Data & Analytics

Models the true financial structure of go-to-market channels — direct, reseller, marketplace, OEM — and designs partner tiers, rebates and channel-conflict rules.

Designs a full measurement framework — north star metric, KPI hierarchy, event taxonomy, dashboards and attribution — and outputs a usable tracking plan.

A CFO-in-a-skill that turns one JSON of costs and prices into unit economics, break-even, a month-by-month year 1 and what-if scenarios.

Turns a dollar budget and your own rules into exact per-stock buy amounts, written as Alpaca-shaped order proposals — never placed.

Pulls a company's filed XBRL numbers from SEC EDGAR and lays out revenue, margins and EPS quarter by quarter against the prior year.

Analyzes GA4 traffic, acquisition, landing pages, events and conversions through the NotFair MCP connector, and safely handles key-event or custom-dimension changes.

Reads dashboard screenshots, CSVs, or public links to validate content performance per post, week, or month, attribute causes, and design the next single experiment.

Audits report spreadsheets, merges subordinate submissions, computes YoY/MoM and percentage-point metrics with visible formulas, and turns them into report-ready sentences plus grayscale Excel charts.

Turns paper drafts or raw experiment results into publication-quality architecture diagrams and conference-sized data charts.

Runs structured investigations on China A-share companies, competitors, people and unverified claims, and outputs reports with credibility labels.

Pulls financials, earnings and key metrics from Yahoo Finance and scores a company's financial strength with the Piotroski F-Score.

Reports scheduled US economic releases (CPI, NFP, FOMC, GDP, PCE, ISM) with ET times, impact, and actual/consensus/previous values.

Runs Google Gemini's Deep Research Agent to autonomously plan, search, and synthesize cited long-form research reports.

Compares training runs across wandb, neptune, mlflow, tensorboard, or local result files by aligning them at the same step, and writes experiment reports.

Compares training runs across wandb, neptune, mlflow, or tensorboard by aligning them at the same training step instead of current-vs-final.

Teaches Claude to build interactive Plotly charts, 3D plots, and multi-panel dashboards with production-ready code.

Gives Claude a complete, code-first seaborn reference for turning pandas DataFrames into publication-ready statistical plots.

Pulls real, citable Bilibili video data — stats, metadata, tags and full danmaku — through login-free API calls so numbers are never guessed.

Scrapes BOSS直聘 (zhipin.com) job listings through Chrome CDP by keyword, city and filters, exporting plaintext-salary JSON/CSV plus summary reports.

Turns finished experiment results into an honest readout: lift, statistical and practical significance, risks, and a ship/no-ship call.