Dados e Análise

Cancer genomics (TCGA et al.) via cBioPortal REST API. Retrieve somatic mutations, CNAs, expression, clinical data (survival/stage/treatment) across thousands of studies. Use for TMB, oncoprints, survival analysis. For population frequencies use gnomad-database; for drug-gene interactions use opentargets-database.

Master SQL query optimization, indexing strategies, and EXPLAIN analysis to dramatically improve database performance and eliminate slow queries. Use when debugging slow queries, designing database schemas, or optimizing application performance.

Turn bulk RNA-seq cohorts into synthetic single-cell datasets using omicverse's Bulk2Single workflow for cell fraction estimation, beta-VAE generation, and quality control comparisons against reference scRNA-seq.

Implement GDPR/App Store/Play Store compliant account deletion with confirmation flow, data cleanup, and auth sign-out. Use when adding "delete account", "remove account", or "user data deletion" features. Required for both App Store and Play Store compliance.

Load and preprocess imaging mass cytometry (IMC) and MIBI data. Covers MCD/TIFF handling, hot pixel removal, and image normalization. Use when starting IMC analysis from raw MCD files or preparing images for segmentation.

Jira Data Center via Apideck's Proxy API + managed Vault auth — Apideck handles auth and proxies HTTP calls to Jira Data Center's native API. Use when the user wants to call Jira Data Center (no unified API resource mapping). Routes through Apideck with serviceId "jira-data-center".

GraphQL gives clients exactly the data they need - no more, no less. One endpoint, typed schema, introspection. But the flexibility that makes it powerful also makes it dangerous. Without proper controls, clients can craft queries that bring down your server. This skill covers schema design, resolvers, DataLoader for N+1 prevention, federation for microservices, and client integration with Apollo

Use this skill for token-level data: search tokens, trending/hot tokens (热门, 代币榜单), liquidity pools, holder distribution (whale/巨鲸, sniper, bundler-tagged holder %), token risk metadata (riskControlLevel, tokenTags, dev stats, suspicious/bundle holding % via advanced-info), recent buy/sell activity, trade feed/逐笔成交/每笔交易/stream trades, top profit addresses, token trade history, detailed price info

Fast in-memory DataFrame with lazy evaluation, parallel execution, Arrow backend. Use for tabular data in RAM (1–100 GB) when pandas is too slow. Expression API: select, filter, group_by, joins, pivots, window. Lazy mode enables predicate/projection pushdown. Reads CSV, Parquet, JSON, Excel, DBs, cloud. Larger-than-RAM: Dask; GPU: cuDF.

Enforce the No-Bluff SEO/GEO protocol using DataForSEO and SEMRush. Use when generating or modifying any SEO-related copy, claims, or structured data for Synthex or client sites.

Analyzes and optimizes application performance across frontend, backend, and database layers. Use when diagnosing slowness, improving load times, optimizing queries, reducing bundle size, or when asked about performance issues.

Dimensionality reduction and clustering for single-cell RNA-seq using Seurat (R) and Scanpy (Python). Use for running PCA, computing neighbors, clustering with Leiden/Louvain algorithms, generating UMAP/tSNE embeddings, and visualizing clusters. Use when performing dimensionality reduction and clustering on single-cell data.