machine learning plugins

48 tagged machine learning, measured the same way as everything else here.

Browse within: data-science 7

lean-explore

26

justincasher/lean-explore

Plugin Claude Code

Search Lean 4 declarations through the hosted LeanExplore MCP server.

76 1mo ago A tokens not measured Apache-2.0

scholar-feed

28

YGao2005/scholar-feed-mcp

Plugin Claude Code

Scholar Feed: research-paper search and literature-review tools for Claude Code.

10 6d ago A tokens not measured original MIT

scholar-feed

29

YGao2005/scholar-feed-mcp

Plugin Claude Code

Search 600,000+ CS/AI/ML papers with LLM novelty analysis, citation graph, full-text extraction, and BibTeX, without leaving Claude Code. Built for literature reviews.

10 6d ago A tokens not measured original MIT

mcpbr

30

greynewell/mcpbr

Plugin Claude Code

mcpbr - MCP Benchmark Runner plugin marketplace.

10 4mo ago A tokens not measured original MIT

mcpbr

31

greynewell/mcpbr

Plugin Claude Code

Expert benchmark runner for MCP servers using mcpbr. Handles Docker checks, config generation, and result parsing.

10 4mo ago A tokens not measured original MIT

tidymodels-skills

32

tidymodels/skills

Plugin Claude Code

Plugin marketplace listing 2 plugins: tidymodels-developers, tidymodels-users.

9 4d ago A tokens not measured

tidymodels-skills

33

tidymodels/skills

Plugin Claude Code

Claude Code skills for the Tidymodels ecosystem — developer tools for building extensions and user guides for data analysis and modeling.

9 4d ago A tokens not measured

nixtla-plugins

34

jeremylongshore/plugins-nixtla

Plugin Claude Code

Plugin marketplace listing 3 plugins: nixtla-baseline-lab, nixtla-bigquery-forecaster, nixtla-search-to-slack.

9 7d ago A tokens not measured

jeremylongshore/plugins-nixtla

Plugin Claude Code

Real changelog automation. Fetches data from GitHub (gh CLI), git log, and optional Slack (slack-sdk + NIXTLASLACKTOKEN). Validates frontmatter against jsonschema. Loads + validates .changelog-config.json.

9 7d ago A tokens not measured

jeremylongshore/plugins-nixtla

Plugin Claude Code

Real Apache Airflow tooling for TimeGPT forecasting pipelines. Generate production-ready DAGs (BigQuery / Snowflake / Postgres / S3 sources), AST + DagBag-based DAG validation with credential lint, real Airflow Connection JSON for 5 source types, and pytest test modules that load the DAG via DagBag.

9 7d ago A tokens not measured

superpowers-ml

38

pengzhangzhi/superpowers-ml

Plugin Claude Code

Superpowers core skills plus a conservative ML-research layer (verification rungs, experiment design, result review). Fork of obra/superpowers.

8 8d ago A tokens not measured original MIT

experiment-audit

43

SreeDharshan-GJ/experiment-audit

Plugin Claude Code

Scientific Research Reasoning Engine for evaluating experimental and empirical claims — auditing ML training runs, ablations, and sweeps; reviewing papers; checking reproducibility; and producing structured research reports. Optional Weights & Biases integration via the experiment-audit-mcp server.

4 6d ago A tokens not measured original MIT

last-ds-mile

44

StamKavid/last-ds-mile

Plugin Claude Code

A guided data-science lifecycle for Claude Code, with leakage and honesty checks built into every stage.

3 24d ago A tokens not measured original MIT

last-ds-mile

45

StamKavid/last-ds-mile

Plugin Claude Code

A guided data-science lifecycle for Claude Code: frame, explore, baseline, validate, model, evaluate, and report — with leakage and honesty checks built into every stage.

3 24d ago A tokens not measured original MIT

agentic-ml

47

lawwu/agentic-ml-plugin

Plugin Claude Code

Skills for machine learning workflows: monitoring training runs, debugging models, and managing experiments.

3 5mo ago A tokens not measured

predictalot

48

psyb0t/docker-predictalot

Plugin Claude CodeCodex

Self-hosted forecasting service — zero-shot time-series forecasting (chronos-2, timesfm-2.5, moirai-2, toto-1, sundial-base-128m) across univariate, multivariate, covariate, and sample-path types, plus supervised tabular ML (9 backends, 3 meta-learners) with train+persist and weighted ensembles. Unified REST + MCP…

2 1mo ago A tokens not measured WTFPL