Monitors all active and recently completed experiments across Amplitude projects, triages them by importance, then runs deep analysis and reporting on the most impactful ones. Use when the user asks to "check on experiments", "experiment status", "experiment review", "what experiments are running", or wants a periodic experiment health report.
Designs A/B tests with proper metrics and variants, analyzes running or completed experiments, and interprets results with statistical rigor. Use when setting up experiments, checking experiment status, analyzing results, or making ship decisions.
Post-diagnostic verification — checks that findings address the original concern, skills ran as planned, and results are internally consistent
Sequential Monte Carlo (particle filters) for real-time probability updating. Bootstrap filter with systematic resampling, ESS monitoring, logit-space state evolution, and credible intervals. For live event tracking like election night or real-time market monitoring.
Build and analyze A/B test dashboards, calculate statistical significance, and track experiment results.
Cluster TCR/BCR clones by CDR3 sequences using GIANA or ClusTCR (both Faiss-based). Adds `CDR3_Cluster` column to metadata for clonotype analysis.
Progressive-disclosure workflow for ANDES studies. Use when the user asks to run ANDES through PowerMCP for power flow, small-signal stability, or time-domain simulation, and when the agent should expose base-case steps before advanced dynamic analysis.
Work with 3D mesh processing in MoldGen. Use when implementing geometry algorithms, mesh operations, mold building, orientation analysis, parting surfaces, or GPU kernels.
Visualize cell-cell communication inference results from CellCellCommunication process. Creates publication-ready network diagrams, heatmaps, and interaction plots to help interpret ligand-receptor interactions between cell types.
Performs enrichment analysis (GSEA-based) for metabolic pathways across different cell groups to identify significantly enriched pathways. Uses fast gene set enrichment analysis (fgsea package) to rank pathways by their association with specific clusters, conditions, or cell states. Generates summary plots and enrichment visualizations for biological interpretation.
Master skill for generating immunopipe pipeline configurations. Determines pipeline architecture based on data type (scRNA-seq with or without scTCR/BCR-seq) and analysis requirements. Routes to individual process skills for detailed configuration. Use this skill when starting a new immunopipe configuration or modifying pipeline-level options.
Generate comprehensive clonality statistics and diversity visualizations for TCR/BCR repertoire analysis. Quantifies clonal expansion, measures diversity metrics (Shannon, Simpson, Gini), and creates publication-ready plots.
对蛋白pdb文件，进行预处理，对N、C端进行封端，对特定残基进行离子化，弥补缺失的原子等。得到准备好的pdb文件
Map query single-cell datasets to high-quality reference atlases using Seurat's reference mapping workflow. Performs label transfer, UMAP projection, and integration with reference annotations without modifying query expression data. Enables transfer learning from curated atlases like Azimuth PBMC or custom tissue-specific references.
Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses.
Progressive-disclosure workflow for OpenDSS feeder studies. Use when the user asks to compile a DSS model, solve a distribution circuit, inspect feeder voltages or power, run load multipliers, or perform daily or harmonic studies through PowerMCP, with base-case checks before advanced scenarios.
This skill is used to perform de novo molecule generation basd on a given protein and a coordinate of center of pocket.
Performs fast Gene Set Enrichment Analysis (GSEA) on single-cell data using fgsea R package. Identifies enriched biological pathways by ranking genes based on differential expression between cell groups. Generates enrichment scores, significance metrics, and publication-ready visualizations.
模拟计算液相的热传导系数(thermal conductivity)，多分子堆积成液相盒子，在NPT系综下进行分子动力学（molecule dynamics, MD)计算。分子输入的格式可以是.sdf, .mol, .csv以及smiles等多种格式
