Is Your Agent Skill Actually Good? Microsoft's Dual-Paper Deep Dive into Skill Evaluation and Self-Evolving Optimization

May 31, 2026 · Dev.to

I Built pretext-pdf: Serverless PDFs Without Chromium
I Built pretext-pdf: Serverless PDFs Without Chromium I got frustrated with PDF generation in Node.js. Every tool had tr
Tokyo Transit: How MCP Helped Me Fix a Broken Multi-Agent System
This is a submission for the GitHub Finish-Up-A-Thon Challenge What I Built Tokyo’s train system is incredible—but it ca
Compound Engineering: A Plugin That Makes Your AI Coding Agent Smarter Over Time
Most developers using AI coding tools hit the same ceiling eventually. The agent writes code, you accept or reject it, a
Beyond onlyOwner: Fixing Logic Vulnerabilities in DeFi (A RetoSwap Case Study)
Logic vulnerabilities are often the most dangerous bugs in DeFi. Unlike reentrancy or overflow errors, they don't always
What Building Agent_Sudo Taught Me About AI Agent Security (Before I Found Any Users)
I shipped a real thing. Agent_Sudo is a local permission gateway for AI agents: it sits in front of an agent's tool call