面切换中断。无对白,无旁白,无背景音乐,无配乐。

[负面提示词]

保持简洁、精确,统一使用:

人物呆站不动、僵硬摆拍、对镜甜笑、多光源均匀补光、面部过曝或暗沉、背景亮人物黑、整体发黄金橙、塑料感皮肤、廉价CG感、人物变形、多余人物、文字水印、字幕、溶解叠化、淡入淡出、背景音乐与配乐。

[语言锁]

默认使用:

本片无对白,模型禁止自主补充任何语种台词、字幕、文字与口型。

只有用户明确要求人物对白时,才根据用户提供的具体台词修改;不得自主创作对白。

续写规则

用户要求续写、增加镜头或修改局部镜头时,默认继承当前短片已经确认的:

  • 人物身份与外貌
  • 服装
  • 场景与空间结构
  • 道具
  • 时间与天气
  • 光源方向与色温
  • 画面风格词汇
  • 环境动态与声音

续写必须优先增加新的动作功能、空间角度和光影细节,避免重复已有的吃东西、坐着看远处、面部微笑、触摸动物、树叶空境和原姿态收尾。

修改单个镜头时,只重写用户指定的镜头;未被指出的镜头、资产与风格保持不变。

© JGRFW, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in skills/光感小清新skilllight-fresh-short-film-skill/light-fresh-short-film of JGRFW/comfyui-AICG3D.

  • SKILL.md
  • meta.yaml

Open the folder on GitHubat commit d123f29

Compare with similar skills

Light Fresh Short Film next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Light Fresh Short Film compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Light Fresh Short Film this skillJGRFW/comfyui-AICG3D187—~926Automated safety check: PassGPL-3.0
RunninghubHM-RunningHub/OpenClaw_RH_Skills142—~1.6kAutomated safety check: PassApache-2.0
ComfyUI Local DriverSlavaSexton/ComfyUI-Agent-Kit105—~12kAutomated safety check: PassApache-2.0
VRGDG H3 Short Film Pipelinevrgamegirl19/comfyui-vrgamedevgirl765—~4.2kAutomated safety check: PassCustom licence
MiniMax H3 Video DirectorTFboy1/oh-my-minimaxh3-director143—~2.4kAutomated safety check: PassMIT
H3 Videoagent-next/video-agent120—~2.9kAutomated safety check: PassApache-2.0

Similar skills

  • Runninghub

    HM-RunningHub/OpenClaw_RH_Skills

    Generate images, videos, audio, and 3D models via RunningHub API (420 endpoints) and run any RunningHub AI Application (custom ComfyUI workflow) by webappId.

    142 GitHub stars~1.6k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed
  • ComfyUI Local Driver

    SlavaSexton/ComfyUI-Agent-Kit

    Drives a local ComfyUI install over its HTTP API to generate and edit images, video and audio, with per-model prompt recipes and workflow guidance.

    105 GitHub stars~12k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed
  • VRGDG H3 Short Film Pipeline

    vrgamegirl19/comfyui-vrgamedevgirl

    Builds an AI short film in a local ComfyUI with the VRGDG Video Builder, MiniMax H3 scenes, reference images, a music score, QA and a final edit.

    765 GitHub stars~4.2k tokensUpdated yesterday
    Media & CreativeAuto-check passed
  • MiniMax H3 Video Director

    TFboy1/oh-my-minimaxh3-director

    Turns a script into a storyboard, assigns MiniMax H3 workflows in ComfyUI, monitors batch generation and builds a Jianying draft of the finished video.

    143 GitHub stars~2.4k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed
  • H3 Video

    agent-next/video-agent

    OpenVideo skill (v0.1.0): generate high-quality local video with the OpenVideo product (MiniMax H3 backend).

    120 GitHub stars~2.9k tokensUpdated yesterday
    Media & CreativeAuto-check passed
  • Krea in ComfyUI

    SlavaSexton/ComfyUI-Agent-Kit

    Helps choose and wire Krea models in ComfyUI: the hosted Krea 2 API nodes versus local open weights, FLUX.1 Krea Dev, and add-on packs for ControlNet and editing.

