agentleFS
danielrosehilldanielrosehill/Claude-Image-Production-Plugin/skills/read-metadata/SKILL.md

read-metadata

Skill21 starsChanged 7 days agoMITView on GitHub

Read and display EXIF, IPTC, XMP, and other metadata from images as structured JSON. Use when you need to inspect image metadata without modifying it — opposite of scrub-metadata, which removes metadata.

  • Installs packages

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Recursive?: If directory, ask whether to descend.

    line 21
  2. Distinctive:

    Directory (non-recursive): read all image files in the folder.

    line 38
  3. Very specific:

    Recursive: use find to walk the tree.

    line 39
  4. Distinctive:

    If the user wants a summary, parse the JSON:

    line 82
  5. Very specific:

    GPS privacy: Check for -GPS tags before sharing a photo.

    line 111

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Read Image Metadata

Extract metadata from image files using exiftool and output as structured JSON. Supports single files, batch operations, and filtering by metadata group (EXIF, IPTC, XMP, GPS, etc.).

When to use

  • Inspecting the metadata on a photo before sharing or publishing.
  • Auditing a batch of images to verify copyright, GPS, or camera information.
  • Programmatically querying metadata for file organization or validation.

Inputs to gather

  • Input file or directory — single image or folder. Default: current directory.
  • Recursive? If directory, ask whether to descend. Default: no (flat).
  • Filter/group (optional) — ask if they want a specific metadata subset (e.g., EXIF only, GPS only, copyright-related tags). Default: all metadata.
  • Output format — JSON (default) or a human-readable summary. Recommend JSON for programmatic use, summary for quick inspection.

Procedure

1. Check tooling

command -v exiftool || echo "exiftool not installed — install with: sudo apt install libimage-exiftool-perl"

Abort if missing.

2. Determine scope

  • Single file: direct read.
  • Directory (non-recursive): read all image files in the folder.
  • Recursive: use find to walk the tree.

3. Read metadata

Single file, full metadata as JSON:

exiftool -j "<file.jpg>"

Single file, summary (human-readable):

exiftool -G1 -a -s "<file.jpg>" | head -50

Filtered by group (EXIF only):

exiftool -j -G1 -EXIF "<file.jpg>"

Common filters:

  • -EXIF — EXIF metadata only.
  • -IPTC — IPTC tags (description, keywords, copyright).
  • -XMP — XMP metadata (structured, often used by Adobe).
  • -GPS — GPS coordinates (latitude, longitude, altitude).
  • -MakerNote — camera-specific metadata.

Batch (directory or recursive):

find <target> -maxdepth <1|999> -type f \
  \( -iname '*.jpg' -o -iname '*.jpeg' -o -iname '*.png' \
     -o -iname '*.heic' -o -iname '*.webp' -o -iname '*.tif' \) \
  -exec exiftool -j {} \; > metadata.json

4. Summarize or display

For JSON output:

If the user wants a summary, parse the JSON:

exiftool -j "<file.jpg>" | jq '.[] | {File, Make, Model, DateTime, GPSLatitude, GPSLongitude, Copyright}'

For a batch report:

exiftool -j -a -s "<target>/*" | jq '.[] | {FileName, Make, Model, LensModel, FocalLength, ISO, ExposureTime, FNumber}'

5. Report

Print the metadata (JSON or summary, per user preference). If batch:

  • Count of files read.
  • Any files with missing metadata.
  • Common metadata patterns (e.g., "15 images from Canon EOS 5D Mark III", "8 images missing GPS").

Output / side effects

  • Metadata displayed on stdout (or saved to a JSON file if requested).
  • No files modified.

Notes

  • Metadata standards overlap: EXIF, IPTC, and XMP sometimes describe the same field (e.g., copyright, description, keywords). exiftool -j merges these intelligently; check the JSON keys to see what's present.
  • Camera-specific tags: Each camera manufacturer (Canon, Nikon, Sony, etc.) embeds maker-specific metadata. Run with -MakerNote to inspect.
  • GPS privacy: Check for -GPS tags before sharing a photo. Many smartphone cameras and some cameras embed GPS by default.
  • Phone metadata: iPhones embed extensive metadata in EXIF and XMP, including model, iOS version, and processing applied.
  • PNG text chunks: PNG metadata lives in text chunks (tEXt, iTXt) rather than EXIF. exiftool reads them as XMP or PNG metadata.
  • Batch JSON: Combine multiple JSON objects with jq -s '.' output.json to create a single JSON array for programmatic processing.
  • Depends: apt install libimage-exiftool-perl.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.