AI for Developers
Agent skill (SKILL.md) Open source MIT 18.9k

SkillOpt

Microsoft research code that improves a skill document by scoring it, the way training adjusts model weights.

Install

For this project
$ npx skills add microsoft/SkillOpt -a claude-code
For every project
$ npx skills add microsoft/SkillOpt -a claude-code -g

Or copy the skill folder into .claude/skills/ (project) or ~/.claude/skills/ (all projects).

For this project
$ npx skills add microsoft/SkillOpt -a codex
For every project
$ npx skills add microsoft/SkillOpt -a codex -g

Or copy the skill folder into .agents/skills/ (project) or ~/.agents/skills/ (all projects).

For this project
$ npx skills add microsoft/SkillOpt -a openclaw
For every project
$ npx skills add microsoft/SkillOpt -a openclaw -g

Or copy the skill folder into skills/ (project) or ~/.openclaw/skills/ (all projects).

Clone the repository and follow the README to configure a backend and benchmark.

When to use

Use it when you have a skill with a measurable benchmark and want to improve it by score instead of by hand.

SkillOpt is Microsoft research code that improves a skill document the way training adjusts model weights, but without touching the model. It uses epochs, batch sizes, learning rates and validation gates. A separate optimizer model reads scored rollouts and proposes small add, delete or replace edits. By default an edit is kept only if it strictly improves a held-out validation score, and a learning-rate budget limits how much changes per step.

There's a web UI, and you can add your own backends and benchmarks. It's published on PyPI, backed by a paper that was accepted as a NeurIPS 2026 Spotlight, and documented in a versioned docs site and technical blog. It's research software, so expect to read the docs before running it.

Related skills

All skills