hiddink-harness-improve-report

Name: hiddink-harness-improve-report
Availability: InStock
Author: hiddink-ai

Query the eval-core database and generate markdown improvement reports.

1|Updated May 21, 2026

Search Tags:#performance #analysis #insights #reporting #harness #eval-core

Ready to run

npx skills add https://github.com/hiddink-ai/hiddink-harness --skill hiddink-harness-improve-report

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: hiddink-harness-improve-report
Source: https://github.com/hiddink-ai/hiddink-harness/tree/main/templates/skills/omcustom-improve-report
Command: npx skills add https://github.com/hiddink-ai/hiddink-harness --skill hiddink-harness-improve-report

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill addresses the lack of visibility into agent performance and routing quality by providing a structured, read-only summary of improvement suggestions generated by the eval-core analysis engine.

Core Features & Use Cases

Automated Analysis Rendering: Converts raw eval-core database insights into readable markdown reports.
Confidence-Aware Reporting: Automatically annotates reports with data sufficiency levels to ensure users understand the reliability of the insights.
Use Case: A developer can quickly check if their current agent routing configuration is effective by running this skill to see if the analysis engine has identified patterns or bottlenecks in recent session data.

Quick Start

Invoke the improve report skill to display the latest analysis insights from the eval-core engine.

Frequently Asked Questions about hiddink-harness-improve-report

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I generate an agent performance report from eval-core session data?▼

To generate an agent performance report, query the local eval-core database using the analysis engine to surface routing quality and actionable improvement suggestions formatted as markdown.

What is eval-core analysis and how does it show actionable insights?▼

Eval-core analysis is a mechanism that reads local session data to evaluate agent performance and routing quality, rendering structured markdown reports with confidence-aware data sufficiency annotations.

Do I need the eval-core CLI tool to analyze agent routing quality?▼

Yes, the eval-core CLI tool must be present in the environment to execute the read-only database queries and generate the markdown analysis report.

How does confidence-aware reporting work for agent performance insights?▼

Confidence-aware reporting annotates the generated markdown with data sufficiency levels based on session data volume, indicating the reliability of the routing quality insights.

Can I use this analysis report to fix agent routing configuration bottlenecks?▼

Yes, the report surfaces patterns and bottlenecks found in recent session data, allowing developers to check if their current agent routing configuration is effective.

What are the limitations when analyzing agent performance with low session data volume?▼

The analysis engine annotates reports with data sufficiency levels, meaning low session data volume will yield lower confidence insights and less reliable improvement suggestions.