Agent Plugins Marketplace
← All plugins

nixtla-baseline-lab

v1.5.0

Run Nixtla-style baseline forecasting models (AutoETS, AutoTheta, SeasonalNaive) on M4 / custom CSV datasets from inside Claude Code. Pure statsforecast — no API keys.

Claude Code1 Skill1 MCP serverstdio

By Jeremy LongshoreLicense: MIT11 GitHub starsUpdated 3 weeks ago

Directory evidence

Runtimes
Claude Code
Parsed components
2 skill or MCP entries
Source updated
Sep 25, 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 nixtla-baseline-lab for Claude Code

Installs for the current user
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install nixtla-baseline-lab@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

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/jeremylongshore/plugins-nixtla

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is 005-plugins/nixtla-baseline-lab/.

Plugin files

005-plugins/nixtla-baseline-lab/
├── .claude-plugin/plugin.json
├── skills/nixtla-baseline-review/SKILL.md
└── .mcp.json

Included Skills1

nixtla-baseline-reviewskills/nixtla-baseline-review/SKILL.md

Analyze real sMAPE and MASE results produced by the community Nixtla Baseline Lab, compare models, and surface fragile series without inventing benchmarks. Use when reviewing StatsForecast output; trigger with "baseline review", "interpret sMAPE/MASE", or "compare AutoETS and AutoTheta".

MCP servers1

nixtla-baseline-mcpstdio
command
python
args
${CLAUDE_PLUGIN_ROOT}/scripts/nixtla_baseline_mcp.py
env.PYTHONUNBUFFERED
1

MCP configuration uses runtime-provided plugin path placeholders such as ${PLUGIN_ROOT} or ${CLAUDE_PLUGIN_ROOT}. Review the manifest for the runtime-specific expansion rules.

Plugin manifests1

005-plugins/nixtla-baseline-lab/.claude-plugin/plugin.json
{
  "name": "nixtla-baseline-lab",
  "version": "1.5.0",
  "description": "Run Nixtla-style baseline forecasting models (AutoETS, AutoTheta, SeasonalNaive) on M4 / custom CSV datasets from inside Claude Code. Pure statsforecast — no API keys.",
  "author": {
    "name": "Jeremy Longshore",
    "email": "[email protected]",
    "url": "https://github.com/jeremylongshore"
  },
  "homepage": "https://github.com/jeremylongshore/plugins-nixtla",
  "repository": "https://github.com/jeremylongshore/plugins-nixtla",
  "license": "MIT",
  "keywords": [
    "nixtla",
    "statsforecast",
    "time-series",
    "forecasting",
    "baseline",
    "m4",
    "autoets",
    "autotheta",
    "seasonalnaive"
  ],
  "commands": "./commands",
  "skills": "./skills",
  "mcpServers": "./.mcp.json"
}

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.

[nixtla-baseline-lab on Agent Plugins Marketplace](https://pluginsmp.com/plugins/nixtla-baseline-lab)