Data & Analytics

Use when the work itself is still being shaped — a new project, an incoming request, a metric, a model — before anything is built. A stakeholder has data and goals but NO question yet — what is worth knowing must be PROPOSED: a question-charter of candidates, each anchored to a decision or tiered curiosity, feasibility cited or UNVERIFIED, answers labeled HYPOTHESIS. Detects: "what can our data tell us", "what should we be looking at", "we don't know what we need", "what's worth analyzing her...

Use when the work is hands-in-the-data right now — a number moved, an open question needs exploring, a picture of the estate needs drawing, a change needs its blast radius known. A number or result is wrong, suspicious, or moved unexpectedly in production and the why must be found before it is explained - a KPI that jumped or cratered, two reports that won't reconcile, a figure no one trusts. Drives a systematic differential across the whole failure surface - code, data, pipeline, definition,...

Use when a finished thing — a source, a result, code, or the record — is about to be trusted or consumed; the gate fires before the work leans on it. A dashboard or report — the assembled surface — needs reviewing before it ships. The failures live in the ASSEMBLY, not the SQL — non-additive totals (summed distinct counts, averaged averages), measure-filter interactions, default filters that silently exclude, stale extracts, titles and axes that claim what the data doesn't. Reviews the defini...

Use when the work is hands-in-the-data right now — a number moved, an open question needs exploring, a picture of the estate needs drawing, a change needs its blast radius known. An OPEN-ENDED look at data with no wrongness symptom - find what is there, and make the findings survive scrutiny later. Pre-registers the questions and the finding-bar BEFORE results are examined, logs every cut (N cuts => ~N/20 false hits expected), keeps effect sizes and bases ahead of significance talk, labels fi...

Turn rich agent answers and any file, folder, URL, or export into a polished single-file HTML page. Auto-picks a default route plus 17 concrete design systems (teaching, dashboard, atlas, timeline-story, document, …).

Access AlphaFold's 200M+ AI-predicted protein structures. Retrieve structures by UniProt ID, download PDB/mmCIF files, analyze confidence metrics (pLDDT, PAE), for drug discovery and structural biology.

Master modern SQL with cloud-native databases, OLTP/OLAP

Automate SendGrid email operations including sending emails, managing contacts/lists, sender identities, templates, and analytics via Rube MCP (Composio). Always search tools first for current sche...

Monitor portfolio risk, R-multiples, and position limits. Creates

Build financial models, backtest trading strategies, and analyze

Write Python code in n8n Code nodes. Use when writing Python in n8n, using _input/_json/_node syntax, working with standard library, or need to understand Python limitations in n8n Code nodes.

'"Implements cross-market relationships and asset class correlations

'"''Position Sizing Algorithms: Fixed Fractional, Kelly Criterion, and

'"Exit strategies, trailing stops, and take-profit mechanisms for trading"

'"Preventing lookahead bias in backtesting through strict causality enforcement"

'"Implements forecast volatility for risk management and option pricing

"Provides Time series forecasting for price prediction and market analysis"

'"Provides Generate synthetic financial data for training and testing

"Provides Detect current market regime for adaptive trading strategies"

'"Provides Analyze order flow to detect market pressure and anticipate

'"Implements process news text using nlp embeddings for trading signals

'"Provides Model inter-asset relationships for portfolio and cross-asset

'"Provides Combine multiple models for improved prediction accuracy and

'"Provides Monitor production ML models for drift, decay, and performance