Skills for Real Engineers. Straight from my .agents directory.
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
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)
1# Image Edit23Edit 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.45This 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.67## Tool89- `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.1415Do not call other image CLIs, local scripts, or external image APIs.1617## When to use18…
Excerpt shown under the repository's MIT license.
More skills in AiToEarn
Similar skill repositories
Public repository for Agent Skills
An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.
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
Production-grade engineering skills for AI coding agents.
Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
