Runs task-based LLM workflows including classification, extraction, summarization, and drafting via API.
npx skills add https://github.com/myapihq/myapi --skill my-llm-api
Please help me install this Agent Skill. Skill: my-llm-api Source: https://github.com/myapihq/myapi/tree/main/skills/my-llm-api Command: npx skills add https://github.com/myapihq/myapi --skill my-llm-api
This Skill provides a unified way to access language model capabilities without forcing developers to manage separate inference interfaces, model routing, or workflow-specific prompt handling.
Ask the my-llm-api skill to summarize a document, classify an input, extract structured fields, or draft a message using the LLM workflow interface.
High-intent search queries and answers about installing and using this skill.
You can add LLM summarization and classification to your application pipeline by using task-based workflow interfaces that handle prompt routing and model selection automatically, providing predictable API operations for structured data extraction and drafting.
Yes, you can run OpenAI-compatible inference and chat completions without managing separate model routing by accessing a unified, self-hosted model catalog through configurable request parameters and authenticated API endpoints.
The best way to generate embeddings and draft responses is through a unified language model interface that abstracts model selection behind stable task verbs, ensuring predictable API operations for automated workflows.
Yes, you need authenticated API access to perform cost-aware inference requests and model catalog discovery, enabling you to retrieve available self-hosted models and manage completion parameters securely.
Yes, this approach supports extracting structured business data from incoming requests by utilizing specialized task-based LLM verbs designed for classification, extraction, and document summarization workflows.
Your LLM workflow requires a stable task interface for automated pipelines because it keeps model selection and prompt handling behind predictable API operations, preventing disruptions when underlying models change.
rish2jainDeploy and operate NVIDIA Inference Microservices for GPU-accelerated AI inference.
sahiixxGenerate embeddings, analyze images, and extract structured JSON from text and documents.
Kingly-AgencyBuild RAG pipelines that ground LLM responses with retrieved external knowledge.
AveerOrchestrate deployment and configuration of local LLM inference servers for OpenCode.
