Skills

CrimeStats

Pulls US city crime statistics from public sources (FBI crime data, city police data...

Install

npx skills add danielmiessler/LifeOS --skill CrimeStats -g -a claude-code -y
Repository
danielmiessler/LifeOS19.7k
Category
Engineering
Updated
8d ago
License
MIT
Context cost
Mediumabout 1,801 tokens
Runs scripts
No, instructions only

What it does

Pulls US city crime statistics from public sources (FBI crime data, city police data portals, state open-data portals, rate aggregators): rates per 100K, year-over-year trends, recent incidents and city comparisons, defaulting to a configured home city. USE WHEN crime stats, crime rate, crime trends, violent crime, property crime, recent incidents, neighborhood safety, compare cities, is my city safe. NOT FOR people investigations.

CrimeStats

Contents: Ideal State · Anti-criteria · Intent Routing · Data & Config · Data Storage · Gotchas · Examples

Pulls and analyzes US city crime statistics from public data sources, rates per 100K, year-over-year trends, recent incidents, and regional comparisons, for the configured default city or any named one. Crime stats live across a dozen sites that disagree with each other, FBI UCR data lags, incident feeds are partial, and a city name can be ambiguous across states, so the skill knows which source to trust for which question: the configured city's police portal (Config.md) for local incident data, AreaVibes, CrimeGrade and HomeSnacks for rate snapshots, CityRating and FBI UCR for multi-year trends, SpotCrime and Patch for recent incidents, and the state DOJ open-data CSVs for agency-level data.

Ideal State

  • The numbers are for the city the user meant: the named city verified by its state (and county and ZIP for the configured city), or the configured default city when none was named.
  • Every reported figure names its source and data year, and the answer flags the caveat that shapes it (source baselines that disagree, FBI lag, felony-only portal counts, partial incident feeds, small-city rate swings).
  • Rate answers carry, when available, the total, property, violent, burglary, robbery and vehicle theft rates per 100,000, the YoY change as a percentage, and the percentage above or below the national average, with absolute numbers alongside for small cities.
  • Each pull is saved as dated JSON under the Data Storage path, so a later run can compare against it.

Anti-criteria

  • Never reports or stores the names of people arrested, accused or involved in an incident: figures, offenses, dates and block-level locations only.

Intent Routing

Read the whole SKILL.md on GitHub

More in Engineering