skills.rest
openkaiden
openkaidenOFFICIAL
Explore all skills by this author →
GitHub

add-inference

Standardize new LLM inference provider integration into OpenShell image builder.

3|2|Updated May 20, 2026
Search Tags:#integration#llm#rust#container#inference#openshell
One-click install
npx skills add https://github.com/openkaiden/openshell-image-builder --skill add-inference
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: add-inference
Source: https://github.com/openkaiden/openshell-image-builder/tree/main/.agents/skills/add-inference
Command: npx skills add https://github.com/openkaiden/openshell-image-builder --skill add-inference

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill addresses the complexity of integrating new LLM inference providers into the OpenShell image builder by providing a structured, multi-layer implementation checklist.

Core Features & Use Cases

  • End-to-End Integration: Guides the developer through trait implementation, agent wiring, and policy configuration.
  • Testing Framework: Ensures new providers meet quality standards through unit and integration test requirements.
  • Use Case: A developer needs to add a new proprietary LLM backend to their custom OpenShell image; this Skill ensures all necessary network policies, environment variables, and configuration files are correctly defined.

Quick Start

Follow the add-inference checklist to implement the necessary trait and registration steps for your new provider.

Frequently Asked Questions about add-inference

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I add a new LLM inference provider to a Rust container image builder?▼

To add a new LLM inference provider, implement the required inference traits, define network policies, and wire agent-specific configurations into the image builder architecture. This ensures consistent backend integration and validation across test suites.

What steps are needed to standardize LLM backend integration for inference providers?▼

Standardizing LLM backend integration requires implementing inference traits, configuring network policies, and completing agent-specific configuration wiring. Following a structured checklist ensures new providers meet unit and integration test quality standards.

Do I need to define network policies when integrating a new LLM inference backend?▼

Yes, defining network policies is required when integrating a new LLM inference backend. The standardization process mandates configuring network policies alongside environment variables and configuration files to ensure secure and correct provider communication.

How does inference trait implementation work for custom LLM providers in OpenShell?▼

Inference trait implementation for custom LLM providers involves defining the provider's specific behaviors and registration steps within the OpenShell architecture. This process standardizes how the builder interacts with the new backend across unit and integration tests.

What testing is required after wiring a new LLM inference provider into an image builder?▼

After wiring a new LLM inference provider, both unit and integration tests are required. The standardization process ensures new backends meet quality standards through comprehensive testing and validation across the image builder architecture.

Related Skills

Explore More Software Engineering Skills→
openkaidenopenkaiden
3

integration-tests

Validate openshell-image-builder container images with podman integration tests.

Official
Advanced
SchurupIK72SchurupIK72

test-writer

Generate and execute pytest suites for PyQt6 applications.

Community
Advanced
openkaidenopenkaiden
3

debug-image

Inspect container images and replicate integration test failures via shell access.

Official
Intermediate
bflandevbflandev
1

agentic-patterns

Design and implement multi-agent workflows with pattern strategies and smoke tests.

Community
Advanced