seedance Skill (inference.sh) for Claude Code: What It Does and How to Install It

Lets Claude generate videos with ByteDance Seedance 2.0 through the inference.sh belt CLI, with synced audio and reference inputs.

Installs: 13K; on skills.sh
Stars: 17; on GitHub
Updated: Aug 2026; last repo commit

This skill makes Claude call 4 Seedance 2.0 apps with belt app run: standard, Fast, Studio and Studio Fast. It covers text-to-video, image-to-video, first and last frame control and reference-to-video, with synchronized audio, 4 to 15 seconds and up to 1080p.

It is a third-party skill, not published by ByteDance. It needs belt installed and signed in, and each run uses inference.sh credits.

Good for

Creators making social clips, music videos and product demos with sound
Marketers who need videos built from reference images, clips and audio

Install seedance

Claude Code

Copy this prompt.

Install the seedance skill in Claude Code. Run this command:

npx skills add https://github.com/inference-sh/skills --skill seedance

Then check that it loaded and tell me how to use it.

2
Paste it into Claude Code. It shows the change and asks before running it.

Requires Node.js.

Pick one route for the skill, then install the belt CLI with one of the belt routes and run belt login. Every command in SKILL.md is a belt app run call, and its allowed-tools line is Bash(belt *), so the skill does nothing without belt. The folder holds 1 file, SKILL.md (repo tree). It runs belt in a shell, so there is no Claude app upload route.

Built from the package data we hold. Not yet tested by us.

What's in the skill

When it loads

Generate videos with ByteDance Seedance 2.0 via inference.sh CLI. Unified model for text-to-video, image-to-video, and reference-to-video with synchronized audio, up to 1080p, 4-15s duration. Pro and Fast variants. Studio variants with private asset library for portrait consistency. Use for: social media videos, music videos, product demos, animated content, AI video with sound. Triggers: seedance, seedance 2, bytedance video, seedance t2v, seedance i2v, seedance r2v, video with audio, seedance 2.0, bytedance seedance, seedance studio

Sections in SKILL.md

Quick Start
Models
Modes
Examples
Text-to-Video with Audio
Fast Mode (Cheaper)
Image-to-Video
Image-to-Video with Start and End Frames
Multi-Image Reference
Video Editing (Replace Elements)
Video Extension (Stitch Clips)
Reference with Audio
Studio Mode (Portrait Consistency)
Product Ad with Multiple References
Prompt Guide
Parameters

Key facts

Author: inference.sh (owner of the repo; plugin.json lists inference.sh as author)
License: MIT per plugin.json and the README badge; the repo has no LICENSE file
Installs on skills.sh (101-skills/superpowers listing): 13,039 (Nov 2, 2026)
GitHub stars: 797 for the whole repo (Nov 2, 2026)
Last repo commit: Oct 15, 2026
Audits on skills.sh (101-skills/superpowers listing): Gen Agent Trust Hub: pass, Socket: warn, Snyk: pass
What it includes: 1 file: SKILL.md (from the repo tree)
Needs: The inference.sh belt CLI, signed in with belt login
Allowed tools: Bash(belt *)

What it includes

belt app run bytedance/seedance-2-0 with generate_audio
Set duration (4 to 15, or -1 for auto) and ratio.
Try: “Make a 10-second cinematic clip of waves crashing on rocks in a storm, with sound”
Runs code · Text-to-video with audio
bytedance/seedance-2-0-fast is quicker and limited to 720p
Also cheaper per the price table.
Runs code · Fast mode
Pass image to animate a still as the first frame
Add a prompt for the camera and motion.
Runs code · Image-to-video
Pass image and end_image to control start and end
end_image needs image.
Runs code · First and last frame
reference_images (9), reference_videos (3), reference_audios (3)
Refer to them in the prompt as Image 1, Video 1, Audio 1. Reference mode cannot mix with first and last frame.
Runs code · Multimodal reference
Replace elements in a reference video with a prompt
Formulas for add, remove and modify.
Runs code · Video editing
Extend forward or backward, or stitch several clips
Uses reference_videos with up to 3 clips.
Runs code · Video extension
bytedance/seedance-2-0-studio uploads references to BytePlus
SKILL.md says it uploads reference images to a private virtual portrait library for face consistency.
Runs code · Studio mode

From the official docs

Permissions

Medium risk

This skill makes your agent run belt app run commands that send your prompts and files to inference.sh and use credits on your account. Check the price of an app with belt app pricing before you start a large batch.