    105 GitHub stars~2.8k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed

More from JGRFW/comfyui-AICG3D

  • Eastern Megastructure Director

    JGRFW/comfyui-AICG3D

    为 Midjourney V8.2 设计、精简、分析和修正东方巨构、白玉京、天宫仙境与东方巨景提示词,并把完成图片转为约5秒的稳定图生视频提示词。支持一句话或关键词造景、参考图构图转译、多个主题发散、生成结果诊断、机位焦段修正、建筑丰富度与中式纯度控制、英文MJ生成失败修复,以及云海缓慢翻涌的视频动态。用于“写天宫提示词”“设计东方巨构全景”“参考图片生成同类画面”“分析为什么不够宏大”“建筑太…

    187 GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed
  • Short Scene Director Lite

    JGRFW/comfyui-AICG3D

    将参考图、单个简单剧情、简短场景想法或已有提示词整理成最长15秒的中文电影感视频生成提示词。用于基础文生视频、图生视频、一镜到底、两至三个镜头、动作时间线、简单运镜、光影色调、声音设计和局部修改;优先保证事件明确、动作可执行、时序连续和生成稳定。不用于完整剧本、长篇分镜、整部短剧、广告策划、角色设定或复杂世界观开发。

    187 GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • 将主题、情绪、故事或参考图片转化为具有电影叙事感的超现实图像提示词,并在用户上传生成结果后,继续输出默认约5秒、单镜头、不切镜的图生视频提示词。默认提供中文通用提示词与Midjourney提示词两套版本。

    187 GitHub stars~2.1k tokensUpdated yesterday
    Auto-check passed
  • High Density Fight Prompt

    JGRFW/comfyui-AICG3D

    根据参考图和用户设定创作高密度、连续因果的电影级打斗视频提示词,并输出保持同一时间线的中文导演稿与 MiniMax H3 Ref2VA 英文六段稿。适用于 15 秒动作设计、武器战、徒手战、巨物战和参考图驱动的连续攻防。

    187 GitHub stars~590 tokensUpdated yesterday
    Auto-check passed
  • Phone Vlog

    JGRFW/comfyui-AICG3D

    将用户的生活主题、人物资产、道具资产与场景信息,整理成30秒以内、可直接用于AI视频生成模型的真实手机自拍Vlog提示词。强调真实手机拍摄逻辑、自然表演、生活碎片、现场收音、资产一致性与设备不穿帮。

    187 GitHub stars~2.2k tokensUpdated yesterday
    Auto-check passed

Works with

Questions about Light Fresh Short Film

What does Light Fresh Short Film do?

根据用户提供的人物、场景、剧情、参考画面或续写要求,直接生成5—30秒“光感小清新短片”视频提示词。固定输出整体场景与氛围、多分镜时间轴、画面风格、统一环境动态、统一环境音、负面提示词和语言锁,重点保证清透冷调、自然光感、人物细微状态与前后光线连续。. Light Fresh Short Film is an agent skill from JGRFW/comfyui-AICG3D.

When should I use Light Fresh Short Film?

Light Fresh Short Film fits situations like: tasks that involve AI video generation.

How do I install Light Fresh Short Film in Claude Code?

Run `npx skills add JGRFW/comfyui-AICG3D --skill light-fresh-short-film -a claude-code`. Or copy the skill folder (skills/光感小清新skilllight-fresh-short-film-skill/light-fresh-short-film in JGRFW/comfyui-AICG3D) into .claude/skills/light-fresh-short-film in your project. Claude Code loads it when a task matches its description.

How do I install Light Fresh Short Film in Codex?

Run `npx skills add JGRFW/comfyui-AICG3D --skill light-fresh-short-film -a codex`. Or copy the skill folder (skills/光感小清新skilllight-fresh-short-film-skill/light-fresh-short-film in JGRFW/comfyui-AICG3D) into .agents/skills/light-fresh-short-film in your project. Codex loads it when a task matches its description.

Can I use Light Fresh Short Film in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add JGRFW/comfyui-AICG3D --skill light-fresh-short-film -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/light-fresh-short-film, .gemini/skills/light-fresh-short-film, .github/skills/light-fresh-short-film and .opencode/skills/light-fresh-short-film in your project.

What does Light Fresh Short Film need to run?

SKILL.md names no scripts, command-line tools or credentials: Light Fresh Short Film is instructions for the agent only.

Does Light Fresh Short Film access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Light Fresh Short Film safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Light Fresh Short Film use?

Light Fresh Short Film is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Light Fresh Short Film use?

About 926 tokens (SKILL.md is roughly 3.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Light Fresh Short Film?

Skills that share tags, products or a category with Light Fresh Short Film: Runninghub (HM-RunningHub/OpenClaw_RH_Skills, 142 stars), ComfyUI Local Driver (SlavaSexton/ComfyUI-Agent-Kit, 105 stars), VRGDG H3 Short Film Pipeline (vrgamegirl19/comfyui-vrgamedevgirl, 765 stars) and MiniMax H3 Video Director (TFboy1/oh-my-minimaxh3-director, 143 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Light Fresh Short Film?

JGRFW (a GitHub user) maintains it in JGRFW/comfyui-AICG3D, which has 187 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 10, 2026.

Source: JGRFW/comfyui-AICG3D on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.