← Back to Skills Marketplace
826
Downloads
3
Stars
5
Active Installs
4
Versions
Install in OpenClaw
/install seedance-ai-video
Description
Generate AI videos using ByteDance's Seedance 1.5 Pro — a native audio-visual joint generation model with cinematic camera control, multi-language lip-sync,...
Usage Guidance
This skill appears to do what it claims: it sends prompts/images to api.atlascloud.ai and downloads generated videos, and it requires only your Atlas Cloud API key. Before installation: (1) Verify you trust https://www.atlascloud.ai and that your API key is created with appropriate billing/quotas — generation may incur charges. (2) Inspect the script if you plan to run it locally; the example model IDs in the script (alibaba/wan-2.6) differ from the SKILL.md (bytedance/seedance-v1.5-pro), so confirm the correct model ID you want to use. (3) Be cautious when using the upload command — it will upload local media to Atlas Cloud (the script prompts for confirmation by default). If any additional environment variables or unusual endpoints appear in future versions, treat that as a red flag.
Capability Analysis
Type: OpenClaw Skill
Name: seedance-ai-video
Version: 1.1.2
The skill is a legitimate integration for ByteDance's Seedance AI video models via the Atlas Cloud API (api.atlascloud.ai). The included Python script (scripts/generate_video.py) uses only standard libraries to handle API requests, polling, and file downloads/uploads, with clear logic and no evidence of obfuscation or malicious intent. Sensitive data handling is limited to the required ATLASCLOUD_API_KEY environment variable, and the instructions in SKILL.md are consistent with the stated purpose of video generation.
Capability Assessment
Purpose & Capability
The name/description (Seedance by ByteDance) aligns with a video-generation skill that calls api.atlascloud.ai. The script and SKILL.md both target Atlas Cloud model endpoints and require only ATLASCLOUD_API_KEY. Minor inconsistency: commented usage in scripts/generate_video.py shows example model IDs like alibaba/wan-2.6, while SKILL.md references bytedance/seedance-v1.5-pro — likely copy/paste but worth checking that the intended model IDs are available on Atlas Cloud.
Instruction Scope
SKILL.md and the script instruct only to send prompts, image URLs, and optionally upload local media to api.atlascloud.ai. The script reads only ATLASCLOUD_API_KEY from the environment and does not reference other system files, secrets, or unexpected remote endpoints. Uploads of local files require user confirmation by default.
Install Mechanism
No install spec — instruction-only plus a single Python script that uses only the standard library. Nothing is downloaded or executed from unknown remote URLs during install.
Credentials
Only ATLASCLOUD_API_KEY is declared and used; the script sends it in Authorization header to api.atlascloud.ai. This is proportionate for a cloud API client. The skill does not request unrelated credentials or config paths.
Persistence & Privilege
always is false and the skill does not request persistent system-level privileges. The skill does not modify other skills or system-wide settings.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install seedance-ai-video - After installation, invoke the skill by name or use
/seedance-ai-video - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.1.2
## seedance-ai-video v1.1.2
- Added a Python script (`scripts/generate_video.py`) to support video generation from the command line, with no external dependencies required.
- Updated documentation to include setup and usage instructions for the new script, including model listing, text-to-video, and image-to-video examples.
- Introduced a `metadata.openclaw.requires.env` field in the manifest for clear API key requirements.
v1.1.1
- Updated API polling endpoint in workflow instructions from `/result/{prediction-id}` to `/prediction/{prediction-id}` for accuracy.
- No functional or feature changes; documentation improvement only.
v1.1.0
update
v1.0.0
Initial release — AI video generation powered by ByteDance Seedance models.
- Generate short AI videos from text prompts or images, with synchronized native audio.
- Features multi-language lip-sync, cinematic camera control, and diverse video styles.
- Supports resolutions up to 720p and durations from 5–12 seconds per clip.
- Provides both "Pro" (high quality) and "Fast" (quick draft) model options.
- Includes detailed setup, API usage, and pricing guidance for Atlas Cloud integration.
Metadata
Frequently Asked Questions
What is Seedance 2.0 — AI Video by ByteDance?
Generate AI videos using ByteDance's Seedance 1.5 Pro — a native audio-visual joint generation model with cinematic camera control, multi-language lip-sync,... It is an AI Agent Skill for Claude Code / OpenClaw, with 826 downloads so far.
How do I install Seedance 2.0 — AI Video by ByteDance?
Run "/install seedance-ai-video" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Seedance 2.0 — AI Video by ByteDance free?
Yes, Seedance 2.0 — AI Video by ByteDance is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Seedance 2.0 — AI Video by ByteDance support?
Seedance 2.0 — AI Video by ByteDance is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Seedance 2.0 — AI Video by ByteDance?
It is built and maintained by MikeWang (@xixihhhh); the current version is v1.1.2.
More Skills