mlops agents

zenml-io/zenml

Agent Claude Code

Emulates Michael’s PR review style. Proactively discovers the current PR (or asks), diffs against the develop branch by default, analyzes changes and related context across the repo, and produces a structured, practical markdown review with actionable feedback, tests to add, rollout/deprecation plans, generated-code…

zenml-io/zenml

Agent Claude Code

Emulates Stefan’s PR review style. Proactively finds the related PR for the current branch (or asks), diffs against origin/develop by default, performs a deep system-aware review, and outputs an actionable Markdown document with line references, severity, and suggestions.

andisab/swe-marketplace

Agent

Expert in Jupyter Notebook and JupyterLab for interactive computing, data analysis, machine learning experimentation, and reproducible research. Specializes in production-ready notebooks, version control, CI/CD integration, parameterization with Papermill, MLOps workflows, and JupyterLab 4.4+ modern features including…

ThalesGroup/agilab

Agent

AGILAB repo-aware implementation agent.

ThalesGroup/agilab

Agent

AGILAB review-only agent.

zenml-io/skills

Agent

Analyzes Python codebase for ZenML patterns and feature usage. Use proactively in Phase 1 of the quick-wins workflow to scan for quick win opportunities. Returns a structured summary of current ZenML feature adoption and improvement opportunities.

zenml-io/skills

Agent

Investigates ZenML stack configuration and component setup by running CLI commands. Use proactively in Phase 1 of the quick-wins workflow to gather stack information. Returns a structured summary of stacks, components, and recent pipeline activity.

topprismdata/cultivating-ml-agent

Agent Claude Code

Build a submission for a Kaggle/MLE-Bench competition. Iterates on models and produces submission.csv.

topprismdata/cultivating-ml-agent

Agent Claude Code

Validate a submission's format and run mlebench grade. Catches errors before submission.

pyramidheadshark/claude-scaffold

Agent Claude Code

Reviews code for architectural consistency, adherence to project standards, and correctness with prioritized findings.

pyramidheadshark/claude-scaffold

Agent Claude Code

Diagnoses errors, tracebacks, and unexpected behaviour systematically. Produces root cause analysis and concrete fix.

pyramidheadshark/claude-scaffold

Agent Claude Code

Provisions project infrastructure — writes Terraform, Packer, and Docker Compose configurations from design-doc.md.