skillopt
v0.1.0+codex.20260622193805Use Microsoft SkillOpt to train reusable agent skill documents from scored rollouts.
By Eidos AGILicense: MIT0 GitHub starsUpdated 2 weeks ago
Directory evidence
- Runtimes
- Codex and Claude Code
- Parsed components
- 1 skill or MCP entry
- Source updated
- Oct 4, 2026
- Manifest status
- Canonical path parsed
The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →
Install skillopt for Codex and Claude Code
codex plugin marketplace add eidos-agi/eidos-marketplace
codex plugin marketplace upgrade eidos-agi
codex plugin add skillopt@eidos-agiPaste and run these commands in a terminal with Codex. They add and refresh the eidos-agi catalog, then install this plugin.
Compatibility: the page URL and API slug “skillopt” remain stable.
- Codex:
skillopt@agent-plugin-marketplace→skillopt@eidos-agi
The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.
Get the source manually
git clone https://github.com/eidos-agi/eidos-marketplaceClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/skillopt/.
Plugin files
├── .codex-plugin/plugin.json├── .claude-plugin/plugin.json└── skills/use-skillopt/SKILL.md
Included Skills1
Use when the user wants Microsoft SkillOpt, self-evolving agent skills, skill optimization from rollouts, validation-gated skill edits, token-cost reduction, thrashing detection, or Tokut/Token Cut remediation.
Plugin manifests2
{
"name": "skillopt",
"version": "0.1.0+codex.20260622193805",
"description": "Use Microsoft SkillOpt to train reusable agent skill documents from scored rollouts.",
"author": {
"name": "Eidos AGI",
"email": "[email protected]",
"url": "https://github.com/eidos-agi"
},
"homepage": "https://github.com/microsoft/SkillOpt",
"repository": "https://github.com/microsoft/SkillOpt",
"license": "MIT",
"keywords": [
"skillopt",
"agent-skills",
"skill-optimization",
"token-cost",
"tokut",
"eidos",
"codex"
],
"skills": "./skills/",
"interface": {
"displayName": "SkillOpt",
"shortDescription": "Train reusable skills from scored agent rollouts.",
"longDescription": "SkillOpt brings Microsoft Research's text-space optimizer into the Eidos workflow. Use it to turn rollout evidence, validation scores, and token-waste patterns into bounded edits on a deployable skill document, including Tokut-style remediation loops for thrashing and runaway AI cost.",
"developerName": "Eidos AGI",
"category": "Developer Tools",
"capabilities": [
"Skill Optimization",
"Rollout Analysis",
"Validation Gates",
"Token Waste Remediation",
"Tokut Workflow",
"CLI Bootstrap"
],
"websiteURL": "https://github.com/microsoft/SkillOpt",
"privacyPolicyURL": "https://github.com/microsoft/SkillOpt/security",
"termsOfServiceURL": "https://github.com/microsoft/SkillOpt",
"defaultPrompt": [
"Use SkillOpt to optimize this agent skill from scored rollouts.",
"Use SkillOpt to turn token-thrashing evidence into a better skill.",
"Bootstrap Microsoft SkillOpt for a local Eidos experiment."
],
"brandColor": "#2563EB"
}
}{
"name": "skillopt",
"version": "0.1.0",
"description": "Use Microsoft SkillOpt to train reusable agent skill documents from scored rollouts.",
"author": {
"name": "Eidos AGI",
"email": "[email protected]",
"url": "https://github.com/eidos-agi"
},
"homepage": "https://github.com/microsoft/SkillOpt",
"repository": "https://github.com/microsoft/SkillOpt",
"license": "MIT",
"keywords": [
"skillopt",
"agent-skills",
"skill-optimization",
"token-cost",
"tokut",
"eidos",
"claude-code"
],
"skills": "./skills/"
}For maintainers
If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.
[skillopt on Agent Plugins Marketplace](https://pluginsmp.com/plugins/skillopt)