exploring-llm-evaluations

Official

Coordinate LLM and Hog evaluations end-to-end.

AuthorPostHog
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Inspect, compare, and manage Hog (deterministic) and llm_judge (LLM-based) evaluations across configurations, runs, and summaries to enable debugging, optimization, and lifecycle governance.

Core Features & Use Cases

  • List, inspect, and manage evaluation configs for both Hog and LLM judge types.
  • Run evaluations against specific $ai_generation events, query results, and generate AI-powered summaries of pass/fail patterns.
  • Drill into failing examples and manage the evaluation lifecycle (create, update, enable/disable, delete).

Quick Start

Create a sample Hog or llm_judge evaluation, enable it, and run it against a representative generation to observe the results.

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: exploring-llm-evaluations
Download link: https://github.com/PostHog/skills/archive/main.zip#exploring-llm-evaluations

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.