I let a local Gemma 4 name my screenshots (and it caught my fake password)
Description and use
Automatically renaming screenshots and detecting secrets with a local Gemma 4 model cut the manual effort from 10‑15 minutes to 25 seconds and prevented a password leak.
Problem
Manually renaming many screenshots is tedious and error‑prone, and screenshots may contain sensitive data that should not be shared.
Outcome
Renamed eight screenshots in 25 seconds versus 10‑15 minutes manually, and automatically flagged a fake password with no false positives.
Workflow
- Scan each image in the folder
- Use a local Gemma 4 model via Ollama to generate a one‑sentence description and a "sensitive: yes/no" flag
- Convert the description into 2‑5 hyphenated words for the filename
- Perform a dry run to preview changes
- Apply the renaming with --apply, ensuring no overwrites and logging to CSV
Evidence
Turns "Screenshot 2026-10-11 173802.png" into "sql-show-chunks.png". A local Gemma 4 model looks at each screenshot, describes it and suggests a name that says what's inside.
It also flags screenshots that seem to contain a password or a key, before they end up in a repo or a blog post.
I could fix what broke. The endless names, the copied example and the ignored content were all fixed by changing things I fully control: the output limit, the prompt and the number of steps.
By hand, last week: about 10 to 15 minutes for 7 screenshots (look, think of a name, F2, type). With the namer: 8 screenshots in 25 seconds (from 12:26:49 to 12:27:14 in the rename log), plus about a minute to read the dry run.
- Record date: 2026-10-25T13:11:25.307Z