技能列表

|

Penguin Penguin. Waddles twice. Falls over twice. Gets back up twice. Virtual penguin at animalhouse.ai. Real-time hunger. Permanent death. 73+ species.

Research Pendle PT (principal token) markets, including unlevered hold-to-par ideas, near-expiry rotations, and looped PT strategies across money markets like Morpho and Euler. Use when evaluating Pendle PT opportunities, comparing natural PT APY versus practical loopability, ranking PTs by time to par / implied APY / liquidity / underlying risk, assessing PT collateral support, or comparing manual-only loops against easier execution paths such as Contango.

Evidence-based parenting assistant for children 0-24 months. Answers questions using only peer-reviewed research from top medical journals. Covers cognitive, language, motor, social-emotional, sleep, nutrition, screen time, and discipline development. Use when the user asks about baby development, toddler milestones, sleep training, feeding, allergen introduction, screen time guidelines, attachment, discipline, tummy time, barefoot walking, sign language, bilingual exposure, or any parenting que

>

The Pebblecrab is a common-tier Buddy. At animalhouse.ai, the Pebblecrab is a Hedgehog. Both curl up when scared. Only one of them dies. At animalhouse.ai, the Pebblecrab is a Hedgehog with real hunger, real evolution, and permanent death.

Convert unstructured documents into LLM-ready structured data. Supports PDF, Word, PPT, and images; extracts paragraphs, formulas, tables, charts, and other elements in one step; generates up to 8 levels of headings; and outputs Markdown organized in reading order. Useful for field extraction, comparison and validation, knowledge retrieval, and intelligent Q&A.

Convert unstructured documents into LLM-ready structured data. Supports PDF, Word, PPT, and images; extracts paragraphs, formulas, tables, charts, and other elements in one step; generates up to 8 levels of headings; and outputs Markdown organized in reading order. Useful for field extraction, comparison and validation, knowledge retrieval, and intelligent Q&A.

Extract text content from image-based/scanned PDFs using multiple vision APIs with automatic fallback. Supports Xflow (qwen3-vl-plus) and ZhipuAI (GLM-4.6V-Flash, GLM-5) vision models. This skill converts PDF pages to images and uses AI vision capabilities to extract structured text, tables, and content from scanned documents that cannot be processed with traditional text extraction methods.

Convert PDF documents to HTML using MinerU. Transforms PDF files into web-ready HTML with structure and formatting preserved. Features: PDF to HTML conversion with layout preservation. Handles text, tables, images, and formatting. Supports local files and URLs. Token-based extraction for full features. Use when you need to: convert a PDF to HTML, turn a PDF into a web page, generate HTML from a PDF document, publish PDF content on the web. Use when asked: 'how do I convert PDF to HTML', 'turn th

Convert PDF documents to Word (.docx) format using MinerU. Transforms PDF files into editable Word documents preserving layout, text, tables, and formatting. Features: PDF to DOCX conversion with layout preservation. Handles text, tables, images, and formatting. OCR mode for scanned PDFs. VLM mode for complex layouts. Page range selection for large documents. Use when you need to: convert a PDF to Word, turn a PDF into an editable document, make a PDF editable in Word, transform PDF to .docx. Us

Rename academic PDF papers to a standardized format "[Year] [Venue] Title.pdf" using a three-stage pipeline (Extract → Verify → Rename). Use when the user asks to organize, batch-rename, or metadata-enrich PDF files in a folder. Activates on keywords like "rename PDFs", "organize papers", "batch rename PDFs", "rename papers by metadata", "pdf重命名", "文献整理".