tlamatini-daily-chat-test

Official

Automate the daily Tlamatini chat regression.

AuthorXAIHT
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This harness automates daily regression testing for the Tlamatini chat UI, eliminating manual verification by driving a real Chrome session and collecting results.

Core Features & Use Cases

  • End-to-end regression: runs up to 1000 curated questions with Multi-Turn enabled to exercise the chat workflow.
  • Results and visibility: generates a dated report (report.md) and a JSON summary (summary.json) plus per-question results for easy analysis.
  • Safe, repeatable testing: logs interaction traces and surfaces WEAK/FAIL items to guide fixes; can combine with optional LLM judging for weak/failed cases.

Quick Start

Run the daily chat regression harness against a running Tlamatini server to execute all 1000 curated questions in a visible Chrome window and produce a dated report.

Dependency Matrix

Required Modules

playwrightanthropic

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: tlamatini-daily-chat-test
Download link: https://github.com/XAIHT/Tlamatini/archive/main.zip#tlamatini-daily-chat-test

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.