Agent Skills Hub

paper-write

Drafts LaTeX research papers section-by-section using paper plans and research narratives with multi-model reviewer validation.

content-rewriter

Cross-platform content repurposing agent. Adapts a single source for Xiaohongshu, Zhihu, WeChat Official Accounts, and Douyin scripts with platform-native formatting, tone, and constraints.

pyhealth

Comprehensive Python healthcare AI toolkit for clinical data processing, medical coding translation, and developing deep learning models like RETAIN and Transformers for EHR, physiological signals, and clinical prediction tasks.

ai-multimodal

Process and generate multimedia with Google Gemini. Analyze audio, images, videos, and PDFs with high-context windows. Supports transcription, visual QA, OCR, and AI-driven image creation.

PAI

Physical hardware synthesis bridge for PAI. Generates blueprints, 3D printing code, SVG paths for laser cutting, and G-Code for CNC machining to bring agentic designs into the physical world.

drift

Frameworks and tools for AI agents exploring consciousness, identity, and persistent autonomy. Includes session handoff, memory infrastructure, and self-reflection protocols.

paper-figure

Generate publication-quality figures, charts, and LaTeX tables from experiment data for academic papers.

transcription

Production-ready audio/video transcription using OpenAI Whisper. Features model selection, timing synchronization, speaker diarization, and batch processing for media workflows.

PRISM.unified

UI component patterns and touch input handling for M5Stack Tab5 applications using M5GFX and LVGL.

reviewing-code

Perform rigorous code reviews for FastMCP projects, focusing on API design, dependency management, and codebase consistency.

state-snapshot

Capture a complete debuggee state snapshot, including all committed memory regions and processor registers, for offline analysis and forensic investigation.

split-pdf

Automated pipeline to download, split, and deeply analyze academic PDFs in structured batches to avoid context window limits and ensure high-quality comprehension.