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

Add vision-analysis skill; move workaround from TOOLS.md; update log-work-expense to skip image analysis

Browse source
This commit is contained in:
Connor Rhodes 2026-04-29 02:40:45 +00:00
parent ac1b4f83f3
commit 9e522fc164
3 changed files with 44 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

2
log-work-expense/SKILL.md
View file

@ -16,6 +16,8 @@ Log work expenses into `wip.work_expenses` via `scripts/log_expense.py`.
1. **Classify images** — Run each image through `scripts/classify_image.py <path>` to determine if it is a `receipt` or `odometer`. The script outputs exactly one word.
⚠️ **Do NOT analyze receipt/odometer images yourself.** Do not extract merchant names, amounts, item details, or calculate mileage. Only classify and upload. The note field should contain only what the user provides or minimal context — never information you derived from reading the images.
2. **Determine type and account** — The user provides the expense type and account (e.g. "meals and mileage for LTISD"). Ask if unclear.
3. **Upload images to S2** — Upload all images to S2 and collect the URLs.