Museum Object Number Photo Alias
Turn your photo filenames and accession map into a review with clear source references.
Museum collection records
Check that the files listed in your supplied process checklist and folder are present.
A downloadable skill for your AI agent.
Missing decision 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.
Supplied process checklist and folder. 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 Museum Deaccession File Evidence Inventory skill. Review the attached records: supplied process checklist and folder. Prepare this result: missing decision 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 compares the attachment list with the files in your chosen folder. It reports missing files and checks file fingerprints when you supply them.
Supplied process checklist and folder.
For this task, keep one review row for each deaccession requirement + file. Record required decision, supplied path, and version. Keep the source location beside each value.
Preserve uncertainty, approximate dates, attribution, and provenance qualifiers during every transformation. Distinguish ownership claims from documented custody.
Do not convert uncertain provenance into a fact. Rights, deaccession, and insurance values need explicit source records.
A hash or non-empty file does not prove PDF, image, Office, audio, video, or archive validity. Use an available format-specific tool and record its result separately. The helper labels format validation as not performed.
This synthetic example shows the included check in use. Your agent uses its findings to complete your task report.
Synthetic example records
| Sample record | path: missing.txt |
|---|
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": "deaccession requirement + file / SYNTHETIC-001", "path": "missing.txt", "sha256": "27b7c827e17a4f158c6a8f92424527b9f408c6a8a68698c9f37b8043eb58b129"}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 supplied process checklist and folder. Confirm the case, period, and source versions before the review.
Use accession ID, object, loan, movement, catalog version to keep records distinct. The agent records the original value, an exact quote, and the source location.
Check listed files inside the chosen folder and compare supplied hashes where present. Run the Python helper on the structured records. Check each finding against its source.
Prepare the task result: missing decision 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.