connor/assistant-skills
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

remove OCR, use today's date and ask user for merchant

Browse source
This commit is contained in:
Connor Rhodes 2026-04-29 02:02:15 +00:00
parent 6d6baa79fa
commit f18d6b25ad
2 changed files with 5 additions and 74 deletions
Download patch file Download diff file Expand all files Collapse all files

19
log-work-expense/SKILL.md
View file

@ -16,23 +16,15 @@ Log receipt images and expense details into the `wip.work_expenses` collection i
## Steps
1. **Extract receipt info** — If the user sent an image, run the OCR script to read the merchant and amount:
1. **Upload the receipt image to S2** — If the user provided an image, upload it to S2 and get the public URL. If they only provided a file or no image, skip this step.
```bash
uv run --with requests python3 scripts/ocr_receipt.py /path/to/image.jpg
```
The script is located at `~/notes/skills/log-work-expense/scripts/ocr_receipt.py`. It returns JSON with `merchant` and `amount` fields. If they only provided text, use that.
2. **Upload the receipt image to S2** — If the user provided an image, upload it to S2 and get the public URL. If they only provided a file or no image, skip this step.
3. **Insert into MongoDB** — Insert a document into `wip.work_expenses` with this structure:
2. **Insert into MongoDB** — Insert a document into `wip.work_expenses` with this structure:
```json
{
"file": "https://s2.connorrhodes.com/agent/{sha256}.{ext}",
"date": "YYYY-MM-DD",
"merchant": "Name of the merchant from the receipt (e.g. Starbucks, 7 Eleven)",
"merchant": "Name of the merchant",
"description": "Context the user provided about the expense",
"status": "todo"
}
@ -40,14 +32,13 @@ The script is located at `~/notes/skills/log-work-expense/scripts/ocr_receipt.py
- **file**: The S2 URL of the uploaded receipt image. Omit if no image was provided.
- **date**: Always use today's date (the date you receive the message), formatted as YYYY-MM-DD.
- **merchant**: Extracted from the OCR result.
- **merchant**: Ask the user if not stated.
- **description**: What the user told you about the expense (e.g. "travel meal during LTISD onsite"). If they didn't provide context, ask.
- **status**: Always set to `"todo"` when inserting.
4. **Confirm** — Reply with a brief confirmation showing what was logged (date, merchant, and file link if applicable).
3. **Confirm** — Reply with a brief confirmation showing what was logged (date, merchant, and file link if applicable).
## Notes
- Use `uv run --with pymongo` for MongoDB scripts.
- Use the S2 upload endpoint from TOOLS.md for file uploads.
- If the user sends a receipt without context, log what you can read from the image and note that context is pending.