What problem does it solve? Investigating people and companies across fragmented public records — corporate filings, federal contracts, lobbying disclosures, sanctions lists, property deeds, court records, and news archives — requires manually querying a dozen different government and open-data APIs and reconciling inconsistent entity names. This Skill automates acquisition, entity resolution, timing analysis, and evidence-chain construction across 11 public-records sources using only the Python standard library. ## Core Features & Use Cases - Multi-source data acquisition: Fetch normalized CSVs from SEC EDGAR, USAspending, Senate lobbying disclosures, OFAC SDN sanctions, ICIJ Offshore Leaks, NYC ACRIS property records, OpenCorporates, CourtListener, Wayback Machine, Wikipedia/Wikidata, and GDELT news. - Cross-source entity resolution: Match entity names across datasets with three explicit confidence tiers (exact, fuzzy word-bag, token overlap) so every link carries a stated confidence level. - Timing correlation and evidence chains: Run permutation tests to detect suspicious clustering (e.g., lobbying filings near contract awards) and compile findings.json where every claim traces to a specific source row. - Use Case: A journalist investigating pay-to-play can pull a company's lobbying filings and federal contracts, resolve the entity names across both datasets, test whether filing dates cluster near award dates, and produce a verifiable findings document. ## Quick Start Ask the agent to investigate a company by pulling its SEC filings, federal contracts, and lobbying records, then cross-reference the results and build an evidence chain.
