Agent skill

Video Generation

Generates short videos from a structured JSON prompt, optionally guided by a reference image used as the first or last frame.

MITAuto-check passedMedia & Creative

Install Video Generation

skills CLI

$ npx skills add bytedance/deer-flow --skill video-generation -a claude-code

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

GitHub CLI

$ gh skill install bytedance/deer-flow video-generation --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/bytedance/deer-flow.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/public/video-generation .claude/skills/video-generation && 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/

Paste into Claude Code

Install the "video-generation" agent skill from https://github.com/bytedance/deer-flow/tree/main/skills/public/video-generation into .claude/skills/video-generation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "video-generation", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/bytedance/deer-flow/tree/main/skills/public/video-generation

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add bytedance/deer-flow --skill video-generation -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install bytedance/deer-flow video-generation --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/bytedance/deer-flow.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/public/video-generation .agents/skills/video-generation && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "video-generation" agent skill from https://github.com/bytedance/deer-flow/tree/main/skills/public/video-generation into .agents/skills/video-generation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "video-generation", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add bytedance/deer-flow --skill video-generation -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install bytedance/deer-flow video-generation --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/bytedance/deer-flow.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/public/video-generation .cursor/skills/video-generation && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "video-generation" agent skill from https://github.com/bytedance/deer-flow/tree/main/skills/public/video-generation into .cursor/skills/video-generation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "video-generation", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/bytedance/deer-flow.git --path skills/public/video-generation

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add bytedance/deer-flow --skill video-generation -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install bytedance/deer-flow video-generation --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/bytedance/deer-flow.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/public/video-generation .gemini/skills/video-generation && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "video-generation" agent skill from https://github.com/bytedance/deer-flow/tree/main/skills/public/video-generation into .gemini/skills/video-generation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "video-generation", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install bytedance/deer-flow video-generation

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add bytedance/deer-flow --skill video-generation -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/bytedance/deer-flow.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/public/video-generation .github/skills/video-generation && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "video-generation" agent skill from https://github.com/bytedance/deer-flow/tree/main/skills/public/video-generation into .github/skills/video-generation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "video-generation", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add bytedance/deer-flow --skill video-generation -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install bytedance/deer-flow video-generation --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/bytedance/deer-flow.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/public/video-generation .opencode/skills/video-generation && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "video-generation" agent skill from https://github.com/bytedance/deer-flow/tree/main/skills/public/video-generation into .opencode/skills/video-generation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "video-generation", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: video-generation
GitHub stars: 84k
Used in: 3 other repos
Token cost: ~1.4k tokens
SKILL.md length: 460 words
Files: 2 (incl. scripts)
Skills in repo: 23
Repo updated: Oct 10, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Generates short videos from a structured JSON prompt, optionally guided by a reference image used as the first or last frame.

Works in 4 steps: Understand Requirements → Create Structured Prompt → Create Reference Image (Optional when… → …
Asked to create or imagine a short video clip
SKILL.md covers Overview, Core Capabilities, Workflow and Video Generation Example, plus 3 more sections
Runs Python scripts from its folder; calls python; reaches api.minimaxi.com; needs GEMINI_API_KEY and MINIMAX_API_KEY

What it does

The agent starts by pinning down what the video should show: the subject, the style and mood, technical specs such as aspect ratio and lighting, and any reference image. It then writes a structured JSON prompt file into `/mnt/user-data/workspace/` and, when the image-generation skill is available, can create a reference image first. A single supplied image is used as the guiding frame of the video.

Generation runs through `scripts/generate.py`, called with a prompt file, an output file, optional reference images and an aspect ratio that defaults to 16:9. The skill tells the agent to call the script with its parameters rather than read its source. The worked example builds a short clip of a film's opening scene after searching for that scene online. The excerpt is cut off before the remaining example steps.

