Skills
.Work. You
Rest

bench-corpus-review

Official

Automate and review the quality of the whole corpus with bench-task-judge.

Software Engineering#quality assurance#quality control#benchmarking#corpus review#diolog-swe-bench
AuthorDiologIR
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill automates the re-run of the whole-corpus quality review of diolog-swe-bench, allowing for an efficient assessment of every task in the corpus.

Core Features & Use Cases

  • Automated Review: Re-run the quality review of all tasks in the corpus.
  • Task Verdicts: Assemble documentation of per-task verdicts, summary counts, and re-run plans.
  • Diffing: Compare the current review against the previous one to identify changes and trends.
  • Use Case: Ideal for auditing the benchmark, after new tasks have been added, or on a scheduled basis to ensure ongoing quality.

Quick Start

Run the bench-corpus-review skill from the diolog-swe-bench repo root to regenerate the corpus-wide task review.

Dependency Matrix

Required Modules

None required

Components

scripts

💻 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: bench-corpus-review
Download link: https://github.com/DiologIR/diolog-plugins/archive/main.zip#bench-corpus-review

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 620,000+ vetted skills library on demand.