ocs-chatbot-eval

Community

Evaluate OCS transcripts with LLM verdicts.

Authorjjackson
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Quickly judges captured OCS chatbot transcripts to produce standardized verdicts and reports that feed gate decisions.

Core Features & Use Cases

  • Reads the most recent qa-captures transcript across quick, deep, and monitor modes and applies a four-dimension rubric (correctness, source usage, tone, tagging).
  • Generates a machine-readable verdict YAML under verdicts/ and a human-readable eval report under eval-reports/, plus a gate brief in deep mode.
  • Outputs per-item judgments and gate-surfaced insights to support risk and product decisions.

Quick Start

Run the ocs-chatbot-eval skill against a transcript to generate a verdict YAML and an eval report.

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: ocs-chatbot-eval
Download link: https://github.com/jjackson/ace/archive/main.zip#ocs-chatbot-eval

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.