When your agent uses it

Asked to create or imagine a short video clip
Animating from a reference image used as the first or last frame
Writing a structured JSON prompt for a video model

Example prompts

“Generate a short video of a fox running through snowy woods at dawn.”
“Make a clip that starts from this product photo: ./assets/lamp.jpg.”
“Create a 16:9 video of a paper boat drifting down a rain-filled street.”

Requirements

Python to run `scripts/generate.py`

Workflow steps

4 steps, taken from the step headings in SKILL.md.

Understand Requirements
Create Structured Prompt
Create Reference Image (Optional when image-generation skill is available)
Execute Generation

What it can do on your machine

Read from SKILL.md and the folder at commit ab9920f. 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
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
- python
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
- api.minimaxi.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
- GEMINI_API_KEY
- MINIMAX_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Video Generation loads about 1.4k tokens when it runs. Until then it costs about 41 tokens; SKILL.md has 460 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~41
When it runs · the whole SKILL.md, loaded when a task matches: ~1.4k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from bytedance/deer-flow at commit ab9920f, republished under its MIT licence (© bytedance). 460 words, ~1,371 tokens.

Download SKILL.mdSave it as .claude/skills/video-generation/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.

name: video-generation
description: Use this skill when the user requests to generate, create, or imagine videos. Supports structured prompts and reference image for guided generation.

Video Generation Skill

Overview

This skill generates high-quality videos using structured prompts and a Python script. The workflow includes creating JSON-formatted prompts and executing video generation with optional reference image.

Core Capabilities

Create structured JSON prompts for AIGC video generation
Support reference image as guidance or the first/last frame of the video
Generate videos through automated Python script execution

Workflow

Step 1: Understand Requirements

When a user requests video generation, identify:

Subject/content: What should be in the image
Style preferences: Art style, mood, color palette
Technical specs: Aspect ratio, composition, lighting
Reference image: Any image to guide generation
You don't need to check the folder under /mnt/user-data

Step 2: Create Structured Prompt

Generate a structured JSON file in /mnt/user-data/workspace/ with naming pattern: {descriptive-name}.json

Step 3: Create Reference Image (Optional when image-generation skill is available)

Generate reference image for the video generation.

If only 1 image is provided, use it as the guided frame of the video

Step 3: Execute Generation

Call the Python script:

bash

python /mnt/skills/public/video-generation/scripts/generate.py \
  --prompt-file /mnt/user-data/workspace/prompt-file.json \
  --reference-images /path/to/ref1.jpg \
  --output-file /mnt/user-data/outputs/generated-video.mp4 \
  --aspect-ratio 16:9

Parameters:

--prompt-file: Absolute path to JSON prompt file (required)
--reference-images: Absolute paths to reference image (optional)
--output-file: Absolute path to output image file (required)
--aspect-ratio: Aspect ratio of the generated image (optional, default: 16:9)

[!NOTE] Do NOT read the python file, instead just call it with the parameters.

Video Generation Example

User request: "Generate a short video clip depicting the opening scene from "The Chronicles of Narnia: The Lion, the Witch and the Wardrobe"

Step 1: Search for the opening scene of "The Chronicles of Narnia: The Lion, the Witch and the Wardrobe" online

Step 2: Create a JSON prompt file with the following content:

json

{
  "title": "The Chronicles of Narnia - Train Station Farewell",
  "background": {
    "description": "World War II evacuation scene at a crowded London train station. Steam and smoke fill the air as children are being sent to the countryside to escape the Blitz.",
    "era": "1940s wartime Britain",
    "location": "London railway station platform"
  },
  "characters": ["Mrs. Pevensie", "Lucy Pevensie"],
  "camera": {
    "type": "Close-up two-shot",
    "movement": "Static with subtle handheld movement",
    "angle": "Profile view, intimate framing",
    "focus": "Both faces in focus, background soft bokeh"
  },
  "dialogue": [
    {
      "character": "Mrs. Pevensie",
      "text": "You must be brave for me, darling. I'll come for you... I promise."
    },
    {
      "character": "Lucy Pevensie",
      "text": "I will be, mother. I promise."
    }
  ],
  "audio": [
    {
      "type": "Train whistle blows (signaling departure)",
      "volume": 1
    },
    {
      "type": "Strings swell emotionally, then fade",
      "volume": 0.5
    },
    {
      "type": "Ambient sound of the train station",
      "volume": 0.5
    }
  ]
}

Step 3: Use the image-generation skill to generate the reference image

Load the image-generation skill and generate a single reference image narnia-farewell-scene-01.jpg according to the skill.