What it can do

Read your data
Create and change things
Delete things
Read-only mode

Watch out for

Each run uses inference.sh credits
SKILL.md lists Seedance 2.0 at $4.30 to $7.70 per million tokens and Fast at $3.30 to $5.60, with tokens = (width x height x fps x duration) / 1024. The belt README shows belt balance to check credits and belt app pricing to see the cost formula before a run. github.com
Your prompts and files go to inference.sh
Every belt app run sends its input to an inference.sh app. The belt README says local file paths in an input are uploaded by the CLI. Reference images, videos and audio you pass are inputs to the app. github.com
Studio variants upload your reference images to BytePlus
SKILL.md says the Studio and Studio Fast apps automatically upload reference images to the BytePlus private virtual portrait library. Use the standard or Fast app if you do not want faces uploaded there. github.com
You must install the belt CLI first
The belt README gives a download-and-review install script, Homebrew, npm and Scoop. cli-install.md in the repo says the installer downloads a binary and checks its SHA-256 checksum. The belt skill named in SKILL.md can also run brew install and npm install -g. github.com

Security advisories

No published security advisories as of Nov 2, 2026.

Technical details

Turning on read-only	SKILL.md describes no read-only mode.
Talks to	inference.sh (belt app run calls). cli.inference.sh and dist.inference.sh (belt installer)
Sign-in and keys	Run belt login to sign in to inference.sh. SKILL.md does not say where belt keeps the login.
Scopes	Runs belt app run commands in your shell (allowed-tools: Bash(belt *)) Uploads the inputs you give it, including local files, to inference.sh

Questions

What does the seedance skill do?

It makes Claude generate videos with ByteDance Seedance 2.0 through the inference.sh belt CLI. It supports text-to-video, image-to-video, first and last frame control and reference-to-video with synchronized audio, up to 1080p.

How do I install it?

Use the install box at the top of this page for the skill. You also need the belt CLI from inference.sh, installed with one of the belt routes in the box, and a belt login. There is no Claude app upload route because the skill runs belt in a shell.

Does it need an account or API key?

It needs an inference.sh sign-in through belt login. SKILL.md names no separate API key. SKILL.md lists Seedance 2.0 at $4.30 to $7.70 per million tokens and Fast at $3.30 to $5.60, where tokens = (width x height x fps x duration) / 1024.

Is it safe?

It runs belt app run commands through your shell. Each run sends your prompt and any files or URLs you give it to inference.sh and uses credits. The belt CLI has to be installed first, so read its install steps before you run them.

Is this a ByteDance skill?

No. It is not published by ByteDance. The repo owner is inference-sh, and its plugin.json names inference.sh as author. The skill calls the bytedance/seedance-2-0 apps on inference.sh.

Who publishes this skill?

inference.sh, in its own repo github.com/inference-sh/skills. The repo's plugin.json lists inference.sh as author and https://inference.sh as homepage.

Is there another copy of this skill?

skills.sh also lists this skill under 101-skills/superpowers, a repo whose plugin.json names inference.sh as author and inference-sh/skills as the repository. This page links to inference-sh/skills, the repo the plugin.json points to.

Which Seedance variant should I use?

SKILL.md describes Seedance 2.0 as best quality up to 1080p, Fast as quicker and up to 720p, and the Studio variants as adding a private asset library for portrait consistency.

How much does a video cost?

SKILL.md prices Seedance 2.0 at $4.30 to $7.70 per million tokens and Fast at $3.30 to $5.60, depending on resolution and input type. Tokens are (width x height x fps x duration) / 1024.

Which other skills does it point to?

Its Related Skills section lists infsh-cli, ai-video-generation, google-veo, ai-image-generation and ai-avatar-video from inference-sh/skills. They are optional.

Information

updated Nov 2, 2026

Repository: inference-sh/skills
Folder: tools/video/seedance

inference-sh/skills skills.sh

Sources

Docs, issue trackers and discussions this page is built from.

Show all 6

seedance SKILL.md · github.com
belt CLI README · github.com
cli-install.md · github.com
README · github.com
plugin.json · github.com
belt skill SKILL.md · github.com