Loading...
Loading...
Found 66 Skills
Use to interpret qualitative feedback, trends, and risks across community channels.
AI text humanization: reduce AI-detection patterns, natural phrasing, tone adjustment
Coordinate smart-home actions across existing integrations with clear dry-run and safety confirmation.
Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.
Aggregate news from popular cryptocurrency RSS feeds, analyze sentiment of articles, and calculate an overall market sentiment score with detailed explanation. Use when assessing crypto market sentiment for trading decisions, research, or monitoring trends from RSS sources.
10 data wrangling skills. Trigger: messy data, format conversion, missing values, data reshaping. Design: pipeline-oriented recipes for common data cleaning and transformation tasks.
Use when "HuggingFace Transformers", "pre-trained models", "pipeline API", or asking about "text generation", "text classification", "question answering", "NER", "fine-tuning transformers", "AutoModel", "Trainer API"
This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets.
World-class alternative data and sentiment analysis for trading - social media, news, on-chain data, positioning. Extract alpha from information others miss. Use when "sentiment, alternative data, social media trading, news trading, twitter signals, on-chain, whale watching, fear greed, positioning, " mentioned.
Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need multilingual support, CJK languages, or reproducible tokenization.
Detect and remove AI-generated writing patterns from text while preserving semantic meaning and factual accuracy. Rewrites text to sound natural, varied, and human-authored across domains including academic, technical, blog, professional, and social media writing. Use this skill when the user asks to "humanize text", "make this sound human", "remove AI patterns", "rewrite to sound natural", "make this less AI", "de-slop this", "clean up AI writing", "make this not sound like ChatGPT", or provides AI-generated text and asks for a natural rewrite. Also trigger when reviewing drafts for AI tells, checking if text sounds AI-generated, or requesting a "human pass" on content.
Datumbox integration. Manage Organizations, Users, Goals, Filters. Use when the user wants to interact with Datumbox data.