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 model catalog to discover, compare, and execute AI models for generative tasks. Ideal for workflows that frequently swap between different models for image, audio, and video generation.
- Discover available AI models from Replicate's catalog
- Compare model capabilities and performance
- Run models via Replicate's API
- Support for image, audio, and video generation
- Swap between models in active pipelines
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 skill using npx skills add with the provided GitHub URL
- 2.Set your Replicate API credentials in the agent environment
- 3.Invoke the skill by name ('replicate') or use trigger phrases like 'run ai model' or 'model comparison'
- 4.Specify the model and parameters for your task
- 5.Execute and iterate on results
Use cases
- Building image generation pipelines that test multiple models
- Comparing audio synthesis models for quality and speed
- Creating video generation workflows with model flexibility
- Prototyping generative AI applications with quick model iteration
- Automating model selection based on task requirements
- AI/ML engineers
- Generative AI developers
- Product teams building with multiple models
- Researchers comparing model performance
replicate FAQ
Replicate supports image, audio, and video generation models, among others. Check the upstream catalog at https://github.com/replicate/skills for the full list.
Yes, you need a Replicate API key to authenticate requests to their API.
Yes, the skill allows you to discover and compare models from Replicate's catalog before execution.
Visit https://github.com/replicate/skills to inspect the README and install the complete upstream bundle with original assets and scripts.
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 OpenDesign 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
Turn research notes into an evidence-backed decision room with themes, confidence scores, and experiment queues.
resume-modern
Modern minimal single-page A4 resume, ready for print or PDF export.
screenshot
Capture desktop, windows, or pixel regions across platforms for screenshots and bug reports.
screenshots-marketing
Generate marketing screenshots with Playwright for landing pages, App Store, and changelogs.
shadcn-ui
Build accessible UI components with shadcn/ui, integrated with the Stitch design loop.
shader-dev
GLSL shader techniques for ray marching, fluid simulation, particle systems, and procedural generation.