model-eval-report

Generate a Quarto report from the latest LLM evaluation results JSON.

Updated Mar 27, 2026
One-click install
npx skills add https://github.com/LinusConradM/test_crpd_dashboard --skill model-eval-report
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: model-eval-report
Source: https://github.com/LinusConradM/test_crpd_dashboard/tree/main/.claude/skills/model-eval-report
Command: npx skills add https://github.com/LinusConradM/test_crpd_dashboard --skill model-eval-report

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Generates a professional Quarto HTML model performance evaluation report for the CRPD Dashboard LLM integration, enabling consistent, shareable assessments from the latest evaluation results.

Core Features & Use Cases

  • Automatically locate the latest evaluation results JSON from LLM_Development and extract phase, run_date, test_questions, configs, winner, and recommendation to drive report generation.
  • Generate a polished Quarto (.qmd) report with interactive visuals, a performance summary, and a model recommendation.
  • Save reports sequentially in Model Performance Evaluation/ as report_001_, report_002_, ... with a phase slug and date in the filename.
  • Trigger on demand or automatically after phase evaluation completes (evaluate_phase*.py) when a report for that phase hasn't been generated yet.
  • Handle multiple configs and rate-limit skipped configurations, including a clear recommendation and known gaps.

Quick Start

Ask the skill to generate the latest model evaluation report and it will locate the most recent eval_results_phase*.json, build a Quarto report, and save it under Model Performance Evaluation/report_NNN_phaseSlug_YYYY-MM-DD.qmd.

Frequently Asked Questions about model-eval-report

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

FAQPage Schema
How do I auto-generate an LLM model evaluation report from JSON results?

To generate an LLM model evaluation report from JSON, the skill locates the latest eval_results JSON in LLM_Development, extracts test metrics and configurations, and outputs a structured Quarto document with an executive summary and recommendation.

What metrics are included in a Quarto model evaluation report?

A Quarto model evaluation report includes performance metrics such as MRR and ndCG, alongside retrieval and judge-lens analyses, a performance summary table, model recommendations, and known gaps extracted from the evaluation JSON.

How do I create a Quarto report from a JSON file for LLM development?

You can create a Quarto report from a JSON file by having the skill identify the latest phase evaluation results, compute the next sequential report number, and save a formatted .qmd file with visualizations to the Model Performance Evaluation directory.

Can I generate a model performance evaluation report automatically after a phase evaluation completes?

Yes, the report generation can be triggered on demand or automatically after phase evaluation scripts finish, provided a report for that specific phase has not yet been generated.

How does the reporting tool handle rate-limit skipped configurations in LLM evaluation?

The reporting tool handles rate-limit skipped configurations by documenting them within the generated Quarto report, providing a clear model recommendation while explicitly noting the skipped configs as known gaps.

Do I need Quarto installed to generate model evaluation reports from JSON?

Quarto is the target format for the report output, generating a .qmd file with interactive visuals and structured analyses, so you need a Quarto environment to render the final HTML document.