Use Claude to Rename and Organize Architecture Site Photos
Apps it uses
I run operations for my husband’s residential architecture firm, and I have no coding background. After every site visit, dozens of photos landed in Google Drive named `IMG_8834.JPG`. Renaming and filing them took about an hour per visit, when it happened at all. When it didn’t, the photos sat unnamed and unfindable. For an architecture firm, that creates a professional liability gap because the photos document site conditions on a specific date, as well as lost portfolio material and a hole in the firm’s permanent project archive.
I solved this by building a Claude skill: a saved set of instructions that runs the same way every time with one command. I trained it to examine each photo through the eye of a residential architect, describe what the image actually shows using our professional vocabulary, and rename the file in a consistent format. `IMG_8834.JPG` becomes `2026-07-17_03_side-elevation-porch-brick-piers.JPG`—searchable, legible, and filed.
Because it’s a skill rather than a one-off chat, it’s a file I can hand to anyone in the office. Everyone runs the same process and gets identical output.
Step-by-step
- I gathered the raw photos into one “unsorted” folder in Google Drive.
- In Claude’s desktop app, I used Cowork mode, which handles actual files, and connected only that folder—not my whole Drive. This is the safety practice I’d urge anyone to follow: the skill can see and touch only what you connect, so connect the narrowest folder that does the job.
- I created a skill that tells Claude to read each photo, identify what it shows using the industry’s vocabulary, and rename each file in a standard format. I wrote mine for residential architecture, but the approach also works for real estate, inspections, insurance, and other field work. My format is `date_sequence_description`.
- I ran the skill with one command, and Claude worked through the folder photo by photo.
- The renamed photos were filed into a dated site-visit folder, ready to reference by number in reports.
- I handed the skill file to teammates so they could run it on their machines and get the same result.
One caveat for anyone using this on business files: check your client confidentiality obligations and your AI vendor’s data policy before pointing any tool at project files. We did.
I wrote up the full build, including how to decide when something should be a skill versus a regular Claude conversation, at The 2040 Studio: https://the2040studio.substack.com/p/every-img_8834jpg-is-snitching-on
- Industry
- Real Estate & Construction
- Tags
- #photorenaming
4 comments
Have a question about this workflow, or a way to improve it?
Log in to comment Create a free accountThe bit about photos documenting site conditions on a specific date is what makes this more than tidying, and I appreciated you naming the confidentiality caveat. What happens when a photo is genuinely ambiguous and it has to guess?
What you've built makes the archive readable today, and that part works. What I'd worry about is longer term: a filename isn't metadata. It doesn't survive a copy into someone else's system, an import into photo software, or a colleague reorganising the folder, and site photos on a project with any legal life ahead of them tend to do all three. The same descriptions written into the file's own IPTC fields travel with the image forever, and the filename becomes a convenience rather than the only record. The second one is less obvious and, from where I sit, more expensive. IMG_8834 is useless but honest. A generated name that says "north elevation flashing detail" when it's a different assembly is worse than useless, because it asserts something, it reads as professional, and nothing about it looks wrong. In my experience the errors that cost real money are never the ugly ones, they're the confident ones, and an archive is where a confident error sits undetected for years. What's worked for me on footage is refusing to let the system name what it isn't sure about. An archive that's 95 percent named and 5 percent flagged as unidentified is more trustworthy than one that's 100 percent named with 5 percent invisible errors, because the first one tells you where to look. Uncertainty in the output turned out to be a feature. Which is my question, and I ask because I have the same problem cataloguing rushes. Have you ever spot-checked a batch against the actual photos? Not to police it, but because if it does get one wrong, I can't see what the signal would be.
Really smart workflow, especially limiting Claude to the unsorted folder instead of giving it access to the whole Drive. Turning messy site photos into a searchable project archive is a bigger operational win than it sounds. Have you found Claude consistently accurate enough with architectural terminology, or do you still review the filenames before filing them?
This is a great example of solving a small operational task that actually has bigger consequences. Turning site photos into consistently named, searchable records improves both the project archive and the liability trail. Have you found the naming format specific enough when several photos show very similar conditions from different angles?
Posting guidelines