Automatically Learning Skills for Coding Agents

From a brief look, this appears to be using LLM-as-optimizer techniques to generate and measure the impact of skills. That's a lot more involved and likely more effective than the typical "ask Claude to write a skill for the task it just did".

> Using gskill, we learn repository-specific skills for jinja and bleve with a simple agent (Mini-SWE-Agent, gpt-5-mini), boosting its resolve rate from 55% to 82% on Jinja and from 24% to 93% on Bleve. These skills also transfer directly to Claude Code: on Bleve, Claude Haiku 4.5 jumps from 79.3% to 100% pass rate while running faster; on Jinja, Claude Haiku 4.5 improves from 93.9% to 98.5%.