← Back to Skills Marketplace
aaronzoe

video-generator-seedance

by aaronzoe · GitHub ↗ · v1.0.1 · MIT-0
cross-platform ⚠ suspicious
848
Downloads
2
Stars
6
Active Installs
2
Versions
Install in OpenClaw
/install video-generator-seedance
Description
使用火山引擎 SD1.5pro API 生成视频。支持文本到视频和图生视频,异步处理任务。
Usage Guidance
Things to check before installing or running this skill: - Expect to provide a Volcengine API key and model ID via a local config.json (the registry metadata does NOT declare these). Do not paste keys into public/shared places. - Verify the service endpoint: the script posts to https://ark.cn-beijing.volces.com while the SKILL.md and README reference console.volcengine.com. Confirm that the hostname is legitimate (typo vs valid API host) with the vendor documentation before sending your API key. - Ensure Python and the 'requests' package are available in your environment (the skill does not declare dependencies). Run in a sandbox or isolated environment if you have doubts. - Review the full script contents (the distributed file was truncated here) to ensure there is no hidden network exfiltration or unexpected behavior. - Prefer to run with a minimal-permission API key (quotas/limits) and monitor network traffic the first time you use it. If the author can update the registry metadata to declare required credentials/config paths and document runtime dependencies and the endpoint is validated, the inconsistencies would be resolved and the risk lowered.
Capability Analysis
Type: OpenClaw Skill Name: video-generator-seedance Version: 1.0.1 The skill is a legitimate implementation for generating videos using the Volcengine (火山引擎) SD1.5pro API. The Python script `scripts/generate_video.py` follows standard practices for API interaction, including reading credentials from a local `config.json`, polling for task completion, and downloading the resulting file. No evidence of data exfiltration, malicious execution, or prompt injection was found; the hardcoded default output path to a Windows desktop is a usability choice rather than a security risk.
Capability Assessment
Purpose & Capability
The skill's code and SKILL.md clearly require a Volcengine API key and a config.json file with model ID, yet the registry metadata lists no required environment variables or config paths. A consumer would legitimately need those credentials/config, so the metadata is incomplete and incoherent with the declared purpose.
Instruction Scope
SKILL.md and the script limit actions to creating tasks on a remote API, polling task status, and downloading the resulting video to disk — all consistent with a video-generation skill. The instructions do require creating a local config.json containing an api_key and model, which is expected but is not reflected in the registry metadata.
Install Mechanism
This is an instruction-only skill with no install spec. No remote installers or archive downloads are used, which is low-risk. However, the script depends on Python and the 'requests' library but the skill does not document these runtime dependencies in the registry.
Credentials
The script requires a sensitive API key (api_key) stored in a local config.json, but the skill metadata declares no primary credential or required env vars. The missing declaration makes it unclear how credentials are expected to be provided and audited. The number and sensitivity of secrets (API key) are proportionate to the task, but the omission from metadata is a governance concern.
Persistence & Privilege
The skill does not request always:true or other elevated persistence. It runs as an invoked script and writes only the downloaded video file locally. No modifications to other skills or global agent settings are apparent.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install video-generator-seedance
  3. After installation, invoke the skill by name or use /video-generator-seedance
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
- No code or documentation changes detected in this version. - Functionality and usage remain the same as the previous release.
v1.0.0
- Initial release of Video-Generator-SeeDance skill. - Supports video generation via Volcano Engine SD1.5pro API with text-to-video and image-to-video modes. - Async task handling: polls for status and downloads generated video automatically. - Configuration via config.json for API key and model required on first use. - Multiple parameters supported (image, duration, output path, camera-fixed, watermark). - Detailed usage instructions, sample commands, and error handling guidance included.
Metadata
Slug video-generator-seedance
Version 1.0.1
License MIT-0
All-time Installs 7
Active Installs 6
Total Versions 2
Frequently Asked Questions

What is video-generator-seedance?

使用火山引擎 SD1.5pro API 生成视频。支持文本到视频和图生视频,异步处理任务。 It is an AI Agent Skill for Claude Code / OpenClaw, with 848 downloads so far.

How do I install video-generator-seedance?

Run "/install video-generator-seedance" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is video-generator-seedance free?

Yes, video-generator-seedance is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does video-generator-seedance support?

video-generator-seedance is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created video-generator-seedance?

It is built and maintained by aaronzoe (@aaronzoe); the current version is v1.0.1.

💬 Comments