Data & Analytics

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.

A monthly CFO cadence that pulls bank, payment, payroll and expense data, reconciles it, and ships a cash snapshot plus runway forecast.

Turns Claude Code transcript tokens into a manager-readable cost report (HTML/PDF/JSON/CSV) with cost per completed outcome and the price of wasted work.

Scans a Karpathy-pattern LLM wiki (raw sources + wikilinked markdown + schema) and builds an interactive knowledge graph with entities, implicit relationships, and topic clusters.

A skill for querying and analyzing DepMap CRISPR gene dependency and drug sensitivity data to validate cancer-specific targets.

Guides Claude through the complete PyMC 5 Bayesian workflow — priors, NUTS sampling, convergence diagnostics, LOO model comparison, and prediction.

Generates and runs reproducible Python/R analyses for medical research and outputs publication-ready tables, figures and manuscript text.

When the Bigdata.com (RavenPack) MCP only returns synthesized prose, this skill drops to the official SDK and /v1 REST endpoints for raw financials, prices, estimates and sentiment.

Enforces a discover → inspect → plan → query → validate workflow for any data question against a ktx-connected database, with a deep set of correct-SQL heuristics.

Maps dbt schema.yml models, sources and tests into ktx semantic-layer overlays and column notes without inventing physical columns.

A ktx-specific skill that mines historic SQL query shards for recurring cross-table analytical intents and emits verified pattern evidence.

Turns text, URLs, code repos and Obsidian vaults into InfraNodus knowledge graphs to surface content gaps, questions and GraphRAG answers.

Turns a parsed document plus a user intent into four auditable card types — blue facts, green explanations, yellow risks, and red actions — with mandatory source citation.

Defines the implementation phase of a math-modeling project: Python/MATLAB code, result tables, publication-grade figures, flowcharts and a reproduction manifest, enforced by two independent QA gates.

Pulls your live Interactive Brokers PMCC positions and generates a tactical collar (protective put) report for earnings and other high-risk events.

A five-step pre-flight checklist — config diff, run naming, path verification, monitoring, and ETA — plus restart/kill cleanup for long GPU training runs.

Turns one validated analysis template into N variable-swapped R/Python scripts across exposure × outcome pairs, then aggregates everything into a summary results matrix.

Turns historical campaign data and a recent baseline into CPM/CVR/AOV estimates and backtested budget, revenue, and contribution-profit scenarios.

A pipeline skill that turns one staged historic-SQL table JSON file into typed table-usage evidence.

A KTX memory-agent skill that reads staged Google Drive documents and distills them into durable, well-cited internal wiki pages.