Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Integrate Didit Proof of Address standalone API to verify address documents. Use when the user wants to verify a proof of address, validate utility bills, bank statements, government documents, extract address from documents, verify residential address, implement address verification, or perform PoA checks using Didit. Supports OCR extraction, geocoding, name matching, and multi-page documents.
.claude/skills/didit-protocol-didit-proof-of-address/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 72% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 166% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 54% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 127% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 49% | 0% |
Verifies address documents by submitting images or PDFs. Extracts address information, performs authenticity checks, name matching, geocoding, and returns structured data.
Key constraints:
Capabilities: OCR extraction, intelligent document classification, name matching with identity documents, issue date validation, geocoding with lat/lng coordinates, language detection, multi-page support.
Accepted document types:
| Category | Examples | |---|---| | Utility Bill | Electricity, water, gas, internet, phone, combined utilities | | Bank Statement | Account statement, credit card, mortgage, loan | | Government-Issued | Tax assessment, residency certificate, voter registration | | Other PoA | Lease, rental agreement, insurance policy, employer letter |
API Reference: https://docs.didit.me/standalone-apis/proof-of-address Feature Guide: https://docs.didit.me/core-technology/proof-of-address/overview
All requests require x-api-key header. Get your key from Didit Business Console → API & Webhooks, or via programmatic registration (see below).
If you don't have a Didit API key, create one in 2 API calls:
POST https://apx.didit.me/auth/v2/programmatic/register/ with {"email": "you@gmail.com", "password": "MyStr0ng!Pass"}POST https://apx.didit.me/auth/v2/programmatic/verify-email/ with {"email": "you@gmail.com", "code": "A3K9F2"} → response includes api_keyTo add credits: GET /v3/billing/balance/ to check, POST /v3/billing/top-up/ with {"amount_in_dollars": 50} for a Stripe checkout link.
See the didit-verification-management skill for full platform management (workflows, sessions, users, billing).
POST https://verification.didit.me/v3/poa/| Header | Value | Required | |---|---|---| | x-api-key | Your API key | Yes | | Content-Type | multipart/form-data | Yes |
| Parameter | Type | Required | Default | Description | |---|---|---|---|---| | document | file | Yes | — | PoA document (JPG/PNG/TIFF/PDF, max 15MB) | | save_api_request | boolean | No | true | Save in Business Console | | vendor_data | string | No | — | Your identifier for session tracking |
pythonimport requests response = requests.post( "https://verification.didit.me/v3/poa/", headers={"x-api-key": "YOUR_API_KEY"}, files={"document": ("utility_bill.pdf", open("bill.pdf", "rb"), "application/pdf")}, data={"vendor_data": "user-123"}, ) print(response.json())
typescriptconst formData = new FormData(); formData.append("document", documentFile); const response = await fetch("https://verification.didit.me/v3/poa/", { method: "POST", headers: { "x-api-key": "YOUR_API_KEY" }, body: formData, });
json{ "request_id": "a1b2c3d4-...", "poa": { "status": "Approved", "issuing_state": "ESP", "document_type": "UTILITY_BILL", "issuer": "Endesa", "issue_date": "2025-01-15", "document_language": "es", "name_on_document": "Elena Martínez Sánchez", "poa_address": "Calle Mayor 10, 28013 Madrid", "poa_formatted_address": "Calle Mayor 10, 28013 Madrid, Spain", "poa_parsed_address": { "street_1": "Calle Mayor 10", "city": "Madrid", "region": "Comunidad de Madrid", "postal_code": "28013", "raw_results": { "geometry": {"location": {"lat": 40.4168, "lng": -3.7038}} } }, "document_file": "https://example.com/document.pdf", "warnings": [] }, "created_at": "2025-05-01T13:11:07.977806Z" }
| Status | Meaning | Action | |---|---|---| | "Approved" | Address verified, document valid | Proceed with your flow | | "Declined" | Document invalid or expired | Check warnings for specific reason | | "In Review" | Needs manual review | Check for name mismatch or quality issues | | "Not Finished" | Processing incomplete | Wait or retry |
| Code | Meaning | Action | |---|---|---| | 400 | Invalid request | Check file format, size, parameters | | 401 | Invalid API key | Verify x-api-key header | | 403 | Insufficient credits | Top up at business.didit.me |
| Field | Type | Description | |---|---|---| | status | string | "Approved", "Declined", "In Review", "Not Finished" | | issuing_state | string | ISO 3166-1 alpha-3 country code | | document_type | string | "UTILITY_BILL", "BANK_STATEMENT", "GOVERNMENT_ISSUED_DOCUMENT", "OTHER_POA_DOCUMENT", "UNKNOWN" | | issuer | string | Issuing institution name | | issue_date | string | YYYY-MM-DD | | document_language | string | Detected language code | | name_on_document | string | Extracted name | | poa_address | string | Raw extracted address | | poa_formatted_address | string | Formatted address | | poa_parsed_address | object | {street_1, street_2, city, region, postal_code} | | poa_parsed_address.raw_results.geometry.location | object | {lat, lng} geocoded coordinates | | document_file | string | Temporary URL (expires 4 hours) | | warnings | array | {risk, log_type, short_description, long_description} |
| Tag | Description | |---|---| | POA_DOCUMENT_NOT_SUPPORTED_FOR_APPLICATION | Document type not accepted for your app | | EXPIRED_DOCUMENT | Document older than 90 days | | INVALID_DOCUMENT_TYPE | Document cannot be processed | | MISSING_ADDRESS_INFORMATION | No valid address could be extracted |
| Tag | Description | |---|---| | NAME_MISMATCH_WITH_PROVIDED | Name doesn't match verified identity | | NAME_MISMATCH_ID_VERIFICATION | Name doesn't match ID document | | POA_NAME_MISMATCH_BETWEEN_DOCUMENTS | Names differ between multiple PoA docs | | POOR_DOCUMENT_QUALITY | Insufficient image quality | | DOCUMENT_METADATA_MISMATCH | Digital signature/metadata indicates tampering | | SUSPECTED_DOCUMENT_MANIPULATION | Signs of document manipulation | | UNSUPPORTED_DOCUMENT_LANGUAGE | Document language not supported | | ADDRESS_MISMATCH_WITH_PROVIDED | Address doesn't match provided address | | UNABLE_TO_EXTRACT_ISSUE_DATE | Could not determine issue date | | ISSUER_NOT_IDENTIFIED | Could not identify issuing institution | | UNPARSABLE_OR_INVALID_ADDRESS | Address couldn't be parsed | | UNABLE_TO_VALIDATE_DOCUMENT_AGE | Could not determine document age | | FUTURE_ISSUE_DATE | Issue date is in the future |
Warning severity: error (→ Declined), warning (→ In Review), information (no effect).
