A user's Claude Code handled non-coding tasks: photo edits, PDF analysis for exam prep, killing a hung process, finding materials, checking warranties, and renaming an agent across files.
A user's Claude Code handled non-coding tasks: photo edits, PDF analysis for exam prep, killing a hung process, finding materials, checking warranties, and renaming an agent across files.
The user asked their Claude Code assistant to list recent tasks solved together. It rotated a photo from a shared folder and copied it to the clipboard, read a PDF exam to identify question types, located and killed a hung process, searched for cheap weatherproof steel, checked remaining warranties, combined and scaled two photos, explained a share dialog sentence, and renamed an agent name across six files.
All tasks completed without being programming work; code was generated only when the user explicitly requested it.
I'm going to give you some everyday chores in this folder: [list of tasks, e.g. resize photos in /photos, summarize the PDFs in /study for an exam on [topic], find files about [subject], rename [old name] to [new name] across my files]. Do them one at a time and tell me what you changed. Pause and show me the list of files before you rename, overwrite or delete anything. Finish with a short recap of each task.
A Claude Code-built agent checked ESPN every 30 minutes and sent each 2026 World Cup final score, written up in a persona, to a 3-person Signal group, with a code check on scores.
The poster exports Garmin data into a Claude project and meal planner, where Claude spotted a link between eating more on one day and reduced medication efficacy.
A Claude Cowork skill tracks diet and medical metrics in a spreadsheet, and meals told to Claude on mobile are logged in the daily record.