@oliviscusAI: MICROSOFT JUST OPEN-SOURCED SELF-EVOLVING AGENT SKILLS. it's called skillopt. skills that improve themselves the same w…

X AI KOLs Timeline Tools

Summary

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 JUST OPEN-SOURCED SELF-EVOLVING AGENT SKILLS. it's called skillopt. skills that improve themselves the same way you train an ai model. no more guessing whether your prompt tweaks helped. a base model runs the task, an optimizer evaluates the output and rewrites the instructions itself. → isolates successful paths from failures to find precise improvements → auto-rejects any edit that doesn't beat your benchmark score → beats hand-crafted prompts and optimizers like textgrad → zero model lock-in, the skill transfers to any model you switch to 100% free. open source.
Original Article
View Cached Full Text

Cached at: 07/20/26, 07:31 PM

MICROSOFT JUST OPEN-SOURCED SELF-EVOLVING AGENT SKILLS.

it’s called skillopt.

skills that improve themselves the same way you train an ai model.

no more guessing whether your prompt tweaks helped. a base model runs the task, an optimizer evaluates the output and rewrites the instructions itself.

→ isolates successful paths from failures to find precise improvements → auto-rejects any edit that doesn’t beat your benchmark score → beats hand-crafted prompts and optimizers like textgrad → zero model lock-in, the skill transfers to any model you switch to

100% free. open source.

Similar Articles

@omarsar0: New research from Microsoft Research I see a lot of AI engineers handwriting agent skill docs and hope they generalize.…

X AI KOLs Following

Microsoft Research introduces SkillOpt, a method that treats agent skill documents as trainable external state, using an optimizer model to make bounded edits validated by a held-out set. The approach achieves best or tied results across 52 evaluation cells and improves accuracy by over 23 points on GPT-5.5, with zero extra inference cost and transferable skills.