Machine learning

Provides access to the user's personal wiki, including notes, research, project documentation, decisions, and archived knowledge.

Use when a medical AI paper should be found and cited by AI search engines and RAG tools.

Use when clinical data may contain PHI and must be de-identified before any LLM-assisted analysis.

Use when designing a study that benchmarks AI systems against a human-expert panel, before data collection.

Use when designing or auditing how an LLM or multimodal LLM is evaluated on a clinical task (report generation, VQA, text extraction).

Use when you need a runnable PyTorch training repo for a medical-imaging task (segmentation, classification, detection, synthesis, self-supervised, or…

Use when building or auditing a radiomics or tabular clinical-ML prediction model with a classical learner (LASSO, SVM, random forest, XGBoost and similar).

Analyze a Karpathy-pattern LLM wiki knowledge base and generate an interactive knowledge graph with entity extraction, implicit relationships, and topic…

Eval-driven skill tuning.

Local scVI/scANVI-based single-cell latent embedding and batch-aware integration from raw-count .h5ad or 10x Matrix Market input, with stable integrated…

End-to-end ML phylogenetic tree inference — MSA, trimming, ModelFinder, IQ-TREE2/RAxML-NG.

This skill should be used for advanced LLM evaluation: LLM-as-judge systems, direct scoring, pairwise comparison, rubric calibration, evaluator bias…

Suede AI code review and A-F ship grade for a diff, PR, branch, or commit range: findings ranked P0-P3 with file:line evidence and a fix path, an A-F grade…

This skill provides reference guidance for citation verification in academic writing.

Opinionated Bayesian modeling workflow with PyMC and ArviZ.

Build and maintain an LLM-curated knowledge base from papers, articles, transcripts, notes and project findings.

Create and validate Earth2Studio data source wrappers (DataSource, ForecastSource, DataFrameSource, ForecastFrameSource) from remote stores.

Build deterministic forecast scripts with Earth2Studio (model, data source, IO, inference).

Pick the serving stack and per-runtime memory flags (vLLM, SGLang, llama.cpp, TensorRT Edge-LLM) for an LLM/VLM workload on any NVIDIA Jetson.

Use when building or maintaining a personal LLM-powered knowledge base.

Benchmark Jetson LLM/VLM serving performance across vLLM, llama.cpp, and Ollama with structured JSON output.

AI 视频生成全流程：通过 6 个阶段（剧本→角色/场景设计→分镜→参考图→视频生成→后期剪辑）将用户想法转化为完整视频。支持临时工作台（单独调用 LLM、VLM、文生图、图生图、视频生成）。触发词：视频生成、AI视频、AIGC、创作视频、制作视频、AI画图。

Fetch weather/climate data via Earth2Studio data sources for specific variables and times.

Comprehensive news aggregator that fetches, filters, and deeply analyzes real-time content from 44+ sources including Hacker News, Lobsters, Dev.to, GitHub…