skills.rest
sourcegraph
sourcegraphOFFICIAL
Explore all skills by this author →
Website𝕏@sourcegraphGitHub

generate-report

Generate aggregate CodeScaleBench evaluation reports from Harbor runs in markdown, JSON, and CSV.

32|4|Updated Feb 1, 2026
Search Tags:#automation#report generation#benchmark#harbor#code evaluation#metrics analysis
One-click install
npx skills add https://github.com/sourcegraph/CodeScaleBench --skill generate-report-sourcegraph
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: generate-report
Source: https://github.com/sourcegraph/CodeScaleBench/tree/main/skills/generate-report
Command: npx skills add https://github.com/sourcegraph/CodeScaleBench --skill generate-report-sourcegraph

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill automates the generation of comprehensive evaluation reports for CodeScaleBench benchmark runs, consolidating metrics and performance data into human-readable and machine-readable formats.

Core Features & Use Cases

  • Aggregate Metrics: Collects and processes results from multiple benchmark runs.
  • Report Generation: Produces markdown summaries, JSON data, and CSV files for detailed analysis.
  • Use Case: After running a suite of benchmark tests, use this Skill to generate an overall performance report, highlighting key metrics like reward, pass rate, and efficiency across different configurations.

Quick Start

Use the generate-report skill to create the aggregate CSB evaluation report from completed Harbor runs.

Frequently Asked Questions about generate-report

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

FAQPage Schema
How do I generate a CodeScaleBench evaluation report from completed Harbor runs?▼

This Skill generates CodeScaleBench evaluation reports from completed Harbor runs by processing metrics and producing markdown, JSON, and CSV outputs consolidating your benchmark performance data.

What metrics are included in a CSB benchmark aggregate report?▼

An aggregate CSB benchmark report includes key metrics like reward, pass rate, and efficiency across different configurations, consolidated into markdown summaries and machine-readable files.

What is the best way to automate post-benchmark analysis and performance reporting?▼

The best way to automate post-benchmark analysis is using Python scripts to aggregate, enrich, and filter benchmark run data, generating detailed performance reports without manual data processing.

Can I export benchmark results to CSV and JSON formats for metrics analysis?▼

Yes, you can export benchmark results to CSV and JSON formats. The Skill processes completed benchmark runs and generates both machine-readable JSON data and CSV files for detailed metrics analysis.

Do I need Python scripts to aggregate metrics from multiple benchmark runs?▼

Yes, Python scripts are required to aggregate metrics from multiple benchmark runs. The Skill relies on Python to perform data aggregation, enrichment, filtering, and file generation for CodeScaleBench evaluation.

When should I use an automated report generation workflow for code evaluation?▼

You should use an automated report generation workflow for code evaluation after running a suite of benchmark tests, enabling you to consolidate metrics and highlight performance across different configurations.

Related Skills

Explore More Software Engineering Skills→
sourcegraphsourcegraph
32

scaffold-task

Generate Harbor-compatible CodeScaleBench task files and suite configurations.

Official
Advanced
filipnyquistfilipnyquist

benchmark

Benchmark web page performance by collecting navigation and resource timings.

Community
Advanced
KaiserWhoLearnsKaiserWhoLearns

harbor

Automate agent performance evaluation with Harbor framework tasks.

Community
Advanced
xiaoyuge886xiaoyuge886
196

skill-creator

Draft, evaluate, and optimize AI skills with Python-based benchmarks.

Community
Advanced