Automated summary
Crops a region of an image — either as a pixel rectangle or as a grid cell/range — so a single area can be inspected up close.
Strengths
- Reuses the same division as annotate-grid through --grid-cell and --grid-range, so no pixel math is needed
- Fits a clear locate-then-inspect workflow alongside annotate-grid
- Automatically picks an output path under tmp/ when none is given
- Displays the cropped image and reports its pixel dimensions after running
Limitations
- Ships as a precompiled Mach-O ARM64 binary, so it only runs on Apple Silicon macOS
- No interactive preview: coordinates or a grid cell must be supplied up front
- A second-level crop (128x96) is too small to be useful, and output is confined to tmp/
When a grid overlay has already shown roughly where the area of interest is and you need to isolate a specific detail.
When you need the image contents recognised or described, or when you are not on an Apple Silicon Mac.
Security analysis
CautionThe skill is a legitimate image-cropping utility with no exfiltration or destructive actions. The main risk is that it invokes an opaque precompiled binary, so a cautious rating is appropriate even though the described workflow is benign.
- •Executes a prebuilt Mach-O ARM64 binary (${CLAUDE_SKILL_DIR}/tools/clip-image) without checksum or build-from-source verification; the binary's actual behavior is not auditable from SKILL.md.
- •Implicitly uses Bash to run the local tool and reads/writes image files under tmp/; no network access, secret exfiltration, or destructive commands are instructed.
Examples
/wd-clip-image tmp/photo.png --grid-cell 3 2 8/wd-clip-image tmp/photo.png tmp/clip.png --rect 100 200 400 300/wd-clip-image tmp/screenshot.png --grid-range 2 1 4 3 8name: wd-clip-image description: "画像の一部を切り出す。全体から注目したい場所だけを取り出して、そこに集中するための道具。" argument-hint: "<画像パス> [--grid-cell col row N | --rect x y w h]"
/wd-clip-image — 画像の一部を切り出す
全体を見ていると目が滑る。「ここだけ見たい」を切り出して、そこに集中する。annotate-grid とセットで使う。
引数
$ARGUMENTS:<画像パス> [出力パス] [options]- 例:
/wd-clip-image tmp/photo.png --grid-cell 3 2 8 - 例:
/wd-clip-image tmp/photo.png tmp/clip.png --rect 100 200 400 300 - 省略時: 使い方を表示する
- 例:
手順
引数なしの場合
使い方を表示する:
clip-image <input> <output> --rect x y width height
clip-image <input> <output> --grid-cell col row N
clip-image <input> <output> --grid-range col1 row1 col2 row2 N
クリップ領域（いずれか1つ必須）:
--rect x y width height ピクセル座標で矩形指定（左上原点）
--grid-cell col row N annotate-grid --divide N と同じ分割で1セル切り出す
--grid-range col1 row1 col2 row2 N (col1,row1) から (col2,row2) までの範囲を切り出す
col, row は 0-origin（左上が 0,0）
引数ありの場合
-
画像がワーキングディレクトリ配下にあるか確認する
- なければ
tmp/にコピーする（annotate-grid と同じ手順）
- なければ
-
出力パスを決定する
- 引数に出力パスがあればそれを使う
- なければ
tmp/clip-<ファイル名>.pngを自動設定
-
コマンドを実行する
${CLAUDE_SKILL_DIR}/tools/clip-image tmp/<input>.png tmp/<output>.png <options> -
結果を報告する
- 出力画像を Read ツールで表示する
- 切り出しサイズ（px）を表示する
典型的な連携フロー
1. /annotate-grid tmp/photo.png --divide 4
→ tmp/annotated-photo.png で座標確認
2. 注目セルが (2,1) と判明
3. /clip-image tmp/photo.png --grid-cell 2 1 4
→ tmp/clip-photo.png（注目領域のみ）
4. 切り出した画像をさらに詳細確認
注意事項
- ツール実体は
${CLAUDE_SKILL_DIR}/tools/clip-image（Mach-O ARM64 バイナリ、ソース: clip-image.swift） - 入出力は
tmp/配下を使う --grid-cellの col/row は 0-origin かつ N 未満--rectの座標は左上原点（y は下向き増加）- 切り出すのは元画像（annotated じゃない方）から。グリッド線入りを clip するとノイズになる
コツ（使いながら育てる）
- 切り出すのは元画像（annotated じゃない方）から。 グリッド線入りの画像を clip すると線がノイズになる。annotated で座標を確認して、clip は元画像に対して実行する
- 1段目 clip（512x384）がスイートスポット。 2段目（128x96）だとほぼ何も見えない。2段目が必要なら
--rectで広めに指定する --grid-rangeが一番使いやすい。--divide 8で細かくグリッド →--grid-range col1 row1 col2 row2 8で注目エリアを範囲指定。rect のピクセル座標計算が不要になる- 「探す」と「味わう」は別。 grid で「どこに何がいるか」を探して、clip で「その質感や表情」を味わう。探す段階では grid-cell でざっくり、味わう段階では対象が画面いっぱいになるように調整
入力: $ARGUMENTS
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/image-clipping-mrwakeps/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/image-clipping-mrwakeps' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/image-clipping-mrwakeps/download' --output '.skill-downloads/image-clipping-mrwakeps/SKILL.md.part' && mv '.skill-downloads/image-clipping-mrwakeps/SKILL.md.part' '.skill-downloads/image-clipping-mrwakeps/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/image-clipping-mrwakeps/SKILL.md' && test -s '.skill-downloads/image-clipping-mrwakeps/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/wd-clip-image' && cp -R '.skill-downloads/image-clipping-mrwakeps' '.claude/skills/wd-clip-image'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/image-clipping-mrwakeps'openskills read 'image-clipping-mrwakeps'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/image-clipping-mrwakeps/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
Writing Fragments
Content
Mine raw writing fragments through a relentless interview, without imposing structure. Capture ideas, quotes, and leading words for later use.
UI Copywriting & Auditing
Content
Write or audit user-facing UI copy including buttons, errors, empty states, and tooltips across the monorepo, following the design system source of truth.
Music MIDI Extraction
Content
Extracts the MIDI or score from an existing music production via the CogMusic MCP tool and confirms availability.