# Benchmark Quick > Quick smoke test of the full mdarena pipeline, mine 3 PRs from a repo and run 1 task. Use when this capability is needed. - Skill: `tomevault-io/benchmark-quick` (Agent Skill, multi-file: 2 files) - Install (CLI): `npx skillmds@latest add tomevault-io/benchmark-quick` - Raw SKILL.md: https://api.skillmd.com/api/skills/tomevault-io/benchmark-quick/raw - Safety review: pending (external: skill-scanner PASS, skillspector PASS) - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: DevOps & Infra - Author: tomevault-io (https://skillmd.com/u/tomevault-io) - Updated: 2026-09-17 - Page: https://skillmd.com/skills/tomevault-io/benchmark-quick --- Run a quick end-to-end smoke test of the mdarena pipeline. Use $ARGUMENTS as the GitHub repo (e.g., `owner/repo`). If no repo is provided, ask the user for one. Steps: 1. `uv run mdarena mine $ARGUMENTS --limit 3 -o /tmp/mdarena-smoke/tasks` 2. Verify the manifest.json was created and has tasks 3. Report the number of tasks mined and their difficulty breakdown 4. Note: skip `mdarena run` (requires Claude CLI budget), just verify mining works Report what was mined: task count, PR numbers, difficulty distribution, whether test commands were detected. --- > Source: [HudsonGri/mdarena](https://github.com/HudsonGri/mdarena) — distributed by [TomeVault](https://tomevault.io).