Agent skill
media-tools
Media generation and manipulation tools for creating images, videos, and GIFs. Use when the user needs to generate, search for, or transform visual media content.
Install this agent skill to your Project
npx add-skill https://github.com/binome-dev/humcp/tree/main/src/tools/media
SKILL.md
Media Tools
Tools for generating and manipulating media content including images, videos, and GIFs.
Available Tools
Image Generation
- dalle_generate_image - Generate images using OpenAI DALL-E
- models_labs_generate_image - Generate images via ModelsLab API
- nano_banana_run - Generate media via NanoBanana/Banana.dev API
Image Search
- unsplash_search_photos - Search Unsplash for high-quality royalty-free photos
- unsplash_get_random_photo - Get random photos from Unsplash
- giphy_search - Search for GIFs on Giphy
- giphy_trending - Get trending GIFs from Giphy
Video Generation
- lumalab_generate_video - Generate videos using Luma AI
- moviepy_create_video - Create videos from image sequences using MoviePy
AI Model Platforms
- replicate_run_model - Run any model on Replicate
- replicate_get_prediction - Check status of a Replicate prediction
- fal_run_model - Run AI models via Fal.ai
Image Processing
- opencv_resize_image - Resize images using OpenCV
- opencv_convert_format - Convert image format using OpenCV
Requirements
Set environment variables as needed:
GIPHY_API_KEY- Giphy API keyUNSPLASH_ACCESS_KEY- Unsplash API access keyOPENAI_API_KEY- OpenAI API key (for DALL-E)REPLICATE_API_TOKEN- Replicate API tokenLUMAAI_API_KEY- Luma AI API keyFAL_KEY- Fal.ai API keyMODELS_LAB_API_KEY- ModelsLab API keyBANANA_API_KEY- Banana.dev API key
Examples
Generate an image with DALL-E
result = await dalle_generate_image(
prompt="A serene mountain landscape at sunset",
size="1024x1024",
quality="hd"
)
Search for GIFs
result = await giphy_search(
query="happy dance",
limit=5,
rating="g"
)
Search Unsplash photos
result = await unsplash_search_photos(
query="ocean sunset",
per_page=10
)
Generate a video with Luma AI
result = await lumalab_generate_video(
prompt="A timelapse of clouds moving over mountains"
)
Resize an image
result = await opencv_resize_image(
input_path="/path/to/image.jpg",
output_path="/path/to/resized.jpg",
width=800,
height=600
)
Response Format
All tools return a consistent response format:
{
"success": true,
"data": {
"...tool-specific fields..."
}
}
On error:
{
"success": false,
"error": "Description of what went wrong"
}
When to Use
- Generating images from text descriptions
- Searching for stock photos or GIFs
- Creating videos from image sequences
- Running AI media generation models
- Resizing or converting image formats
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
binome-dev/humcp
llm
Generate text, call tools, and get structured JSON output using LLM providers (Claude, OpenAI, Gemini, Ollama). Use when the user needs to call an LLM API for text generation, function calling, or structured data extraction.
binome-dev/humcp
calendar-tools
Manages calendar bookings and video conferencing. Use when the user needs to check availability, create bookings on Cal.com, or schedule and manage Zoom meetings.
binome-dev/humcp
http-api-client
Make HTTP requests to any URL or API endpoint. Use when the user needs to call a REST API, fetch data from a URL, send webhooks, or test HTTP endpoints. Supports GET, POST, PUT, PATCH, DELETE methods with custom headers and JSON body.
binome-dev/humcp
processing-data
Processes CSV files and pandas DataFrames. Use when working with CSV files, tabular data, spreadsheets, or when the user asks to query, analyze, or manipulate structured data.
binome-dev/humcp
persistent-memory
Store, search, and retrieve persistent memories and conversation history using Mem0 or Zep. Use when the user needs to remember facts, maintain context across sessions, or manage conversational memory.
binome-dev/humcp
storage
Use these tools for S3-compatible object storage operations with MinIO
Didn't find tool you were looking for?