Step 4: Use the generate.py script to generate the video

bash

python /mnt/skills/public/video-generation/scripts/generate.py \
  --prompt-file /mnt/user-data/workspace/narnia-farewell-scene.json \
  --reference-images /mnt/user-data/outputs/narnia-farewell-scene-01.jpg \
  --output-file /mnt/user-data/outputs/narnia-farewell-scene-01.mp4 \
  --aspect-ratio 16:9

Do NOT read the python file, just call it with the parameters.

Show full SKILL.md (143 more words)Show less

Output Handling

After generation:

Videos are typically saved in /mnt/user-data/outputs/
Share generated videos (come first) with user as well as generated image if applicable, using present_files tool
Provide brief description of the generation result
Offer to iterate if adjustments needed

Notes

Always use English for prompts regardless of user's language
JSON format ensures structured, parsable prompts
Reference image enhance generation quality significantly
Iterative refinement is normal for optimal results

Providers (Gemini / MiniMax)

Provider credentials are read from the runtime environment, not embedded in the script. Do not put their values in prompt files or command-line arguments.

Auto-selected by environment variables (CLI unchanged):

GEMINI_API_KEY set → Gemini Veo (default, unchanged).
Only MINIMAX_API_KEY set → MiniMax video (/v1/video_generation, async 3-step poll/download).
Force with VIDEO_GENERATION_PROVIDER=gemini|minimax.

MiniMax overrides: MINIMAX_API_HOST (default https://api.minimaxi.com), MINIMAX_VIDEO_MODEL (default MiniMax-Hailuo-2.3). The first reference image is used as MiniMax first_frame_image. MiniMax ignores --aspect-ratio (it uses resolution/duration).

Files

SKILL.md and 1 other file (scripts) in skills/public/video-generation of bytedance/deer-flow.

SKILL.md
scripts/generate.py

Open the folder on GitHubat commit ab9920f

Used in 3 other repositories

We found 3 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 3 other GitHub owners. This page covers the copy in bytedance/deer-flow, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Video Generation 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.

Video Generation compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Video Generation this skillbytedance/deer-flow	84k	3 repos	~1.4k	Automated safety check: Pass	MIT	today
MoneyPrinterTurbo Video Generatorharry0703/MoneyPrinterTurbo	129k	—	~2.1k	Automated safety check: Warn	MIT	today
Vox DirectorAlisa0808/vox-director	2.2k	—	~5.6k	Automated safety check: Pass	MIT	4 days ago
Gbro Collage Brollpyang5166/gbro-collage-broll	1.3k	—	~2.6k	Automated safety check: Notes	MIT	2 mo ago
VRGDG H3 Short Film Pipelinevrgamegirl19/comfyui-vrgamedevgirl	765	—	~4.2k	Automated safety check: Pass	Custom licence	today
Forge Media Route Layer0x0funky/agent-sprite-forge	4.4k	—	~2.2k	Automated safety check: Pass	MIT	3 days ago

