skills.rest
Arm-Examples
Arm-ExamplesOFFICIAL
Explore all skills by this author →
GitHub

llm-config-schema-change

Modify LLM configuration schemas by updating parsing logic, tests, and documentation for JSON config keys.

4|3|Updated Feb 18, 2026
Search Tags:#testing#schema#llm#configuration#json#parsing
One-click install
npx skills add https://github.com/Arm-Examples/LLM-Runner --skill llm-config-schema-change
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: llm-config-schema-change
Source: https://github.com/Arm-Examples/LLM-Runner/tree/main/skills/llm-config-schema-change
Command: npx skills add https://github.com/Arm-Examples/LLM-Runner --skill llm-config-schema-change

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill provides a structured and safe way to modify the schema of model configuration files, ensuring that parsing, testing, and documentation are updated consistently. It's designed for targeted changes to configuration keys without undertaking a full model onboarding process.

Core Features & Use Cases

  • Schema Modification: Safely add or change JSON keys within model configuration files.
  • Integrated Updates: Ensures corresponding parsing logic, tests, and documentation are updated in sync.
  • Use Case: You need to add a new parameter to control the temperature sampling for a specific model. This skill helps you update the LlmConfig class, add a corresponding test case, and document the new parameter in the relevant configuration files.

Quick Start

Use the llm-config-schema-change skill to update the model configuration schema by adding a new key for 'max_new_tokens'.

Frequently Asked Questions about llm-config-schema-change

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

FAQPage Schema
How do I safely add a new JSON key to an LLM configuration schema?▼

To safely add a new JSON key to an LLM configuration schema, update the parsing logic, tests, and documentation simultaneously. Ensure new keys have safe defaults and validate them through CTest.

What is the process for updating C++ parsing logic when modifying model configuration files?▼

Updating C++ parsing logic requires modifying the LlmConfig class to handle new JSON keys. Changes target the model_configuration_files/ and src/cpp/config/ directories to maintain parsing consistency.

Can I change LLM config schemas without performing a full model onboarding?▼

Yes, you can make targeted schema changes to JSON configuration keys without a full model onboarding. This approach focuses specifically on updating parsing logic, tests, and documentation for the new keys.

How do I validate new configuration parameters added to model configuration files?▼

You validate new configuration parameters by adding corresponding test cases and running CTest. This ensures the new JSON keys are parsed correctly and have safe defaults applied within the C++ config.

What's the best way to keep tests and documentation updated when changing LLM config keys?▼

The best way to keep tests and documentation updated is applying integrated schema modifications. This ensures parsing logic, CTest cases, and configuration docs are synchronized when adding or changing JSON keys.

Related Skills

Explore More Software Engineering Skills→
havingautismhavingautism
190

using-git-worktrees

Create isolated git worktrees for feature development.

Community
Intermediate
tanujsutariatanujsutaria
1

config-validator

Validate API keys, entitlements, and build settings in project configurations.

Community
Basic
flatrickflatrick
1

cpp-testing

Develop and execute C++ tests with GoogleTest and CTest.

Community
Advanced
gancimgancim

sprint-create-agent

Create Sprint onboarding requests with role, icon, and adapter configuration.

Community
Advanced