Fetch real, citable Bilibili video metadata, live engagement stats, and full danmaku text — no login required.
Produces a statistically rigorous A/B test plan with hypothesis, sample size, duration, guardrails, and a results interpretation guide.
Turns finished A/B test numbers into an honest readout with a ship/no-ship verdict, significance checks and segment cuts.
Runs Google Gemini's Deep Research Agent to autonomously plan, search, and synthesize cited long-form research reports.
Turns Brand Registry SFR, Market Basket and Item Comparison exports into an actionable growth strategy report.
Pulls 20 core China A-share pharma tickers from Sina Finance's free quote API, ranks sub-sectors, and pushes a formatted daily report to Feishu.
Co-creates a pure-markdown investment research wiki in Karpathy's LLM Wiki style by interviewing you to distill your own analysis framework into CLAUDE.md.
Pulls China A-share market data via AKShare and produces technical, fundamental, and multi-factor screening reports.
Reads dashboard screenshots, CSVs, or public links to validate content performance per post, week, or month, attribute causes, and design the next single experiment.
Gives Claude a complete, code-first seaborn reference for turning pandas DataFrames into publication-ready statistical plots.
Teaches Claude to build interactive Plotly charts, 3D plots, and multi-panel dashboards with production-ready code.
Writes and validates ggsql queries that fuse SQL with a grammar-of-graphics visualization spec.
Lets Claude Code query your Google NotebookLM notebooks for citation-backed answers and manage sources plus Studio outputs.
Searches, compares and validates real emission factors from Carbonstop's CCDB database for product carbon footprints, LCA and corporate GHG accounting.
Scans Bilibili's AI videos daily, clusters trending topics, and produces an HTML digest plus a multi-engine, cross-verified intelligence report.
Reverse-engineers a researcher's publication strategy from PubMed into a CSV dataset, seven charts, and a strategy report.
A skill that computes option delta, gamma, theta, vega and implied volatility via a Black-Scholes command-line script.
A skill that recommends chunk sizes, overlap ratios, and semantic boundary detection methods for RAG and vector search pipelines.
x
A decision-tree-driven skill for labeling cell types in scRNA-seq data via manual markers, automated classifiers, or reference label transfer.