llm-session-start

Run environment and wiring sanity checks for the LLM repository.

4|3|Updated Feb 18, 2026
One-click install
npx skills add https://github.com/Arm-Examples/LLM-Runner --skill llm-session-start
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: llm-session-start
Source: https://github.com/Arm-Examples/LLM-Runner/tree/main/skills/llm-session-start
Command: npx skills add https://github.com/Arm-Examples/LLM-Runner --skill llm-session-start

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill ensures your LLM development environment is correctly set up and that your project's backend dependencies are properly configured, preventing common build and integration issues.

Core Features & Use Cases

  • Environment Sanity Checks: Verifies your toolchain and project wiring.
  • Framework Version Reporting: Provides a clear overview of pinned backend framework versions (llama.cpp, ONNX Runtime, Mediapipe, MNN).
  • Optional Upstream Update Check: Scans for newer versions of backend frameworks.
  • Debug Bundle Creation: Generates a comprehensive package of logs and environment info for bug reporting.
  • Pinned Version Bumping: Assists in updating and verifying pinned backend framework versions.

Quick Start

Run fast environment and wiring checks for the LLM repository.

Frequently Asked Questions about llm-session-start

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

FAQPage Schema
How do I verify my LLM repository environment and backend framework versions?

You can verify your LLM repository environment by running rapid sanity checks that report on toolchain wiring and pinned backend framework versions like llama.cpp, onnxruntime-genai, mediapipe, and mnn. This ensures your setup is correctly configured to prevent build issues.

What is the best way to check for upstream updates for backend frameworks like llama.cpp?

Checking for upstream updates for backend frameworks like llama.cpp is handled by an optional scan that identifies newer versions. You can then update and verify pinned backend framework versions using build and ctest verification to ensure stability.

How do I generate a debug bundle for an LLM development environment?

Generating a debug bundle for an LLM development environment involves collecting comprehensive logs and environment info into a single package. This provides the necessary diagnostic data for bug reporting when environment or wiring issues occur.

Does this environment check support updating pinned versions for onnxruntime-genai and mediapipe?

Yes, the environment check supports updating and verifying pinned backend framework versions for onnxruntime-genai, mediapipe, llama.cpp, and mnn. It assists with bumping versions while running build and ctest verification to confirm integration.

Why do I need to run sanity checks before upgrading LLM backends?

Running sanity checks before upgrading LLM backends is essential to verify that your toolchain and project wiring are correctly configured. This prevents common build and integration issues when updating core frameworks like llama.cpp or mnn.

What should I do if my LLM project build verification fails after a framework bump?

If build verification fails after a framework bump, generate a debug bundle to collect comprehensive logs and environment info. This package helps diagnose integration issues with backend frameworks like llama.cpp or onnxruntime-genai during session initiation.