Agent Plugins Marketplace
← All plugins

langsmith-evals

v1.1.0

Prompt Engineering, engenharia e auditoria de evals agenticos LangSmith-first: prompts, datasets, evaluators, experiments, backtests e gates de promocao.

Codex1 Skill

By Carlos AraujoLicense: MIT0 GitHub starsUpdated 3 days ago

Directory evidence

Runtimes
Codex
Parsed components
1 skill or MCP entry
Source updated
Sep 21, 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 langsmith-evals for Codex

Installs for the current user
codex plugin marketplace add cadugevaerd/codex-skills
codex plugin marketplace upgrade codex-skills
codex plugin add langsmith-evals@codex-skills

Paste and run these commands in a terminal with Codex. They add and refresh the codex-skills catalog, then install this plugin.

Compatibility: the page URL and API slug “langsmith-evals-2” remain stable.

  • Codex: langsmith-evals-2@agent-plugin-marketplace → langsmith-evals@codex-skills

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/cadugevaerd/codex-skills

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/langsmith-evals/.

Plugin files

plugins/langsmith-evals/
├── .codex-plugin/plugin.json
└── skills/langsmith-evals/SKILL.md

Included Skills1

langsmith-evalsskills/langsmith-evals/SKILL.md

Especialista LangSmith-first para projetar, implementar, executar e auditar evals de chatbots, RAG, agentes, nodes e grafos; criar datasets/evaluators/experiments/backtests; comparar modelos e aplicar gates de promocao com evidencia. Use em qualquer mudanca de modelo, prompt, tool, retrieval, LangGraph ou comportamento agentico que precise de qualidade mensuravel.

Plugin manifests1

plugins/langsmith-evals/.codex-plugin/plugin.json
{
  "name": "langsmith-evals",
  "version": "1.1.0",
  "description": "Prompt Engineering, engenharia e auditoria de evals agenticos LangSmith-first: prompts, datasets, evaluators, experiments, backtests e gates de promocao.",
  "author": {
    "name": "Carlos Araujo",
    "email": "[email protected]",
    "url": "https://github.com/cadugevaerd"
  },
  "homepage": "https://github.com/cadugevaerd/codex-skills",
  "repository": "https://github.com/cadugevaerd/codex-skills",
  "license": "MIT",
  "keywords": [
    "langsmith",
    "prompt-engineering",
    "evals",
    "datasets",
    "experiments",
    "backtesting",
    "llm-as-judge",
    "langgraph"
  ],
  "skills": "./skills/",
  "interface": {
    "displayName": "LangSmith Evals",
    "shortDescription": "Otimiza prompts e executa evals no LangSmith.",
    "longDescription": "Usa LangSmith como control plane para prompts, datasets, experiments, feedback e backtests, preservando pytest e oraculos deterministicos. Inclui Prompt Engineer, Evals Engineer e Auditor com papeis separados.",
    "developerName": "Carlos Araujo",
    "category": "Development",
    "capabilities": [
      "LangSmith",
      "Prompt Engineering",
      "LLM Evals",
      "Agent Evaluation",
      "Backtesting",
      "Model Comparison"
    ],
    "defaultPrompt": [
      "/langsmith-evals use o Prompt Engineer para otimizar este prompt com baseline e candidatos pareados",
      "/langsmith-evals desenhe e execute o eval deste agente",
      "/langsmith-evals audite os experiments e emita GO/NO-GO"
    ]
  }
}

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.

[langsmith-evals on Agent Plugins Marketplace](https://pluginsmp.com/plugins/langsmith-evals-2)