agentleFS
matheus-rib1108matheus-rib1108/claude-skills-br/skills/photo-editor/SKILL.md

photo-editor

Skill0 starsChanged 32 days agoMITView on GitHub

Improves and edits photos locally — fixes light, color and contrast, removes noise, sharpens, upscales with AI (2x-4x), removes the background, crops for Instagram/TikTok/site formats, and makes before/after comparisons. Use when the user sends a photo and asks to "melhorar a foto", "deixar mais bonita/nítida", "aumentar a qualidade", "tirar o fundo", "recortar pro Instagram", or needs images prepared for a site.

  • Installs packages

2 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Look at the photo first and say what you'll fix (dark?

    line 19

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Photo editor

python3 <this-skill-dir>/scripts/photo.py enhance  in.jpg out.jpg
python3 <this-skill-dir>/scripts/photo.py upscale  in.jpg out.jpg 4
python3 <this-skill-dir>/scripts/photo.py nobg     in.jpg out.png
python3 <this-skill-dir>/scripts/photo.py resize   in.jpg out.jpg 1080x1350
python3 <this-skill-dir>/scripts/photo.py compare  in.jpg out.jpg compare.jpg

Install once if missing: pip install pillow opencv-contrib-python-headless numpy rembg onnxruntime. Models download on first use (needs internet).

Steps

  1. Look at the photo first and say what you'll fix (dark? blurry? noisy? bad crop?).
  2. Usual order: upscale (only if small/blurry) → enhance → resize to the target format.
  3. Make a compare image and look at it. Faces must stay natural: if skin looks plastic or colors are off, redo with fewer steps. Never change someone's face or body shape unless they ask for it.
  4. Send the result file(s) to the user.

Formats

Instagram feed 1080x1350 · Stories/Reels/TikTok 1080x1920 · square 1080x1080 · site hero 1920x1080 (then export WebP for the site: cwebp -q 80).

Beyond this script

  • Generative edits (add/remove objects, change background scene) need an image model: plugin canva (already enabled) or an API the user has (e.g. Gemini, OpenAI images).
  • Old/damaged photo restoration of faces: GFPGAN / CodeFormer (heavier install; offer it).

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.