skillopt

Microsoft open-sourced SkillOpt, a tool that enables AI agent skills to self-improve by automatically evaluating and rewriting their instructions, outperforming hand-crafted prompts and other optimizers with no model lock-in.

Microsoft's SkillOpt system improves ChatGPT accuracy from 41% to 80% by treating the AI's skill document as a living model that learns from its own failures, achieving significant gains across benchmarks with zero inference-time overhead.

The tweet discusses Microsoft's SkillOpt paper, which improved GPT-5.5 accuracy from 41% to 80% without retraining by using a small skills file to guide the agent.

Microsoft introduces SkillOpt, a method that trains an agent's skill documentation like a neural network, using epochs, batches, learning rates, and validation sets for optimization, without modifying model weights. It achieves top results across multiple benchmarks and can be transferred across models and tools.

Microsoft proposes the SkillOpt method, which treats documents as trainable parameters. By optimizing natural language documents without modifying weights, it improves model performance. It achieves 52 consecutive wins across 6 benchmarks, with GPT-5.5 improving by 23.5 points and Claude Code by 19.1 points.

This MUSE-Autoskill paper focuses on how an Agent manages an entire skill library, placing skills into a complete lifecycle: creation, memory, management, evaluation, and re-optimization.

Microsoft open-sourced SkillOpt, a method that treats markdown skill files like neural network parameters to train AI agents without modifying model weights, using learning rates, validation checks, minibatches, and epochs.

A tip for Codex users to implement agent research papers directly into their Codex environment using goal mode and local config, with SkillOpt as an example that improved a GPT-5.5 agent by +24.8 points.

This article explains the shift from prompt engineering to skill engineering for AI agents, introducing methods like SkillOpt, SkillOps, and SkillMOO for training, maintaining, and optimizing skills.