rustidi

Agent Eval — Productivity skill for Claude Code

Productivity community

Head-to-head comparison of coding agents / models on reproducible tasks, with pass-rate / cost / time / consistency metrics.

How to install Agent Eval

Installs to ~/.claude/skills/rustidi-ml-portfolio-agent-eval/SKILL.md

Terminal

mkdir -p ~/.claude/skills/rustidi-ml-portfolio-agent-eval && curl -fsSL https://raw.githubusercontent.com/rustidi/ml-portfolio/HEAD/skills/agent-eval.md -o ~/.claude/skills/rustidi-ml-portfolio-agent-eval/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What Agent Eval does

name: agent-eval description: Head-to-head comparison of coding agents / models on reproducible tasks, with pass-rate / cost / time / consistency metrics. Gives a framework instead of vibes when choosing between models for a step (e.g. transcription or text-polish). triggers: ["compare models", "which model is better", "agent eval", "head to head", "model comparison", "model selection"]

Agent Eval Skill

Sanitized example skill. Wraps a third-party CLI tool (credited below).

A ligh

Alternatives in Productivity

/build-hook - Build Custom Claude Code Hooks — Interactive guide for creating custom hooks with Q&A workflow and automatic validation 618 ★
Claude Code Usage Bar — Real‑time statusline for Claude Code: token usage, remaining budget, burn rate, and depletion time 159 ★
Coder Eval Review — Generate per-task review.json (summary + tags) for a completed run 116 ★