bench

Formal benchmark harness. Runs a metric command N times across 2-3 variants (git refs or state-prep shell commands), checks variance, computes delta vs. declared baseline, and emits a reproducible TSV

Get it

$ npx degit ddalcu/mlx-serve/.claude/skills/bench .claude/skills/bench

From the most-starred rig that ships it: ddalcu/mlx-serve. Same-named skills in different rigs may differ — review before use.

Often used together with

Rigs using bench (4)

ddalcu/mlx-serve

Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Zig backend, Swift frontend macOS app with chat, music, voice, video generation.

★ 1,655 project Claude CodeCodex 4 skills 10d ago

Pragmatist 71.4k tok ·

autonomous-ai/openharness

The ultimate harness for coding agents and beyond. All your agents. All your machines. One command center. Start with code, then follow your curiosity and build across disciplines: CAD, circuits, robots, games and music.

★ 1,072 setup Claude CodeCodex 111 skills 7d ago

Skill Collector 23.3k tok ·

arbazkhan971/godmode

Autonomous AI coding agent — 126 skills, 7 subagents, 5 platforms. Iterative optimization with automatic rollback, failure memory, and parallel multi-agent execution. Plugin for Claude Code, Cursor, Codex, Gemini CLI, OpenCode.

★ 26 project CodexCursorGemini CLI 3 mcp 131 skills 1mo ago

Skill Collector 20.8k tok ·

ocrosby/claude-config

Claude Code configuration

★ 1 setup Claude Code 17 skills 20 agents 16 hooks 1d ago

YOLO Cowboy 5.1k tok ·