Microsoft's SkillOpt boosts GPT-5.5 by using nothing but a trained Markdown file
Quick Answer
Microsoft, in collaboration with three Chinese universities, has introduced SkillOpt, a method that enhances GPT-5.5's performance on procedural tasks by approximately 23 points using a trained Markdown file.
Quick Take
This optimization technique is transferable across various models and environments, including Codex and Claude Code.
Key Points
- SkillOpt optimizes AI instruction documents using traditional model training principles.
- A single Markdown file can significantly enhance GPT-5.5's procedural task performance.
- The performance boost of 23 points is notable for AI agent efficiency.
- SkillOpt's methodology is applicable across different AI models and environments.
- Collaboration with Chinese universities highlights international research efforts in AI.
Source Excerpt
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.
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from The Decoder
See more →
An AI model programmed nonstop for 19 days on a single MirrorCode task that cost $2,600 to run
Epoch AI's MirrorCode benchmark reveals Claude Opus 4.7 as the leader with a 56% solve rate, reconstructing a 16,000-line toolkit in 14 hours. Despite this, all models tested struggle with the most complex tasks, highlighting limitations in current AI capabilities. The single task consumed $2,600 over 19 days, raising questions about cost-effectiveness in AI development.
