← Back to Skills Marketplace
fuyunzhishang

Pixmind Video Generation

by Pixmind · GitHub ↗ · v1.3.0 · MIT-0
cross-platform ⚠ suspicious
138
Downloads
0
Stars
0
Active Installs
5
Versions
Install in OpenClaw
/install pixmind-video
Description
Generate AI videos via Pixmind API (text-to-video and image-to-video)
README (SKILL.md)

Pixmind Video Generation Skill

Generate AI videos using Pixmind. Supports text-to-video and image-to-video generation.

Note: The API endpoint aihub-admin.aimix.pro is the official Pixmind API gateway. Result URLs on chatmix.top are Pixmind's CDN for generated content.

When to use

  • User asks to generate or create a video
  • User wants to animate an existing image into a video
  • User requests video content from a text description

Prerequisites

  1. Register at pixmind.io
  2. Create an API key at pixmind.io/api-keys
  3. Set env PIXMIND_API_KEY with your key

API Details

Endpoint: POST https://aihub-admin.aimix.pro/open-api/v1/video/generate Auth: Header X-API-Key: {API_KEY} (from env PIXMIND_API_KEY)

Request Body (JSON)

Parameter Required Type Description
prompt Yes string Video description / prompt
model No string Model name
duration No number Video duration in seconds
aspectRatio No string Aspect ratio: 16:9, 9:16, 1:1
resolution No string Resolution: 1080p, 720p
generateType No string text2video (default) or img2video
imageUrl No string Reference image URL (required for img2video)

Usage

Use curl or the included helper script:

# Text to video (via curl)
curl -X POST https://aihub-admin.aimix.pro/open-api/v1/video/generate \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $PIXMIND_API_KEY" \
  -d '{"prompt": "ocean waves", "duration": 5, "aspectRatio": "16:9"}'

# Or use the helper script
node {baseDir}/video-generate.js --prompt "描述文字" --duration 5 --aspect-ratio 16:9

Task Status Polling

After generation, poll for results:

# Via curl
curl https://aihub-admin.aimix.pro/open-api/v1/task/\x3CTASK_ID> \
  -H "X-API-Key: $PIXMIND_API_KEY"

# Or use the helper script
node {baseDir}/task-status.js --task-id \x3CTASK_ID> --poll

Response Format

Generate response:

{"code": 1000, "data": {"taskId": 19401, "status": "processing"}}

Task status response:

{
  "code": 1000,
  "data": {
    "taskId": 19401,
    "status": "ready",
    "progress": 100,
    "videoUrl": "https://chatmix.top/...",
    "coverUrl": "https://chatmix.top/..."
  }
}
  • data.taskId — Use this to poll status
  • Status values: processingready (success)
  • On success: data.videoUrl contains the video URL, data.coverUrl has the cover image

Guidelines

  1. Always confirm the prompt and duration with the user before generating
  2. Default to text2video mode unless user provides a reference image
  3. Use 16:9 aspect ratio by default for video content
  4. If user provides a reference image, automatically use img2video mode
  5. Video generation takes longer than images — use --poll with appropriate interval
  6. After getting the task ID, poll until completion and return video URL
Usage Guidance
This skill appears to implement what it claims: it needs a Pixmind API key and uses it to call an API gateway to start video jobs and poll status. Before installing or using it: 1) Verify the API gateway (aihub-admin.aimix.pro) and CDN host (chatmix.top) are legitimate Pixmind endpoints by checking Pixmind's official docs or support — do not assume because SKILL.md says so. 2) Consider creating a dedicated/limited API key for third-party integrations so exposure is minimized. 3) Be aware the helper scripts print prompts and full JSON responses to stdout (these can end up in shell history or logs), so avoid running them in places where logs are shared. 4) Prefer to call the official pixmind.io endpoints yourself (or via Pixmind's official SDK) if you have doubts about third-party gateways. If you need higher assurance, ask the skill author for evidence that those domains are official or request an alternative using direct pixmind.io endpoints.
Capability Analysis
Type: OpenClaw Skill Name: pixmind-video Version: 1.3.0 The pixmind-video skill is a legitimate integration for the Pixmind AI video generation service. The code in video-generate.js and task-status.js correctly implements the documented API flow using the required PIXMIND_API_KEY environment variable, and no evidence of data exfiltration, malicious execution, or prompt injection was found.
Capability Assessment
Purpose & Capability
Name, description, declared env var (PIXMIND_API_KEY), and provided helper scripts all align with a Pixmind video-generation integration. However, the SKILL.md and scripts call https://aihub-admin.aimix.pro and reference https://chatmix.top for result URLs rather than pixmind.io; this is called out in the SKILL.md as Pixmind's gateway/CDN but you should independently verify these domains are legitimately used by Pixmind.
Instruction Scope
SKILL.md and the two helper scripts only perform generation and task-status polling against the API gateway and print/poll results. They do not read unrelated files, other environment variables, or system configuration. The scripts log prompts and JSON responses to stdout (which may be captured by system logs).
Install Mechanism
There is no install spec (instruction-only with small included Node helper scripts). Nothing is downloaded or written during an install step; the risk surface is limited to running the included scripts.
Credentials
Only PIXMIND_API_KEY is required and used to set the X-API-Key header for API calls. That single credential is proportional to the stated purpose.
Persistence & Privilege
always is false and the skill does not request persistent system modifications or access to other skills' configs. It does not attempt to store credentials on disk or modify global settings.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install pixmind-video
  3. After installation, invoke the skill by name or use /pixmind-video
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.3.0
Inline API logic, remove shared module to clear security scan
v1.2.0
Remove file read and localhost defaults to fix security scanner flags
v1.1.0
Add homepage, include helper scripts in bundle, clarify API domain
v1.0.1
Add README with usage guide and screenshots
v1.0.0
Pixmind Video Skill 1.0.0 – Initial Release - Generate AI videos from text prompts ("text-to-video") or animate existing images ("image-to-video") using the Pixmind API. - Supports custom duration, aspect ratio, resolution, and model selection. - Automatically chooses generation type based on user input (defaults to text-to-video). - Provides instructions for script-based usage and response polling for task completion. - Requires PIXMIND_API_KEY environment variable for authentication.
Metadata
Slug pixmind-video
Version 1.3.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 5
Frequently Asked Questions

What is Pixmind Video Generation?

Generate AI videos via Pixmind API (text-to-video and image-to-video). It is an AI Agent Skill for Claude Code / OpenClaw, with 138 downloads so far.

How do I install Pixmind Video Generation?

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

Is Pixmind Video Generation free?

Yes, Pixmind Video Generation is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Pixmind Video Generation support?

Pixmind Video Generation is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Pixmind Video Generation?

It is built and maintained by Pixmind (@fuyunzhishang); the current version is v1.3.0.

💬 Comments