Skills
.Work. You
Rest

local-llm-tooling

Community

Run and prompt local LLMs with robust tooling.

Software Engineering#automation#llm#tooling#offline#prompting#server-management#local-llm
AuthorStepowskiEric
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Locally hosted LLMs require reliable workflows for starting servers, routing prompts, and extracting structured outputs without external APIs or data leakage.

Core Features & Use Cases

  • Local backend orchestration: manage Ollama, llama.cpp, or text-generation-webui servers from a single workflow.
  • Prompt engineering and templates: craft task-specific prompts with deterministic behavior.
  • Structured output extraction: enforce JSON or structured formats and validate outputs in your automation.
  • Privacy-first automation: operate entirely offline or within a private network for sensitive data workflows.

Quick Start

Start a local LLM server and issue a structured prompt to produce JSON output.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: local-llm-tooling
Download link: https://github.com/StepowskiEric/Jerrys-agent-skills/archive/main.zip#local-llm-tooling

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.