Skills
.Work. You
Rest

run-deep-swe

Community

Benchmark AI models on DeepSWE via OpenRouter.

Software Engineering#docker#benchmark#openrouter#sandbox#model-evaluation#coding-agent#deep-swe
AuthorMatymatyk-business
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This skill enables automated, reproducible scoring of AI models on the 113-task DeepSWE coding-agent benchmark via OpenRouter, allowing fair comparisons and verification of vendor claims.

Core Features & Use Cases

  • OpenRouter-driven evaluation with mini-swe-agent for model-agnostic benchmarking.
  • Supports single-task, subset, and full 113-task runs, with optional leaderboard submission.
  • Includes setup, OpenRouter wiring, and run workflows to produce comparable results.

Quick Start

Run a full 113-task DeepSWE evaluation for a selected model via OpenRouter and review the resulting score.

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: run-deep-swe
Download link: https://github.com/Matymatyk-business/david-skills/archive/main.zip#run-deep-swe

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.