Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Japanese addresses / 日本の住所

    1

    Clean up Japanese addresses for shipping, CRM and vendor records: normalize notation, parse into prefecture/city/town/block, look up postal codes, geocode and validate how deep an address really matches. Free skill; the JPVerify API is paid per call (from $0.001).

    Free

    Security scanned
    Japanese addresses / 日本の住所

    Japanese addresses / 日本の住所

    Example session with this skill installed

    Our customer typed this delivery address: "東京都千代田区丸の内1丁目9−1", postal code 100-0005. Clean it up for our shipping system and tell me whether the postal code and address actually match.

    • Read your context and instructions
    • Compiled the japanese addresses

    Summary

    The address normalizes to

    東京都千代田区丸の内1丁目9-1, and postal code

    100-0005 belongs to the same town (東京都千代田区丸の内), so the postal code and address are consistent. The address is confirmed down to block 9 (丸の内1丁目9番); house number 1 is not in the address dictionary, so the result is partial, not matched. Cost: 2 calls, $0.006.

    Step 1: postal code

    POST /jp-address/postal-lookup with postal_code 100-0005 ($0.001) → matched, Japan Post data dated 2026-10-30.

    FieldValue
    Prefecture東京都
    City千代田区
    Town丸の内
    Readingトウキョウト チヨダク マルノウチ

    Step 2: normalize and parse

    POST /jp-address/normalize ($0.005) → match_status: partial, confidence 0.82.

    ComponentValue
    Normalized東京都千代田区丸の内1丁目9-1
    Prefecture / city / town東京都 / 千代田区 / 丸の内
    丁目 / block / house1丁目 / 9番 / 1号
    Confirmed toBlock level (丸の内1丁目9番)
    Coordinates35.681252, 139.767235
    Changes madeFull-width digits and the dash normalized
    WarningsDictionary match is one level below the parsed house number

    Comparison

    CheckResult
    Postal code town vs. address townBoth 丸の内, 千代田区 — consistent
    Address existsYes, to block 9
    House number 1Not confirmed by the dictionary (normal for many buildings)

    Next steps

    1. Save the normalized address and its components in your shipping system, with postal code 100-0005.
    2. Delivery to block level is safe; if you need house-level certainty (for example, for KYB), ask the customer for the building name.
    3. For many addresses at once, call the same endpoints per row; postal lookup costs $0.001 each.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Normalize, parse, validate and geocode Japanese addresses (住所の正規化・解析・検証) with JPVerify, and look up Japanese postal codes (郵便番号) — down to 丁目, block and building level, with the evidence behind each match. Use when a task involves cleaning or standardizing a Japanese address, checking that an address exists at a required precision, splitting it into components, finding coordinates, or finding the area for a postal code. Paid per call (API key credits or x402).

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for APIs & Backend.

    Requires a JPVerify API key or x402 wallet. Normalization does not infer a missing postal code (use postal lookup). Confirmation depth depends on the address dictionary: many addresses are confirmed to block (番) level, and house numbers or building names are often not covered. Japanese addresses only.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed today

    • Free with an Agensi account

    Accounts
    Jpverify

    Permissions

    Terminal / Shell
    Network Access
    Environment Variables

    Allowed Hosts

    api.jpverify.com

    Network access to api.jpverify.com only, to send the addresses and postal codes the user provides. The API key is read from the JPVERIFY_API_KEY environment variable and sent only to api.jpverify.com. No files are read or written.

    Listed9 days ago
    Updatedtoday

    What's inside

    Frequently Asked Questions

    An LLM can invent block numbers or postal codes that do not exist. This skill checks addresses against Japan Post postal data and the Jageocoder address dictionary, and reports exactly which level was confirmed (town, 丁目, block, house) and why. When the data cannot confirm a level, the result says partial instead of guessing.

    Any agent that supports the open SKILL.md format (Claude Code, Codex CLI, Cursor, VS Code Copilot, Gemini CLI and others). The skill calls the JPVerify HTTP API with curl; the same checks are also available as an MCP server at https://api.jpverify.com/mcp.

    The skill provides a match confidence score and a 'candidate count.' If an input is ambiguous, the skill returns multiple potential matches, allowing your agent to prompt the user for clarification rather than making an incorrect guess.

    Setup requires connecting to the JPVerify API using either a standard API Bearer token or an x402 wallet for pay-per-call flexibility. Once the connection method is configured, the skill is ready to normalize and geocode data immediately.

    Geocoding returns candidates with prefecture, city and town components, coordinates (latitude/longitude), the matched level, a confidence value and match reasons. It also returns any unmatched tail — the part of the input that could not be mapped in the address dictionary — so you can spot typos or levels the dictionary does not cover.

    New in APIs & Backend

    Free