Microsoft's SkillOpt boosts GPT-5.5 by using nothing but a trained Markdown file

Microsoft and three Chinese universities developed SkillOpt, a method that optimizes instruction documents for AI agents using principles from traditional model training. A simple Markdown file boosted GPT-5.5 by about 23 points on procedural tasks, and the same file transferred across models and agent environments like Codex and Claude Code.

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 https://the-decoder.com/microsofts-skillopt-boosts-gpt-5-5-by-using-nothing-but-a-trained-markdown-file/ appeared first on The Decoder https://the-decoder.com .