Tooluck logoTooluck
SKILL.md

image-edit

Agent skill fromyikart/AiToEarn

Edit an existing image with deterministic pixel operations via image_edit — rotate, flip, crop (free/ratio/circle), resize, compress/format-convert, adjust brightness/saturation/contrast, sharpen, blur, mosaic, rounded corners, negate, overlay, and image watermark. Use when the user asks to 裁剪/旋转/翻转/缩放/压缩/打码/马赛克/加水印/叠图/圆角/调亮/调暗/锐化/模糊 an existing image, convert format, or hit a file-size limit. For AI re-creation, restyle, or adding text, use image-creation instead.

How to install image-edit

install image-edit
# install the AiToEarn pack with the skills CLI
npx skills add yikart/AiToEarn

# or add only this skill to Claude Code: copy the folder

skills/claude-plugin-aitoearn/skills/image-edit/

# into

~/.claude/skills/image-edit/ (all projects)

.claude/skills/image-edit/ (one project)

skills/claude-plugin-aitoearn/skills/image-edit/SKILL.md

MITFull file
1# Image Edit
2
3Edit an existing image with `image_edit` — a local, deterministic pixel pipeline. No AI model and no credits for `image_edit` itself; the auxiliary `probe_image_metadata` call is billed per use. The result is pixel-exact and repeatable.
4
5This is **fine-grained image editing**: unlike AI re-creation (`image-creation`), every operation is pixel-exact. Precision is the premise — free-crop regions, mosaic areas, watermark/overlay positions, and drawn shapes are source-image pixel coordinates, so always work from the real dimensions returned by `probe_image_metadata`, never from guesses.
6
7## Tool
8
9- `image_edit`: one call per image. Pass `url` (source image) plus `operations`, an ordered array of 1–20 operations applied in sequence.
10- `probe_image_metadata` (auxiliary): read the source image's real width/height, format, and size with `info_type=metadata` (default). When transparency matters, use `info_type=alpha`; it also returns width/height/format, so do not call metadata first unless size is also required. Each probe is billed; do not call it again for the same URL.
11- Output: `url` (edited image), `width`, `height`, `format`, `sizeBytes`.
12- `compress` must be the **last** operation (it is the export step).
13- Operations that introduce transparency (circle crop, rounded corners) output PNG with alpha.
14
15Do not call other image CLIs, local scripts, or external image APIs.
16
17## When to use
18…

Excerpt shown under the repository's MIT license.

More skills in AiToEarn

Keep exploring

Similar skill repositories

thedotmack /

claude-mem
116k

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

CCCXGHGM+135 skills

Leonxlnx /

taste-skill
113k

Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages

CCCXCU1 skill

Newsletter

Join the Community

Subscribe to our newsletter for the latest news and updates