PerceptionBench: Evaluating Atomic Visual Perception in Multimodal Large Language Models

A skill for your coding agent to stop it from burying the answer. ADHD-friendly output.

pierre’s open source code

Design principles for agent ergonomics. Higher accuracy with lower token cost than both MCP and regular CLI.

ExploitBench measures how far AI agents climb, from reaching vulnerable code, to triggering the bug, to building exploit primitives, to arbitrary code execution.

Convert documentation websites, GitHub repositories, and PDFs into Claude AI skills with automatic conflict detection

🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman