microsoft/SkillOpt

COLLECTIONcommunity
microsoftMITUpdated 23d agoGitHub

SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.

Train agent skills like you train neural networks — with epochs, (mini-)batchsize, learning rates, and validation gates — but without touching model weights. []( []( []( []( []( [](LICENSE) 📖 For installation, data preparation, training/eval commands, the full configuration reference, and framework internals, see the Documentation & Reproduction Guide — view it rendered online or via GitHub…

This collection bundles
2 skills1 command

⚠ The trust score below reflects the collection's repository only. The bundled units are not individually verified or scanned — review them before use.

Automatically indexed from public sources. Not yet verified by the developer on Forge.Claim this listing →
6kGitHub stars
621Forks
23d agoLast update
Package
Authormicrosoft
LicenseMIT
Sourcegithub
GitHubmicrosoft/SkillOpt
Trust Status
B
60/100Good
✓Listed in Forge index+10/10
—Publisher identity verified+0/25
→ Publisher: run `forge publish` from the package repo to claim ownership
—Ed25519 publish signature+0/10
→ Included automatically when the publisher runs `forge publish`
—Domain verification+0/5
→ Publisher: host /.well-known/forge.json on the package homepage with { "publisher": "<github-login>" }
—CVE scan · not run+0/30
→ Not yet scanned — package must be on npm
✓Static analysis · clean+20/20
—npm provenance (Sigstore)+0/5
→ Publish from GitHub Actions with the --provenance flag
Paste into Claude Code, Cursor, or any AI assistant to fix all gaps
StatusCommunity-indexed
PublisherUnverified
SignatureUnsigned
Domain—
Provenance—
DependenciesNot audited
Tool surface—
Security scan✓ CleanvHEAD · 19d ago
EvalsNone
IndexedJun 14, 2026

Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts — it cannot prove the absence of malicious code.

About

Train agent skills like you train neural networks — with epochs, (mini-)batchsize, learning rates, and validation gates — but without touching model weights. []( []( []( []( []( [](LICENSE) 📖 For installation, data preparation, training/eval commands, the full configuration reference, and framework internals, see the Documentation & Reproduction Guide — view it rendered online or via GitHub Pages. [2026-06-08] 😴 SkillOpt-Sleep is here — plugins for Claude Code, Codex, and Copilot. Give your…

Keywords
agent-skillsself-evolving-agentscollection