Microsoft and three Chinese universities have developed SkillOpt, a method that optimizes instruction documents for AI agents using principles from traditional model training. A simple Markdown file is enough to boost GPT-5.5 by about 23 points on procedural tasks, and the same file transfers across models and agent environments like Codex and Claude Code.
The article Microsoft's SkillOpt boosts GPT-5.5 by using nothing but a trained Markdown file appeared first on The Decoder.
source & further reading
the-decoder.com — original article
Claude Fable 5 outpaces GPT-5.5 by 13 points on FrontierMath's toughest problems
Meta shifts from "tokenmaxxing" to token managing as internal AI costs reportedly hit billions
Moonshot's open model Kimi K2.7 Code undercuts GPT-5.5 and Claude by up to 12x on price per token