Data analysis, machine learning, LLM apps, and prompt design (9.1K skills)
Build JavaScript or TypeScript applications that run text, image, and audio models in browsers or server runtimes. Guides compatible model selection, GPU or CPU execution, caching, and memory cleanup without requiring a Python server.
Evaluate Hugging Face Hub models using inspect-ai or lighteval, with local inference or a provider-backed option. Choose an inference engine, start with a small test, and switch engines when model compatibility requires it.
Explore Hugging Face datasets through the Dataset Viewer API. Preview and retrieve rows, search text, filter records, inspect sizes and column statistics, and find Parquet download links for further analysis or data extraction.
Manage Hugging Face Hub through the hf command line tool. Download and upload models or datasets, organize cloud storage, manage authentication and local caches, run scheduled jobs, and deploy or maintain model inference services.
Write and debug code for further training large language models with TRL. Match training methods to dataset formats, configure supervised or preference-based training, and set up reward functions through Python or the command line.
Train sentence-transformers models for search, similarity, and reranking, which reorders search results by relevance. Choose a model type, prepare data, configure training, compare results against a baseline, and publish the trained model to Hugging Face Hub.
Find and run local AI models with llama.cpp. Choose GGUF model files and quantization levels that fit available memory, launch a command line session or local server, and test an OpenAI-compatible API on your computer.
Find AI models for a specific task using official Hugging Face benchmark leaderboards. Compare scores, model sizes, and licenses, with memory-based estimates of device suitability and flags for models requiring quantization or API access.
Build and publish a browser demo for a supplied LoRA, a model adaptation for image or video tasks. Tailor the Gradio interface to its inputs and follow the model’s recommended settings on Hugging Face Spaces.
Fine-tune vision models on custom images using Hugging Face Jobs cloud GPUs. Covers object detection, image classification, and segmentation—identifying image regions—with dataset validation, hardware selection, cost estimates, monitoring, and saving trained models to the Hub.
Train or fine-tune language and vision models on Hugging Face Jobs without a local GPU. Covers dataset checks, hardware and cost planning, training monitoring, Hub storage, and GGUF conversion for local use.
Estimate inference memory for models on Hugging Face Hub without downloading their weights. Check GPU capacity for Safetensors or GGUF files, with optional estimates for the KV cache, memory used to retain attention data during generation.
Track machine learning experiments with Trackio by recording training measurements, viewing live dashboards, and flagging diagnostic events. Retrieve metrics and alerts through command-line queries, with JSON output for automated monitoring and experiment review.
Create charts for numeric data and diagrams for processes or relationships. Explains how to choose ECharts or Mermaid, apply clear formatting, and use chart_render to display the result in chat and save a downloadable PNG.
Use defined customer and order tables to build sales analysis queries with consistent business rules. Calculate revenue from completed orders, rank customers by spending, and identify high-value orders using the supplied thresholds and SQL example.
Have Claude and GPT critique each other's answers, revise their positions, and work toward a combined response. Choose the number of rounds and see what changed, where they agree, and which disagreements remain.
Retrieve financial data for Chinese markets and selected global markets using akshare-cli. Find stock prices, fund values, exchange rates, economic indicators, and financial news, then extract recent records or save results in common file formats.
Route requests to general assistance, medical source checks, educational answers, structured learning, or registration and subscriptions. It considers the intended use rather than isolated medical words, and refuses high-risk requests such as individual diagnosis or prescription dosing.
Prepare an AI-SPEC.md design agreement for an AI development phase. The skill coordinates framework selection, documentation and domain research, and evaluation planning so the phase has a defined technical direction and assessment strategy.
Turn raw data into an Excel workbook with cleaned records, formula-based summaries, and charts. Get three to five plain-language conclusions grounded in figures, with possible explanations or recommendations and clear acknowledgment when the data is insufficient.
Clean customer lists and combine inconsistent tables using agreed rules for duplicates, dates, numbers, and text. Receive an Excel workbook with the original data, cleaned results, cleaning rules, and a record of changes for review.
Turn historical sales data into an Excel forecast with trends, seasonal patterns, uncertainty bands, and optimistic, base, and pessimistic scenarios. Adjustable assumptions and sensitivity tables show how changes in key inputs affect annual totals.
Clean raw survey responses and produce an Excel analysis workbook plus a Word findings report. Summarize each question, compare respondent groups, chart key results, and organize open-ended answers into themes while documenting exclusions and sample limitations.
Turn sales, customer, finance, or operations data into an Excel dashboard with clear metric definitions, targets, actual results, achievement rates, and trend charts. Review strong and weak performance alongside unusual changes over time.