1. POST /v3/poa/ → {"document": utility_bill}
2. If "Approved" → address verified
If "Declined" → check warnings:
EXPIRED_DOCUMENT → ask for a more recent document
MISSING_ADDRESS_INFORMATION → ask for clearer image
NAME_MISMATCH → verify identity matches1. POST /v3/id-verification/ → verify identity document
2. POST /v3/passive-liveness/ → verify real person
3. POST /v3/poa/ → verify address
4. System auto-matches name between ID and PoA documents
5. All Approved → identity + address verifiedverify_address.py: Verify proof of address documents from the command line.
bash# Requires: pip install requests export DIDIT_API_KEY="your_api_key" python scripts/verify_address.py utility_bill.pdf python scripts/verify_address.py bank_statement.jpg --vendor-data user-123
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 13,946 | 33,112 | +137% | 1 | 1 | 0% | 2,680 | 4,604 | +72% | 0 | 0 | — |
case-02 | fail→pass | 20,508 | 16,792 | -18% | 1 | 1 | 0% | 1,824 | 4,844 | +166% | 0 | 0 | — |
case-03 | fail→pass | 12,191 | 8,404 | -31% | 1 | 1 | 0% | 2,205 | 3,390 | +54% | 0 | 0 | — |
case-04 | fail→pass | 7,104 | 3,129 | -56% | 1 | 1 | 0% | 1,350 | 3,060 | +127% | 0 | 0 | — |
case-05 | pass→pass | 5,140 | 2,049 | -60% | 1 | 1 | 0% | 836 | 2,770 | +231% | 0 | 0 | — |
case-06 | fail→pass | 10,714 | 3,243 | -70% | 1 | 1 | 0% | 2,084 | 3,111 | +49% | 0 | 0 | — |
case-07 | fail→pass | 7,691 | 2,904 | -62% | 1 | 1 | 0% | 1,530 | 3,002 | +96% | 0 | 0 | — |
case-08 | fail→pass | 8,528 | 4,313 | -49% | 1 | 1 | 0% | 1,463 | 3,304 | +126% | 0 | 0 | — |
case-09 | fail→pass | 10,826 | 4,005 | -63% | 1 | 1 | 0% | 2,290 | 3,358 | +47% | 0 | 0 | — |
case-19 | fail→pass | 10,430 | 2,331 | -78% | 1 | 1 | 0% | 634 | 2,924 | +361% | 0 | 0 | — |
case-10 | pass→pass | 8,062 | 3,103 | -62% | 1 | 1 | 0% | 1,524 | 3,017 | +98% | 0 | 0 | — |
case-11 | fail→pass | 6,509 | 2,183 | -66% | 1 | 1 | 0% | 1,266 | 2,842 | +124% | 0 | 0 | — |
case-12 | fail→pass | 6,450 | 3,165 | -51% | 1 | 1 | 0% | 1,146 | 2,973 | +159% | 0 | 0 | — |
case-13 | fail→pass | 7,606 | 2,439 | -68% | 1 | 1 | 0% | 1,265 | 2,865 | +126% | 0 | 0 | — |
case-14 | fail→pass | 6,632 | 3,213 | -52% | 1 | 1 | 0% | 1,328 | 3,120 | +135% | 0 | 0 | — |
case-15 | fail→pass | 6,637 | 2,042 | -69% | 1 | 1 | 0% | 1,170 | 2,856 | +144% | 0 | 0 | — |
case-16 | fail→pass | 5,052 | 1,428 | -72% | 1 | 1 | 0% | 859 | 2,638 | +207% | 0 | 0 | — |
case-17 | pass→pass | 10,015 | 2,466 | -75% | 1 | 1 | 0% | 1,895 | 2,810 | +48% | 0 | 0 | — |
case-18 | fail→pass | 8,236 | 2,020 | -75% | 1 | 1 | 0% | 1,504 | 2,829 | +88% | 0 | 0 | — |
case-20 | pass→pass | 4,791 | 2,223 | -54% | 1 | 1 | 0% | 861 | 2,914 | +238% | 0 | 0 | — |
case-21 | fail→pass | 4,972 | 3,843 | -23% | 1 | 1 | 0% | 929 | 3,272 | +252% | 0 | 0 | — |
case-22 | fail→pass | 8,467 | 2,657 | -69% | 1 | 1 | 0% | 1,678 | 3,056 | +82% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 21 counted toward the lift figure. The other 1 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +82 percentage points is the difference between those two pass rates over the 21 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 8/6/2026 | +77% |
Other measured skills in the registry, with their headline benchmark lift.