replicate
nexu-io/open-design
Discover, compare, and run AI models via Replicate's API for image, audio, and video generation.
What is replicate?
Access Replicate's curated collection of AI models through a unified API. Use this skill when you need to generate, process, or compare outputs from multiple image, audio, or video models without managing individual integrations.
- Discover available AI models across image, audio, and video categories
- Compare model outputs and performance characteristics
- Run inference on selected models via Replicate's API
- Swap between models in generation pipelines
- Access curated model recommendations
How to install replicate
npx skills add https://github.com/nexu-io/open-design --skill replicate- Replicate API key
- Node.js environment with npx
How to use replicate
- 1.Install the upstream skill bundle from https://github.com/replicate/skills
- 2.Set your Replicate API credentials in your environment
- 3.Ask the agent to invoke the skill using 'replicate', 'run ai model', 'model comparison', or 'replicate api'
- 4.Specify the model and input parameters for your task
- 5.Review and iterate on model outputs
Use cases
- Generate variations of images using different model architectures
- Compare audio generation quality across multiple models
- Build video processing workflows that test multiple approaches
- Prototype multi-model pipelines for content creation
- Evaluate model performance before committing to one
- AI engineers building generation pipelines
- Content creators experimenting with multiple models
- Developers prototyping computer vision applications
- Teams evaluating model trade-offs
replicate FAQ
Replicate's skill supports image generation, audio generation, and video processing models. Check the upstream repository for the complete current catalog.
Yes, you need a Replicate API key to authenticate requests. Sign up at replicate.com and add your key to your environment.
The skill allows you to run different models sequentially and compare their outputs, making it suitable for model evaluation workflows.
Visit https://github.com/replicate/skills for the upstream README with complete model listings and documentation.
Full instructions (SKILL.md)
Source of truth, from nexu-io/open-design.
name: replicate description: | Discover, compare, and run AI models using Replicate's API. Strong fit for image, audio, and video generation pipelines that swap models frequently. triggers:
- "replicate"
- "run ai model"
- "model comparison"
- "replicate api" od: mode: image category: image-generation upstream: "https://github.com/replicate/skills"
replicate
Curated from Replicate.
What it does
Discover, compare, and run AI models using Replicate's API. Strong fit for image, audio, and video generation pipelines that swap models frequently.
Source
- Upstream: https://github.com/replicate/skills
- Category:
image-generation
How to use
This catalogue entry advertises the skill in Open Design so the agent discovers it during planning. To run the full upstream workflow with its original assets, scripts, and references, install the upstream bundle into your active agent's skills directory:
# Inspect the upstream README for exact paths
open https://github.com/replicate/skills
Then ask the agent to invoke this skill by name (replicate) or with
one of the trigger phrases listed in this skill's frontmatter.
Related skills
More from nexu-io/open-design and the wider catalog.
research-decision-room
|
resume-modern
Modern minimal resume, single A4 page, ready for print or PDF export.
screenshot
Capture desktop, app windows, or pixel regions across OS platforms.
screenshots-marketing
Generate marketing screenshots with Playwright for landing pages, App Store, and changelogs.
shadcn-ui
Build accessible UI components with shadcn/ui integrated into the Stitch design loop.
shader-dev
GLSL shader techniques for ray marching, fluid simulation, particle systems, and procedural generation.