fulcra-analytics

Analyze your data

Skill

Teaches agents privacy-respecting analysis of any data you've made visible through Fulcra: fetch records or metrics, normalize them into DataFrames, and produce auditable summaries. Real answers from your own data, computed where you control it.

A Python package for descriptive analysis of your own data, built so the raw records stay on your machine. It fetches records or metric time series through the CLI, normalizes them into DataFrames, and produces summaries you can read or publish.

  • Pulls from uvx fulcra-api get-records and uvx fulcra-api metric-time-series, or reads a local JSON, JSONL or CSV export.
  • Computes missingness, numeric summaries, categorical frequencies, boolean ratios, datetime ranges and grouped summaries.
  • Emits auditable JSON, or an OKF-ready report carrying the question, the data used, the methods, the findings, the caveats and the next steps.
  • Keeps raw personal data local by default and uploads only sanitized summaries or artifacts you approved.
  • Stops at descriptive statistics on purpose. Modeling, forecasting and causal work are out of scope.

Install it with npx skills add fulcradynamics/agent-skills/fulcra-analytics.

Paste this to your agent

Read https://docs.fulcradynamics.com/agent-get-started.txt and connect to Fulcra, then install the fulcra-analytics skill and follow it. Tell me what my own data says: pick a type I have plenty of and show me what's there, what's missing, and how it moves — without my raw records leaving my machine.

View the sourceAll skills and workflows