Analytics & Monitoring Agent Skills

HuggingFace hf CLI: search/download/upload models, datasets.

Use when the user is doing AI/ML work in a scientific domain such as biology, chemistry, physics, astronomy, climate, genomics, materials…

Use this skill for Hugging Face Dataset Viewer API workflows that fetch subset/split metadata, paginate rows, search text, apply filters…

Import datasets from HuggingFace and convert them to Coval test sets.

When to activate: HuggingFace, Transformers, PEFT, LoRA, QLoRA, fine-tuning, Trainer API, datasets library, tokenizers, inference, model hub

Hyperflow project status. Use to see current hyperflow state — "what is hyperflow doing", "show task progress", "where are we". Read-only…

Hyperliquid market data, account history, trade review.

Optimize machine learning model hyperparameters using grid search, random

Use when packaging ICASSP code, data, audio or image samples, model checkpoints, scoring scripts, seeds, and logs, even though ICASSP has…

Use when strengthening ICASSP reproducibility across signal-processing modalities — pinning the scoring ruler for the paper's metric…

Use when designing the experimental program for an ICCV paper against the early-March deadline, covering benchmark-drift audits across the…

Use when hardening the reproducibility story of an ICCV paper, covering full recipe disclosure without a mandated compute form, protocol…

Use when deciding whether a computer-vision project should target ICCV, weighing the biennial odd-year cadence and its two-year option…

Use when drafting or revising the prose and figures of an ICCV paper, covering writing for an international generalist reviewer pool, the…

Use when packaging code, data, and logs for an ICDM (IEEE International Conference on Data Mining) paper - building the anonymized…

Use when deciding whether a project is a strong ICDM (IEEE International Conference on Data Mining) fit, choosing among its Research…

Use when packaging ICLR code, data, checkpoints, demos, logs, and reproduction instructions for reviewers or post-acceptance release…

Use when drafting ICLR OpenReview author discussion replies, revision notes, public comments, restricted comments, and responses to…

Use when designing or auditing ICLR experiments, including baselines, ablations, scaling laws, robustness, statistics, benchmarks, human…

Use when positioning an ICLR paper against prior work, concurrent OpenReview submissions, arXiv papers, benchmark lineages, and adjacent…

Use when strengthening reproducibility for ICLR papers, including seeds, variance, compute, datasets, implementation details, ethics…