Maintenance Visit Invoice Evidence Check
Check your work orders and vendor invoices for missing supporting records.
Property maintenance
Find possible duplicate entries in your portal tickets and emails.
A downloadable skill for your AI agent.
Suggested incident groups without changing records.
Source references, missing information, and questions to review stay with the findings.
Open your download and follow the start guide. Use an AI agent that can load skill files and run the included tools.
Portal tickets and emails. Confirm the case and period you want to check.
Copy the request below into your agent. Add the files and any task details it needs.
Check the findings against the original records. Choose where to save the report and follow up on open questions.
Use the Duplicate Tenant Incident Merger Preview skill. Review the attached records: portal tickets and emails. Prepare this result: suggested incident groups without changing records. Include a source reference for each finding. List missing information and questions that need my review. Ask me to confirm the scope and where to save the report before you start.
It groups records with matching values. You review the proposed groups before deciding whether they describe the same event.
Portal tickets and emails.
For this task, keep one review row for each property + asset + incident period. Record occurrence signature, separate tenant reports, and candidate incident identity. Keep the source location beside each value.
Separate an incident, a work order, a vendor visit, and an invoice. Combine repeat messages only after their property, unit, asset, and time range agree.
Distinguish a completion claim from tenant confirmation. Retain callout rates, access limits, and invoice evidence.
A repeated signature is a candidate duplicate. Legitimate repeat events can have the same content. Do not delete, merge, or accuse a party automatically.
This synthetic example shows the included check in use. Your agent uses its findings to complete your task report.
Synthetic example records
| Sample record | occurrence signature: signature-A |
|---|---|
| Sample record | occurrence signature: signature-A |
A difference needs review
This result comes from the checking tool in your download.
These are synthetic records from the bundled example.
{"id": "r1", "key": "property + asset + incident period / SYNTHETIC-001", "value": {"occurrence signature": "signature-A"}}{"id": "r2", "key": "property + asset + incident period / SYNTHETIC-001", "value": {"occurrence signature": "signature-A"}}After purchase, extract the ZIP. Run these commands from the skill folder. Use a new output folder.
python3 scripts/checks.py
python3 scripts/audit.py assets/example.json \
--files-root assets/sample-files --output-dir example-result
Expected exit code: 1. Code 0 means no helper finding. Code 1 means a finding or review item. Code 2 means incomplete or invalid input.
The check uses the records you supply. Review each finding against the original documents.
Ask your agent to save the completed task report in a folder you choose. The report template includes the result, source references, missing information, and next actions.
Tonotes does not receive your work documents through this website. Documents you share with an AI service follow that service's storage settings.
US$11 includes one skill in a ZIP with 18 files. You receive the instructions and tools to run the task with your own records.
Use an agent that supports SKILL.md instructions and Python 3.10 or later with SQLite. Your AI-agent service is separate.
Start with portal tickets and emails. Confirm the case, period, and source versions before the review.
Use property, unit, asset, work order, visit date to keep records distinct. The agent records the original value, an exact quote, and the source location.
Group exact matching values and report duplicate candidates. Run the Python helper on the structured records. Check each finding against its source.
Prepare the task result: suggested incident groups without changing records. Include missing evidence, unresolved questions, and the next action for each open item.
Eight synthetic cases check the tool locally. Live-agent accuracy on real documents has not been tested.