Loading...
Loading...
Found 365 Skills
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.
Manage models, datasets, columns, and relationships and query workspace storage with SQL using the Cargo CLI. Use when the user wants to inspect or modify data models, create or update columns, list datasets, set model relationships, understand the schema, or run SQL against storage.
Create custom LLM evaluation benchmarks using the BYOB decorator framework. Use when the user wants to (1) create a new benchmark from a dataset, (2) pick or write a scorer, (3) compile and run a BYOB benchmark, (4) containerize a benchmark, or (5) use LLM-as-Judge evaluation. Triggers on mentions of BYOB, custom benchmark, bring your own benchmark, scorer, or benchmark compilation.
Goldsky CLI command and flag reference — all valid subcommands, arguments, and options for goldsky turbo, pipeline, subgraph, secret, project, dataset, indexed, and telemetry. Consult before suggesting any goldsky command to avoid hallucinating invalid commands or flags.
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence. Should be invoked for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.
Analyze datasets to discover patterns, anomalies, and relationships. Use when exploring data files, generating statistical summaries, checking data quality, or creating visualizations. Supports CSV, Excel, JSON, Parquet, and more.
Use when you need to choose the right visualization for your data and question, then create a narrated report that highlights insights and recommends actions. Invoke when analyzing data for patterns (trends, comparisons, distributions, relationships, compositions), building dashboards or reports, presenting metrics to stakeholders, monitoring KPIs, exploring datasets for insights, communicating findings from analysis, or when user mentions "visualize this", "what chart should I use", "create a dashboard", "analyze this data", "show trends", "compare these metrics", "report on", "what does this data tell us", or needs to turn data into actionable insights. Apply to business analytics (revenue, growth, churn, funnel, cohort, segmentation), product metrics (usage, adoption, retention, feature performance, A/B tests), marketing analytics (campaign ROI, attribution, funnel, customer acquisition), financial reporting (P&L, budget, forecast, variance), operational metrics (uptime, performance, capacity, SLA), sales analytics (pipeline, forecast, territory, quota attainment), HR metrics (headcount, turnover, engagement, DEI), and any scenario where data needs to become a clear, actionable story with the right visual form.
Expert ReactFlow architect for building interactive graph applications with hierarchical node-edge systems, performance optimization, and auto-layout integration. Use when Claude needs to create or optimize ReactFlow applications for: (1) Interactive process graphs with expand/collapse navigation, (2) Hierarchical tree structures with drag & drop, (3) Performance-optimized large datasets with incremental rendering, (4) Auto-layout integration with Dagre, (5) Complex state management for nodes and edges, or any advanced ReactFlow visualization requirements.
Production-ready microscopy image analysis and quantitative imaging data skill for colony morphometry, cell counting, fluorescence quantification, and statistical analysis of imaging-derived measurements. Processes ImageJ/CellProfiler output (area, circularity, intensity, cell counts), performs Dunnett's test, Cohen's d effect size, power analysis, Shapiro-Wilk normality tests, two-way ANOVA, polynomial regression, natural spline regression with confidence intervals, and comparative morphometry. Supports CSV/TSV measurement tables, multi-channel fluorescence data, colony swarming assays, and neuron counting datasets. Use when analyzing microscopy measurement data, colony area/circularity, cell count statistics, swarming assays, co-culture ratio optimization, or answering questions about imaging-derived quantitative data.
Detects and redacts Personally Identifiable Information (PII) like emails, phone numbers, and credit cards. Use when cleaning logs, datasets, or communications to comply with GDPR/CCPA privacy standards.
Resolves shared ecosystem environment constants (HuggingFace credentials, dataset repo IDs, project root path) for any plugin without depending on internal shared libraries. V2 enforces Token Leakage constraints.