Offboarding Completion Claim Evidence
Check your closed checklist and task receipts for missing supporting records.
Employee onboarding
Find where your approved transfer and payroll/system exports disagree.
A downloadable skill for your AI agent.
Inconsistent department coding.
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.
Approved transfer and payroll/system exports. 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 Employee Transfer Cost-Center Drift skill. Review the attached records: approved transfer and payroll/system exports. Prepare this result: inconsistent department coding. 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 puts records for the same item side by side. It keeps both original values when they differ, so you can check the source.
Approved transfer and payroll/system exports.
For this task, keep one review row for each worker + cost-center field. Record approved transfer, effective date, and system value. Keep the source location beside each value.
Map each required task to an owner and completion evidence. Keep access requests, grants, revocations, asset shipment, and receipt separate.
Use role templates and approved exceptions. A checklist tick does not prove account removal or equipment return.
A changed value does not show which source is correct. Semantic equivalence and identity aliases need an explicit mapping and review.
This synthetic example shows the included check in use. Your agent uses its findings to complete your task report.
Synthetic example records
| Starting record | approved transfer: source-A |
|---|---|
| Record to check | approved transfer: source-B |
A difference needs review
This result comes from the checking tool in your download.
These are synthetic records from the bundled example.
{"id": "e1", "key": "worker + cost-center field / SYNTHETIC-001", "value": {"approved transfer": "source-A"}}{"id": "o1", "key": "worker + cost-center field / SYNTHETIC-001", "value": {"approved transfer": "source-B"}}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 approved transfer and payroll/system exports. Confirm the case, period, and source versions before the review.
Use employee or contractor ID, role, start/end date, system or asset to keep records distinct. The agent records the original value, an exact quote, and the source location.
Match each item, then compare its supplied values. Run the Python helper on the structured records. Check each finding against its source.
Prepare the task result: inconsistent department coding. 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.