Similar skills

MoneyPrinterTurbo Video Generator
harry0703/MoneyPrinterTurbo
Installs and runs MoneyPrinterTurbo to turn a topic or script into a finished short video with voice-over, subtitles, stock footage and music.
129k GitHub stars~2.1k tokensUpdated today
Media & CreativeAuto-check: warnings
Vox Director
Alisa0808/vox-director
Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all…
2.2k GitHub stars~5.6k tokensUpdated 4 days ago
Media & CreativeAuto-check passed
Gbro Collage Broll
pyang5166/gbro-collage-broll
将约 5 秒口播文稿、观点句或抽象概念做成高级 editorial halftone paper-collage / 半调纸拼贴 B-roll。用户说“collage b-roll”“纸拼贴 b-roll”“半调拼贴”“拼贴风格配画面”“用这段文稿做拼贴动画”“gbro-collage-broll”，或希望把一句文稿转成拼贴视觉隐喻时，必须使用此…
1.3k GitHub stars~2.6k tokensUpdated 2 mo ago
Media & CreativeAuto-check: notes
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 today
Media & CreativeAuto-check passed
Forge Media Route Layer
0x0funky/agent-sprite-forge
Generates an image or an image-to-video clip through a configured provider API or a signed-in Codex or Grok CLI, and reports the route, file, hash and cost estimate.
4.4k GitHub stars~2.2k tokensUpdated 3 days ago
Media & CreativeAuto-check passed
Cassette Video Edit
Cassette-Editor/oh-my-cassette
Edit, trim, cut, caption, subtitle, reframe, combine, add background music to, or export video, audio, and image files through Cassette.
119 GitHub starsUsed in 1 repo~3.4k tokens
Media & CreativeAuto-check passed

Questions about Video Generation

What does Video Generation do?

Generates short videos from a structured JSON prompt, optionally guided by a reference image used as the first or last frame. The agent starts by pinning down what the video should show: the subject, the style and mood, technical specs such as aspect ratio and lighting, and any reference image. It then writes a structured JSON prompt file into `/mnt/user-data/workspace/` and, when the image-generation skill is available, can create a reference image first.

When should I use Video Generation?

Video Generation fits situations like: asked to create or imagine a short video clip; animating from a reference image used as the first or last frame; writing a structured JSON prompt for a video model.

How do I install Video Generation in Claude Code?

Run `npx skills add bytedance/deer-flow --skill video-generation -a claude-code`. Or copy the skill folder (skills/public/video-generation in bytedance/deer-flow) into .claude/skills/video-generation in your project. Claude Code loads it when a task matches its description.

How do I install Video Generation in Codex?

Run `npx skills add bytedance/deer-flow --skill video-generation -a codex`. Or copy the skill folder (skills/public/video-generation in bytedance/deer-flow) into .agents/skills/video-generation in your project. Codex loads it when a task matches its description.

Can I use Video Generation 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 bytedance/deer-flow --skill video-generation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/video-generation, .gemini/skills/video-generation, .github/skills/video-generation and .opencode/skills/video-generation in your project.

What does Video Generation need to run?

Going by SKILL.md and its folder, Video Generation needs Python for the scripts in its folder, the command-line tools its instructions call (python) and credentials named GEMINI_API_KEY and MINIMAX_API_KEY. Our summary lists: Python to run `scripts/generate.py`.

Does Video Generation access the network?

SKILL.md names 1 domain. In commands or code: api.minimaxi.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Video Generation 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Video Generation use?

Video Generation is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Video Generation use?

About 1.4k tokens (SKILL.md is roughly 5.5k 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 Video Generation?

Skills that share tags, products or a category with Video Generation: MoneyPrinterTurbo Video Generator (harry0703/MoneyPrinterTurbo, 129k stars), Vox Director (Alisa0808/vox-director, 2.2k stars), Gbro Collage Broll (pyang5166/gbro-collage-broll, 1.3k stars) and VRGDG H3 Short Film Pipeline (vrgamegirl19/comfyui-vrgamedevgirl, 765 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Video Generation?

bytedance (a GitHub organization) maintains it in bytedance/deer-flow, which has 83,611 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on October 10, 2026.

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

Install Video Generation

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Video Generation Skill

Overview

Core Capabilities

Workflow

Step 1: Understand Requirements

Step 2: Create Structured Prompt

Step 3: Create Reference Image (Optional when image-generation skill is available)

Step 3: Execute Generation

Video Generation Example

Output Handling

Notes

Providers (Gemini / MiniMax)

Files

Used in 3 other repositories

Compare with similar skills

Similar skills

More from bytedance/deer-flow

Related

Questions about Video Generation