microsoft/SkillOpt
A Microsoft research tool that automatically optimizes agent skills through a training loop — rollout, reflect, aggregate, select, update, evaluate — with built-in benchmarks.
Why it matters
Most skills are written and tuned by hand, which caps how good they get. SkillOpt treats a skill like something you can measurably improve, iterating against benchmarks across multiple model backends and keeping the version that scores best. For anyone serious about skill quality rather than vibes, it turns optimization into a repeatable, evaluated process.
Use cases
- Automatically iterate and improve a skill against benchmarks
- Compare skill performance across OpenAI, Claude, and other backends
- Run a structured rollout-reflect-evaluate optimization loop
- Ground skill quality in measured results instead of intuition
Quickstart
pip install skilloptRelated repositories
book-to-skill
A skill (and companion CLI) that converts a book or long document into a reusable agent skill, distilling its methods into something Claude can apply.
qiaomu-anything-to-notebooklm
A skill that converts assorted sources — articles, documents, media — into clean material ready to load into Google NotebookLM as a knowledge base.
From the blog
The State of Claude Skills: Spring 2026
An in-depth look at how the open-source community is building around Claude, the rise of MCP servers, and what to expect next.
12 New Claude Skill Repositories to Watch
This week's roundup of the most promising new Claude skills, including a powerful terminal agent and new MCP servers for database management.
Maintain this repo? Submit an update.
Submit an update