A skill for storing, ingesting, querying and exporting VCF/BCF variant data on TileDB sparse arrays for population genomics.
Analyzes an existing PostgreSQL database and scores which tables are worth converting into TimescaleDB hypertables.
A step-by-step playbook for converting existing PostgreSQL tables into TimescaleDB hypertables with optimal chunking, compression, and post-migration validation.
Clones and refreshes competitor repositories, then writes competitive reports where every technical claim carries a file:line citation.
Adversarially tears down a founder, company or product you envy — separating marketing bubble from real signal, then mapping the validated playbook onto your own resources.
Aggregates China A-share news, regulatory announcements and retail sentiment from public Chinese sources into structured JSON or Markdown.
Pulls market data, historical financials and WACC inputs for US-listed tickers from yfinance and emits a validated, standardized JSON for downstream financial analysis skills.
Turns local ccusage data into a clear, evidence-based explanation of your Claude Code token spend, cost, and quota burn.
Extracts and analyzes Google Takeout exports of your Gemini chat history, producing a topic breakdown, key insights, and PII warnings.
Analyzes GA4 traffic, acquisition, landing pages, events and conversions through the NotFair MCP connector, and safely handles key-event or custom-dimension changes.
Designs a full measurement framework — north star metric, KPI hierarchy, event taxonomy, dashboards and attribution — and outputs a usable tracking plan.
Turns paper drafts or raw experiment results into publication-quality architecture diagrams and conference-sized data charts.
Extracts 50+ fields — tiered pricing, SKU variants, seller scores, coupons — from 1688.com product detail pages.
A skill for querying and analyzing DepMap CRISPR gene dependency and drug sensitivity data to validate cancer-specific targets.
Paste a Bilibili video link or BV ID to fetch comments, run four-axis sentiment analysis, and generate an interactive HTML report.
Runs structured investigations on China A-share companies, competitors, people and unverified claims, and outputs reports with credibility labels.
Compares training runs across wandb, neptune, mlflow, or tensorboard by aligning them at the same training step instead of current-vs-final.
Scans a Karpathy-pattern LLM wiki (raw sources + wikilinked markdown + schema) and builds an interactive knowledge graph with entities, implicit relationships, and topic clusters.
Turns a clinical dataset into reproducible Python/R analyses with journal-ready tables, figures, and manuscript text.
Look up the next earnings date, BMO/AMC timing and consensus EPS for any ticker or list of tickers.