Video Generator

使用AI大模型根据文字、首尾帧图片或图片/视频/音频参考素材生成带对白和环境音的视频。适用于文生视频、图生视频、首尾帧过渡和多模态参考视频生成,通过 Deep Code Plus 试算积分、确认后上传素材并生成视频。

2,187 stars 228 forksImages, Video & Audio

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add lessweb/deepcode-cli --skill video-generator
Manual install
git clone --depth 1 https://github.com/lessweb/deepcode-cli.git /tmp/deepcode-cli
mkdir -p ~/.claude/skills
cp -r /tmp/deepcode-cli/packages/core/templates/skills/bundled/video-generator ~/.claude/skills/video-generator

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Video Generator

由 MiniMax H3 驱动,同步生成画面、对白与环境音。使用本技能目录中的 `scripts/video_generator.py`;需要 Python 3.10+,依赖安装命令为 `python3 -m pip install -r scripts/requirements.txt`。

所有用户可见说明、问题和选项使用用户的语言。

## 收集需求

- 整理用户的真实需求时,读取 [视频提示词编写指南](references/video-prompt-writing-guide.md) 并按指南扩写提示词,组织为 `integrated_multimodal_description`、`overall_soundscape`、`non_diegetic_music` 三个核心字段。沿时间线描述主体、动作、镜头、风格、对白与声音,保留用户原始对白、画面文字、语言及限制条件,不要擅自添加会改变意图的设定。
- 根据输入类型采用指南中的纯文本、首帧或首尾帧写法,首尾帧需添加对齐说明并描述连续变化路径;参考素材不能自动视为首尾帧。指南中的仅尾帧(L2VA)写法不适用于本脚本。
- 收集用户提到的本地文件路径或 HTTP(S) 素材直链,并确定每份素材的用途。网页链接不等于素材直链;含义不清时询问。
- 支持纯文本、首尾帧、参考素材三种输入。首帧可附加尾帧;不接受只有尾帧。首尾帧仅支持 JPG/JPEG、PNG、WEBP,每张不超过 10MB,宽和高均至少 300 像素。
- 参考素材最多为 **4 张图片 + 1 个视频 + 2 个音频**,每个文件不超过上传接口的 50 MiB 限制。首尾帧与任何参考素材互斥;冲突时让用户选择用途,不能静默丢弃素材。
- 平台积分有换算,**最终费用只能引用试算接口的 `credits`**。

## 确认比例、分辨率、时长和模式

用户已明确指定支持的比例、分辨率、时长或模式(tier)时直接采用。任何缺失项都必须用 `AskUserQuestion` 让用户选择并确认,合并询问缺失项,不得默默采用默认值。四项参数全部明确后才能试算。

比例选项必须同时包含方向符号和文字:`▭ 21:9(超宽横屏)`、`▭ 16:9(横屏)`、`▭ 4:3(横屏)`、`□ 1:1(正方形)`、`▯ 3:4(竖屏)`、`▯ 9:16(竖屏)`。还支持 `auto(自动比例,方向由模型决定)`,仅在用户明确选择自动时使用。若工具限制选项数量,展示最相关的几个,在题目中列出其余比例及方向供用户填写。分辨率选项为 `720p`、`1080p`。

时长支持 5–20 整数秒。模式选项为 `turbo`(10步推理,缩短渲染时间)或 `base`(20步推理,提升画质)。确认时长后,按实际时长完善提示词时间线,确保切镜时间在视频时长内,尾帧对齐时间与时长一致。

如果宿主agent没有名为 `AskUserQuestion` 的工具,使用宿主agent等价的交互提问工具;没有等价工具时直接提问并等待明确回复。缺失的选择和生成授权不能通过默认选项或等待超时代替。

## 试算与提交确认

在技能目录运行(将占位符替换为真实参数,使用正确的 shell 引号):
Read the full skill on GitHub

Details

Skill name
video-generator
Path
packages/core/templates/skills/bundled/video-generator/SKILL.md
License
MIT
Repo updated
13 November 2026

FAQ

What does the Video Generator skill do?

使用AI大模型根据文字、首尾帧图片或图片/视频/音频参考素材生成带对白和环境音的视频。适用于文生视频、图生视频、首尾帧过渡和多模态参考视频生成,通过 Deep Code Plus 试算积分、确认后上传素材并生成视频。

How do I install the Video Generator skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add lessweb/deepcode-cli --skill video-generator. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Video Generator popular?

It lives in lessweb/deepcode-cli, which has 2,187 GitHub stars and 228 forks.

Related skills

Deepcode Self Refer

2.2k

lessweb/deepcode-cli

Answers questions about Deep Code CLI itself — including features, configuration options, slash commands, Skills, MCP integration, permissions, notifications, session persistence, and troubleshooting. Use this when users ask how to configure or use Deep Code, how to set up an MCP server, configure notifications (such as Slack/Feishu), manage permissions, view available skills, understand slash commands, configure thinking mode, etc.

Software Development228

Image Generator

2.2k

lessweb/deepcode-cli

Generate or edit images from text and local files, image URLs, or data URLs through image API. Use when the user asks to create an image, generate from one or more reference images, combine styles or elements across references, or edit a marked region while blending the result into the original scene.

Images, Video & Audio228

Skill Digester

2.2k

lessweb/deepcode-cli

Reviews and improves another DeepCode skill's SKILL.md description field, and guides Agent Skill installation into user or project .agents/skills roots. Use when the user asks to digest a skill, install an Agent Skill, install a skill to user/project scope, or says "消化技能" or "安装 agent skill".

AI, LLMs & Agents228

Illustration Style

3.4k

Owl-Listener/designer-skills

Define an illustration style guide — visual language, colour usage, and application rules. Use when commissioning or standardising illustration. For icons, use `icon-system` (design-systems).

Images, Video & Audio447

Media Processing

2.2k

mrgoonie/claudekit-skills

Process multimedia files with FFmpeg (video/audio encoding, conversion, streaming, filtering, hardware acceleration) and ImageMagick (image manipulation, format conversion, batch processing, effects, composition). Use when converting media formats, encoding videos with specific codecs (H.264, H.265, VP9), resizing/cropping images, extracting audio from video, applying filters and effects, optimizing file sizes, creating streaming manifests (HLS/DASH), generating thumbnails, batch processing images, creating composite images, or implementing media processing pipelines. Supports 100+ formats, ha

Images, Video & Audio418

Self Host

1.6k

ajnart/self-host

Load when the person wants to run or own apps on their own machine, replace a subscription (Netflix, Google Photos, Dropbox, a password manager), or asks about anything already set up with self-host, such as "where is my movie app?".

Images, Video & AudioIn 2 lists71

Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.