By openmule
Integrate MuleRouter and MuleRun multimodal APIs into Python apps to generate images, videos, audio, speech, and music from text prompts, plus edit existing media using advanced models like Veo3, Sora2, and Kling V3. Set MULEROUTER_API_KEY and base URL env vars for seamless API access in AI media workflows.
npx claudepluginhub openmule/mulerouter-skills --plugin mulerouter-skillsAgent Skill for calling MuleRouter / MuleRun multimodal APIs to generate images and videos.
--list-paramsclaude plugin marketplace add openmule/mulerouter-skills
claude plugin install mulerouter-skills
In a Claude Code session:
/plugin marketplace add openmule/mulerouter-skills
/plugin install mulerouter-skills
After installation, RESTART Claude Code to load the new skill.
| Variable | Description |
|---|---|
MULEROUTER_API_KEY | API key for authentication |
| Variable | Description | Priority |
|---|---|---|
MULEROUTER_BASE_URL | Custom API base URL (e.g., https://api.mulerouter.ai) | Higher |
MULEROUTER_SITE | API site: mulerouter or mulerun | Lower |
Note: MULEROUTER_BASE_URL takes priority over MULEROUTER_SITE. If both are set, MULEROUTER_BASE_URL is used.
Get your API key on the MuleRouter website
export MULEROUTER_BASE_URL="https://api.mulerouter.ai"
export MULEROUTER_API_KEY="your-api-key"
export MULEROUTER_SITE="mulerouter" # or "mulerun"
export MULEROUTER_API_KEY="your-api-key"
Create a .env file in your skill directory:
# Option 1: Use custom base URL (takes priority)
MULEROUTER_BASE_URL=https://api.mulerouter.ai
MULEROUTER_API_KEY=your-api-key-here
# Option 2: Use site (if BASE_URL not set)
# MULEROUTER_SITE=mulerun
# MULEROUTER_API_KEY=your-api-key-here
Note: The tool only reads MULEROUTER_* variables from .env. Other variables in the file are ignored.
# Check environment variables
echo "MULEROUTER_BASE_URL: $MULEROUTER_BASE_URL"
echo "MULEROUTER_SITE: $MULEROUTER_SITE"
echo "MULEROUTER_API_KEY: ${MULEROUTER_API_KEY:+[SET]}"
# Check for .env file
ls -la .env 2>/dev/null || echo "No .env in current directory"
Let Claude Code run /mulerouter-skills:mulerouter-skills to use the skill.
Or just ask Claude to use MuleRouter to generate some images or videos.
skills/mulerouter/
├── SKILL.md # Agent skill entry point
├── scripts/ # Utility scripts
│ └── list_models.py # Model listing utility
├── models/ # Model endpoints (executable)
├── core/ # Core infrastructure
│ ├── config.py # Configuration management
│ ├── client.py # HTTP client
│ ├── registry.py # Model registry
│ └── task.py # Task polling
├── references/ # Documentation
│ ├── REFERENCE.md # API reference
│ └── MODELS.md # Model specifications
└── tests/ # Unit tests
All model scripts support:
| Option | Description |
|---|---|
--api-key KEY | Override API key |
--base-url URL | Override base URL (takes priority over --site) |
--site SITE | Override site (mulerouter/mulerun) |
--json | Output as JSON |
--list-params | Show parameters and exit |
--no-wait | Don't wait for task completion |
--quiet | Suppress progress output |
uv run ruff format .
uv run ruff check --fix .
uv run pytest
MIT
Claude Code skill pack for Runway (18 skills)
Share bugs, ideas, or general feedback.
Generate images, videos, and music using 600+ Fal.ai models. Supports Flux, SDXL, Kling Video, and more.
Video generation at scale. Generate videos, images, and audio with Runway's API — batch ad campaigns, product videos, multishot stories, and creative iteration. Supports seedance2, gen4.5, veo3, Nano, Banana Pro, and more.
The creative suite for AI agents — motion graphics, asset generation, and video rendering via Remotion + @oanim/core
AI-powered image editing and manipulation skill from Fal AI for creative asset generation.
Configurable MCP wrapper that consolidates your tools into just 3, using semantic search for on-demand discovery and sandboxed TypeScript execution. Ships with 7 example servers (96 tools) - reduces context consumption by 97% (48k tokens down to 1.1k).