Mcp Safegen
Generate safer MCP servers from OpenAPI specs with pruning, auth templates, and tool scoring.
Ml Researcher Os
Agent skills and workflows for reproducible ML research.
Training Loop Debugger
Use when reviewing ML training code, suspicious metrics, unstable loss, broken evaluation, or a model that appears too good to be true.
Result Reporter
Use when summarizing experiment logs, benchmark outputs, ablations, failed runs, or model results into an honest research report.
Experiment Planner
Use when turning an ML hypothesis, paper claim, or model idea into a reproducible experiment plan with baselines, metrics, seeds, risks, and expected artifacts.
Hf Release Prep
Use when preparing Hugging Face model cards, dataset cards, Space demos, or release notes for ML artifacts.
Reproducibility Auditor
Use when auditing an ML repository, experiment folder, model release, or paper reproduction for missing files, hidden assumptions, and rerun readiness.
Paper Claim Extractor
Use when reading an ML paper, abstract, README, or result section and the task is to extract claims, assumptions, experiments, limitations, or implementation requirements.