Turns written dream descriptions into videos through an automated pipeline that connects to the JiMeng platform. You paste in dream journal entries or spoken dream recollections, it generates cinematic prompts following strict realism rules (no anime aesthetics, hardcore photography terminology, fish-eye lenses for spatial distortion), then spawns a worker that handles the browser automation, uploads reference images if your dream mentions company environments, monitors generation progress, and downloads the final 15-second video. The prompt engineering is opinionated and detailed, enforcing things like POV perspectives, no overlaid text, ethnicity tagging for background characters, and VHS-style glitch effects at frame edges. Setup requires Python 3.10+, Playwright, and a one-time QR code login to the platform.

skills.sh installs
231
GitHub stars
378
last updated
Jun 3, 2026

Install

$ npx -y skills add mediastormdev/dream-to-video-skill --skill dream-to-video --agent claude-code

Installs into .claude/skills of the current project.

Files

Dream-to-Video 梦境素材全自动视频生成

你负责将用户提供的梦境文字素材转化为视频提示词,并通过自动化工具链提交到即梦平台生成视频、下载到本地。用户只需要给你文字,你最终返回视频文件。


零、首次环境配置

当用户首次使用此 Skill 时,按以下流程自动配置环境。每一步执行后检查结果,全部通过后再告知用户可以开始使用。

路径约定

本文档中 {W} 代表本仓库的 clone 路径(即 dream_to_video/ 目录的父级)。

  • 项目目录:{W}/dream_to_video/
  • Skill 资源目录:{W}/skills/dream-to-video/

执行命令时,将 {W} 替换为实际路径。

自动执行(无需用户操作)

Step 0-0:克隆项目仓库 询问用户希望把项目放在哪个目录,然后执行:

cd "<用户指定的目录>" && git clone https://github.com/mediastormDev/dream-to-video-skill.git && cd dream-to-video-skill

clone 完成后的 dream-to-video-skill 目录即为 {W}。 如果用户说"就在当前目录",则在当前目录下 clone。

Step 0-1:检查 Python

python --version

要求 Python ≥ 3.10。如果未安装或版本过低,停下来提示用户:

请先安装 Python 3.10 或更高版本:https://www.python.org/downloads/ 安装时勾选「Add Python to PATH」。

Step 0-2:安装 Python 依赖

cd "{W}/dream_to_video" && pip install -r requirements.txt

Step 0-3:安装 Playwright 浏览器

playwright install chromium

这会下载 Chromium 浏览器引擎(约 150MB),用于自动操控即梦平台。

Step 0-4:创建必要目录

cd "{W}/dream_to_video" && mkdir -p output data auth/browser_profile reference_images/室内 reference_images/室外

Sponsors

Details

Repository
github.com/mediastormdev/dream-to-video-skill
First seen
Jun 3, 2026

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs