vendor-verification

Verify whether vendors/merchants from expense records are real, registered business entities by querying the free Wikidata open API.

npx skills add https://github.com/google-gemini/gemini-managed-agents-templates --skill vendor-verification

Vendor Verification

Verify whether merchants or vendors from expense records are real, registered business entities by querying the free, open Wikidata API (no key required). This skill helps identify potentially fraudulent or unverified merchants.

Embedded Script

python3 skills/vendor-verification/scripts/verify_vendors.py --workspace .agents/workspace

Arguments

ArgumentDefaultDescription
--workspace.agents/workspaceWorkspace directory containing expenses.csv or reconciliation_data.json

What it does

  1. Loads expense records from .agents/workspace/reconciliation_data.json (if available from a prior reconciliation run) or directly from .agents/workspace/expenses.csv.
  2. Identifies all unique vendor/merchant names.
  3. For each unique merchant, queries the free Wikidata Entity Search API: https://www.wikidata.org/w/api.php?action=wbsearchentities&search={merchant_name}&language=en&format=json
  4. Analyzes the search results:
    • Verified: If a matching entity exists on Wikidata. Extracts the description (e.g. “American multinational technology company”) and entity ID (e.g., Q95).
    • Unverified: If no match is found on Wikidata.
  5. Generates .agents/workspace/vendor_verification_report.md with:
    • Verification summary statistics.
    • A detailed status table for all unique vendors.
    • Flagged unverified vendors requiring secondary research.
  6. Generates .agents/workspace/vendor_verification_data.json containing the structured JSON results.

Licensing & Usage

  • This skill queries Wikidata, which is licensed under Creative Commons CC0 1.0 Universal Public Domain Dedication.
  • It is 100% free of charge, requires no API token/key, has no commercial restrictions, and requires no attribution.

Output

FilePathDescription
Verification Report.agents/workspace/vendor_verification_report.mdHuman-readable markdown report listing verified and unverified merchants with official descriptions.
Verification Data.agents/workspace/vendor_verification_data.jsonStructured JSON containing merchant verification statuses, descriptions, and Wikidata entity URIs.

More skills from google-gemini

greeter
google-gemini
A friendly greeter skill
official
code-reviewer
google-gemini
Automated code review for local changes and remote pull requests with structured analysis across correctness, maintainability, and security. Supports both local file system changes (staged and unstaged) and remote PRs (by number or URL) with automatic GitHub CLI checkout Analyzes code across seven dimensions: correctness, maintainability, readability, efficiency, security, edge case handling, and test coverage Runs optional preflight verification suites (e.g., npm run preflight ) to catch...
official
review-duplication
google-gemini
Use this skill during code reviews to proactively investigate the codebase for duplicated functionality, reinvented wheels, or failure to reuse existing…
official
reconciliation
google-gemini
Reconcile loaded expenses against the pre-parsed invoice database, flagging discrepancies like amount mismatches, missing invoices, and merchant mismatches…
official
gemini-api-cli
google-gemini
Guide for using the Gemini API CLI tool. Use when you need to interact with the Gemini API via the command line, manage agents, or generate media (images,…
official
agent-tui
google-gemini
Main Agents: Do NOT use this skill directly. If you need to test the TUI, invoke the `tui_tester` subagent. Drive terminal UI (TUI) applications…
official
async-pr-review
google-gemini
Trigger this skill when the user wants to start an asynchronous PR review, run background checks on a PR, or check the status of a previously started async PR…
official
behavioral-evals
google-gemini
Guidance for creating, running, fixing, and promoting behavioral evaluations. Use when verifying agent decision logic, debugging failures, debugging prompt…
official