Benchmark

by fynnfluegge

Benchmark is an AI Engineering skill for Claude Code, published by fynnfluegge in agtx.

1.2K stars111 forkson fynnfluegge/agtxAdded 2026/08/20Repository updated 2026/08/11

View source on GitHub Download repo ZIP

claudeclaude-codecodexcursorgeminiopencodespec-driven-developmentvibe-coding

Install in seconds

Install Benchmark

Copy Benchmark into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/fynnfluegge/agtx/tree/main/benchmark/skills/benchmark ~/.claude/skills/benchmark

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/fynnfluegge/agtx.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: benchmark/skills/benchmark/SKILL.md in fynnfluegge/agtx
Installs to: ~/.claude/skills/benchmark
Collection: One of 7 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Benchmark does

Benchmark runs SWE-bench Lite evaluations against agtx coding agent workflows. Use it to configure, execute, and report on benchmark runs for Claude Code, Gemini CLI, or Codex CLI.

Benchmark is cataloged under AI Engineering on DirSkills. Benchmark comes from a repository tagged claude, claude-code, codex, cursor and gemini.

Documentation

README

Excerpt

Benchmark — SWE-bench Lite

You are a benchmark guide. Help the user run, configure, and evaluate SWE-bench Lite benchmarks against agtx agent workflows.

Answer questions, surface the right commands, and walk through setup interactively. All commands assume the user is in the benchmark/ directory.

Prerequisites

This is the opening of the README. Read the full README on GitHub.

Commands Benchmark provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

/testbed

Frequently asked about Benchmark

What else does fynnfluegge publish alongside Benchmark?
Benchmark is one of 7 skills that DirSkills catalogs from fynnfluegge/agtx, the repository it ships in. Its siblings there include AGTX Execute, AGTX Research and AGTX Review. Each one is a separate skill with its own page in this directory, installs the same way Benchmark does, and is maintained by fynnfluegge in that same repository. The rest of the collection is listed on the fynnfluegge/agtx page.
How does Benchmark compare to other AI Engineering skills?
Benchmark ranks #1144 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Benchmark against them. Open each page to compare what they document and how they install.