Loading...
Loading...
Found 331 Skills
Build automated evaluation suites for AI agents using golden datasets, rubrics, and regression gates.
Create diverse synthetic test inputs for LLM pipeline evaluation using dimension-based tuple generation. Use when bootstrapping an eval dataset, when real user data is sparse, or when stress-testing specific failure hypotheses. Do NOT use when you already have 100+ representative real traces (use stratified sampling instead), or when the task is collecting production logs.
Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using Hugging Face Transformers on Hugging Face Jobs cloud GPUs. Covers COCO-format dataset preparation, Albumentations augmentation, mAP/mAR evaluation, accuracy metrics, SAM segmentation with bbox/point prompts, DiceCE loss, hardware selection, cost estimation, Trackio monitoring, and Hub persistence. Use when users mention training object detection, image classification, SAM, SAM2, segmentation, image matting, DETR, D-FINE, RT-DETR, ViT, timm, MobileNet, ResNet, bounding box models, or fine-tuning vision models on Hugging Face Jobs.
Use this skill when the user wants to search the DataHub catalog, discover entities, answer ad-hoc questions about their data, find datasets, or browse by platform or domain. Triggers on: "search DataHub", "find datasets", "who owns X", "what tables contain PII", "what columns does X have", or any request to search, discover, browse, or answer one-off questions about DataHub metadata. For lineage questions ("what feeds into X"), use `/datahub-lineage`. For systematic audits ("how complete is our metadata"), use `/datahub-audit`.
Find and read academic papers: disambiguate queries, discover papers (search, citation traversal, recommendations, arXiv monitoring, trending, GitHub search), evaluate (TLDR, citations, code, SOTA), and read with structured analysis (3-level strategy). Use when: finding papers, reading a paper, related work, citation analysis, research trends, SOTA results, datasets. Do NOT use for generating literature survey reports (use research-survey), generating research ideas (use research-ideation), writing a paper's Related Work section (use paper-writing), comparing/ranking research ideas (use research-ideation), or planning paper structure (use paper-planning).
Expert skill for using Future AGI — the open-source end-to-end platform for evaluating, observing, and improving LLM and AI agent applications with tracing, evals, simulations, datasets, gateway, and guardrails.
Run cross-framework agent comparisons using evaluatorq from orqkit — compares any combination of agents (orq.ai, LangGraph, CrewAI, OpenAI Agents SDK, Vercel AI SDK) head-to-head on the same dataset with LLM-as-a-judge scoring. Use when comparing agents, benchmarking, or wanting side-by-side evaluation. Do NOT use when comparing only orq.ai configurations with no external agents (use run-experiment instead).
Build reliable data pipelines and analytics-ready datasets. USE when cleaning data, designing ETL/ELT, defining contracts, or shipping reproducible data workflows.
Prepare, audit, or revise Nature-ready Data Availability statements, data repository plans, dataset citations, and FAIR metadata checklists for manuscripts. Use when the user asks about Nature data availability, research data sharing, repository selection, accession numbers, restricted or sensitive data, source data, supplementary datasets, DataCite-style dataset references, FAIR metadata for academic publication, or Chinese-to-English data availability wording for Chinese-speaking authors preparing Nature-family submissions.
Provision and manage GPU pods on RunPod for long-running experiments. Use when the user needs persistent GPU compute with SSH access, large datasets, or multi-step experiments.
Find implementable ML training recipes from papers, datasets, docs, and code. Use when the user wants to fine-tune, train, reproduce, or choose a practical ML method, dataset, hyperparameter setup, or benchmark recipe.
Data file fetching and caching for geoscience applications. Download sample datasets with automatic caching, checksum verification, and multiple download sources. Use when Claude needs to: (1) Download datasets from URLs or DOIs, (2) Cache files locally with automatic verification, (3) Verify file integrity with SHA256/MD5 hashes, (4) Extract compressed archives (ZIP, TAR, GZIP), (5) Create data registries for reproducible workflows, (6) Fetch from Zenodo or other repositories.