Agent Skills Hub

deep-thinking

A deep reasoning protocol that ensures systematic analysis, multi-hypothesis generation, and rigorous verification for complex architectural, debugging, and high-stakes tasks.

stable-baselines3

Production-ready reinforcement learning using Stable Baselines3. Train agents, design custom environments, implement training callbacks, and optimize workflows with a scikit-learn-style API.

baidu-search

Search the live web using Baidu AI Search Engine (BDSE) for real-time information, documentation, and research topics.

evaluation

Build systematic evaluation frameworks for AI agents using multi-dimensional rubrics, LLM-as-a-judge, and regression testing to measure performance, quality, and context engineering effectiveness.

paper-write

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

zarr-python

Python skill for high-performance storage of chunked N-dimensional arrays using Zarr, supporting cloud storage (S3/GCS), parallel I/O, and integration with NumPy, Dask, and Xarray.

hegelion

Dialectical reasoning and adversarial coding agent for MCP-enabled editors, forcing LLMs to resolve internal contradictions for higher quality outputs.

seaborn

Statistical visualization library for Python. Create publication-quality graphics like box plots, heatmaps, and violin plots with pandas integration and automatic statistical estimation.

debugging

Standardized debugging and diagnostic guidelines for AI coding agents.

paper-notes

Generate structured, machine-readable notes for papers in a core research set to enable reliable synthesis and evidence-backed writing.

competitive-analysis

Framework for building professional competitive landscape decks, including market positioning, peer benchmarking, and strategic synthesis for finance professionals.

parxy

A unified document processing gateway for PDF parsing, text extraction, conversion, and document manipulation across multiple local and cloud providers.