eval-llm

Community

Safely validate LLM prompt changes end-to-end.

Authoridank
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Evaluates changes to an LLM-based extraction workflow end-to-end against a clean baseline to determine safety and impact before committing.

Core Features & Use Cases

  • Automates baseline+candidate runs for LLM evaluation, comparison, and verdicts on prompt/chunking/post-processing changes.
  • Supports guidance for selecting labels, models, and descriptions; produces structured verdicts (merge/regression/defer).
  • Useful for teams iterating on explainshell/extraction/llm code and needing fast, reproducible evaluation.

Quick Start

Invoke the evaluation workflow to run a baseline and candidate, then compare results to classify the change and decide on commit.

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: eval-llm
Download link: https://github.com/idank/explainshell/archive/main.zip#eval-llm

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 510,000+ vetted skills library on demand.