Calibrate an LLM judge against human labels using data splits, TPR/TNR, and bias correction. Use after writing a judge prompt (write-judge-prompt) when you need to verify alignment before trusting its outputs. Do NOT use for code-based evaluators (those are deterministic; test with standard unit tests).
A modular orbital space station with corridors, control room, airlock, observation deck, and cargo bay
Performs placebo-in-time sensitivity analysis to validate causal claims. Use when checking model robustness, verifying lack of pre-intervention effects, or ensuring observed effects are not spurious.
Recommend a POI in a city (schema + deterministic result).
Write and debug ast-grep rules for structural code search and rewrite. Use when tasks require AST-aware matching (not plain text), such as finding specific syntax shapes, relational patterns (inside/has), composite logic (all/any/not), or precise code refactors across a codebase.
Use this skill for requests related to web research; it provides a structured approach to conducting comprehensive web research
Search arXiv preprint repository for papers in physics, mathematics, computer science, quantitative biology, and related fields
General-purpose X/Twitter research agent. Searches X for real-time perspectives, dev discussions, product feedback, cultural takes, breaking news, and expert opinions. Works like a web research agent but uses X as the source. Use when: (1) user says "x research", "search x for", "search twitter for", "what are people saying about", "what's twitter saying", "check x for", "x search", "/x-research", (2) user is working on something where recent X discourse would provide useful context (new library releases, API changes, product launches, cultural events, industry drama), (3) user wants to find what devs/experts/community thinks about a topic. NOT for: posting tweets or account management. Note: currently uses recent search (last 7 days). Full-archive search is available on the same pay-per-use X API plan but not yet implemented in this skill.
Search biomedical literature from PubMed and bioRxiv for research papers. Use this skill when: (1) Finding research papers on a specific topic or disease, (2) Retrieving recent preprints from bioRxiv, (3) Getting paper titles, abstracts, and metadata, (4) Literature review for drug discovery or biomedical research.
Query CZ CELLxGENE Census (61M+ cells). Filter by cell type/tissue/disease, retrieve expression data, and integrate with scanpy/PyTorch for population-scale single-cell analysis. Use this skill when: (1) Querying single-cell expression data by cell type, tissue, or disease, (2) Exploring available single-cell datasets and metadata, (3) Training machine learning models on single-cell data, (4) Performing large-scale cross-dataset analyses.
All-atom protein design using BoltzGen diffusion model. Use this skill when: (1) Need side-chain aware design from the start, (2) Designing around small molecules or ligands, (3) Want all-atom diffusion (not just backbone), (4) Require precise binding geometries, (5) Using YAML-based configuration. For structure validation, use boltz-2.
Predict protein subcellular localization from amino acid sequence using BioT5. Use this skill when: (1) You have a protein sequence and want to know where it localizes in the cell, (2) You need to identify cellular compartment (nucleus, cytoplasm, membrane, etc.), (3) You want quick localization prediction without experimental data.
Load spatial transcriptomics data from Visium, Xenium, MERFISH, Slide-seq, and other platforms using Squidpy and SpatialData. Use this skill when: (1) Loading Visium spatial transcriptomics data from Space Ranger output, (2) Loading Xenium single-cell resolution spatial data, (3) Loading MERFISH, CosMx, or other spatial platforms, (4) Converting between SpatialData and AnnData formats.
Probabilistic deep learning framework for single-cell multi-omics data analysis. Use this skill when: (1) Analyzing single-cell RNA-seq data with batch correction, (2) Integrating multi-modal data (CITE-seq, ATAC-seq, multi-omics), (3) Performing cell type annotation with scANVI, (4) Spatial transcriptomics deconvolution with DestVI.
Complete single-cell RNA-seq analysis workflow built on Scanpy and AnnData. Use this skill when: (1) Loading diverse single-cell data formats (10X, h5ad, CSV), (2) Performing quality control and filtering, (3) Normalization, dimensionality reduction, and clustering, (4) Marker gene identification and cell type annotation.
Query PubChem database for chemical structures, similar compounds, and bioactivity data. Use this skill when: (1) Converting drug name to molecular structure (SMILES, SDF), (2) Finding similar compounds for lead optimization, (3) Querying bioactivity data against protein targets, (4) Getting compounds active in specific assays.
Predict comprehensive ADMET (Absorption, Distribution, Metabolism, Excretion, Toxicity) properties for drug candidate molecules using GraphMVP ensemble models. Use this skill when: (1) Predicting blood-brain barrier penetration, (2) Assessing side effect profiles, (3) Estimating Caco-2 permeability, half-life, or LD50 toxicity, (4) Evaluating drug-likeness and safety of molecules.
Antibody design using IgGM model. Use this skill when: (1) Epitope-conditioned de novo antibody design, (2) Antibody affinity maturation, (3) Using antigen PDB structure and epitope information. For binding affinity evaluation, use prodigy.
Antibody-related structure prediction using tfold model. Use this skill when: (1) Predict antibody and nanobody structure of a given sequence, (2) Predict antigen-antibody complex structure of given sequences, (3) Using local GPU resources. For binding affinity evaluation, use prodigy.
Protein complex binding affinity prediction. Use this skill when: (1) Predict the binding affinity score, (2) Using protein complex structure.
Query ChEMBL database for bioactivity data on drug-like compounds. Use this skill when: (1) Finding compounds active against a protein target (target-based search), (2) Getting bioactivity profile for a molecule (molecule-based search), (3) Finding drugs for a disease indication (indication-based search).
面向生物医药问答场景的“疾病到创新药综合分析”技能。用于回答“某疾病有哪些创新药/前沿药/在研药/新机制药”等问题，输出疾病-靶点-药物-临床进展-机制趋势的一体化证据报告。适用于联合本地数据库适配代码与公开数据库 API（ChEMBL、ClinicalTrials、Search）进行多数据库查询、去重归一、创新性筛选与结构化报告生成的任务。
Structure prediction using Boltz-2, an open biomolecular structure predictor. Use this skill when: (1) Predicting protein complex structures, (2) Validating designed binders, (3) Predicting protein-ligand complexes, (4) Using local GPU resources. For protein complex binding affinity evaluation, use prodigy.
Modify molecules based on natural language descriptions using MolT5/BioT5 models. Use this skill when: (1) User wants to modify a molecule to improve specific properties (solubility, potency, etc.), (2) User provides a molecule and asks to "make it more X" or "improve Y", (3) User wants to generate molecule variants guided by text descriptions. Triggers on phrases like "modify this molecule", "edit the molecule", "make it more soluble", "improve drug-likeness", "change the molecule to", "optimize this compound".
