Stories by xdotli

Chaos of Agent

Native CLI scaffolds consistently outper-form OpenCode when using the same model

We compare model quality in Cursor

Automatically Learning Skills for Coding Agents

We Reached 74.8% on terminal-bench with Terminus-KIRA

Self-generated skills don't do much for AI agents, but human-curated skills do

First Agent Skills Hackathon by the Authors of SkillsBench

The First Agent Skills Benchmark

GPT-5.2 got worse on Terminal Bench 2.0, so is GPT-5.2 Pro

Claude Skills as a Meta Tool

Show HN: Chat with Claude Code on iMessage with Instaline

Show HN: PokemonGym – 387 milestones designed to test agents and LLMs

Show HN: BenchFlow – run AI benchmarks as an API

Ask HN: Which CRM can help manually curated leads and automate lead discovery?

Ask HN: How to pay myself on F1 Visa as startup CEO