Docker workbench 및 Agent Skills for running deterministic evals against Agent skills.

두 가지 방법으로이 재포를 사용합니다.

• skill-optimizer] 기술/플러그인을 에이전트로 설치하여 저자와 디버그 eval 제품군을 만들 수 있습니다.
• OpenRouter 모델에 대한 Docker의 경우와 스위트를 실행하려면 로컬 CLI를 실행하십시오.

설치

임명은 대리인에 의하여 다릅니다. canonical 기술은 skills/skill-optimizer/SKILL.md; 모든 플러그인은 같은 파일에 점을 나타납니다.

Claude 코드

Claude Code 플러그인 마켓 플레이스로 이 저장소를 등록하십시오:

그런 다음 플러그인을 설치:

OpenAI 코덱 CLI

Codex 플러그인 마켓 플레이스로 이 저장소를 등록하십시오:

그런 다음 플러그인 검색 인터페이스를 엽니 다 :

skill-optimizer을 선택하고 설치하십시오.

OpenAI Codex 앱

Codex 앱에서 사이드바에서 플러그인을 열고 skill-optimizer]을 검색하고 코딩 섹션에서 설치합니다.

나열되지 않은 경우 Codex CLI에서 설치하십시오.

# # # 커서

열린 기술 CLI와 기술을 설치:

커서도 GitHub에서 설정 -> 규칙 -> 프로젝트 규칙 -> 규칙을 추가 -> 원격 규칙 (Github). Cursor 플러그인 메타데이터는 .cursor-plugin/plugin.json에 살고 있습니다.

오픈코드

OpenCode를 말한다:

skill-optimizer

Docker workbench and Agent Skill for running deterministic evals against agent skills.

Use this repo in two ways:

• Install the skill-optimizer skill/plugin into your agent so it can author and debug eval suites.
• Run the local CLI to execute cases and suites in Docker against OpenRouter models.

Installation

Installation differs by agent. The canonical skill is skills/skill-optimizer/SKILL.md; every plugin manifest points at that same file.

Claude Code

Register this repository as a Claude Code plugin marketplace:

/plugin marketplace add fastxyz/skill-optimizer

Then install the plugin:

/plugin install skill-optimizer@skill-optimizer

OpenAI Codex CLI

Register this repository as a Codex plugin marketplace:

codex plugin marketplace add fastxyz/skill-optimizer

Then open the plugin search interface:

/plugins

Select skill-optimizer and install it.

OpenAI Codex App

In the Codex app, open Plugins from the sidebar, search for skill-optimizer, and install it from the Coding section.

If it is not listed, install it from Codex CLI first:

codex plugin marketplace add fastxyz/skill-optimizer

Cursor

Install the skill with the open skills CLI:

npx skills add fastxyz/skill-optimizer --skill skill-optimizer -a cursor -y

Cursor can also import the skill from GitHub via Settings -> Rules -> Project Rules -> Add Rule -> Remote Rule (Github). The Cursor plugin metadata lives at .cursor-plugin/plugin.json.

OpenCode

Tell OpenCode:

Fetch and follow instructions from https://raw.githubusercontent.com/fastxyz/skill-optimizer/refs/heads/main/.opencode/INSTALL.md

Or add the plugin to opencode.json at user or project scope:

{
  "plugin": ["skill-optimizer@git+https://github.com/fastxyz/skill-optimizer.git"]
}

Restart OpenCode. See docs/README.opencode.md for details.

Gemini CLI

Install the Gemini extension from GitHub:

gemini extensions install https://github.com/fastxyz/skill-optimizer

To update:

gemini extensions update skill-optimizer

Skill-Only Install

If you only want the skill files without plugin metadata, use the open skills CLI:

npx skills add fastxyz/skill-optimizer --skill skill-optimizer -a claude-code -a opencode -a codex -a cursor -y

Local CLI Setup

Requirements:

• Node.js 20+
• Docker
• OPENROUTER_API_KEY for real model runs

Install and build:

npm install
npm run build

Only openrouter/... model refs are supported.

Quick Start

Run the suite against the models listed in suite.yml:

npx tsx src/cli.ts run-suite examples/workbench/pdf/suite.yml --trials 1

Run one case directly:

npx tsx src/cli.ts run-case ./case.yml --model openrouter/google/gemini-2.5-flash

CLI help:

npx tsx src/cli.ts --help
npx tsx src/cli.ts run-case --help
npx tsx src/cli.ts run-suite --help