macOS 截圖擷取與分析。「截圖」「擷取畫面」等觸發。
Scanned 9/7/2026
Install to Claude Code
npx -y skills add wasabeef/claude-code-cookbook --skill screenshot --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Screenshot?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/wasabeef-screenshot-3db97038)More formats (shields.io, HTML) on the badges page.
---
description: "macOS 截圖擷取與分析。「截圖」「擷取畫面」等觸發。"
allowed-tools:
- Bash(screencapture *)
---
# macOS 截圖擷取與分析
在 macOS 上截取屏幕並分析圖像。
## 使用方法
```bash
/screenshot [選項]
```
## 選項
- 無 : 選擇窗口 (Claude 會確認選項)
- `--window` : 指定窗口截圖
- `--full` : 截取整個屏幕
- `--crop` : 選擇範圍截圖
## 基本示例
```bash
# 截取窗口並分析
/screenshot --window
"分析截取的画面"
# 選擇範圍並分析
/screenshot --crop
"說明選中範圍的內容"
# 全屏截圖並分析
/screenshot --full
"分析整個屏幕的構成"
```
## 與 Claude 的協作
```bash
# 無特定問題 - 情况分析
/screenshot --crop
(Claude 會自動分析屏幕內容,說明元素和構成)
# UI/UX 問題分析
/screenshot --window
"提出這個 UI 的問題點和改進方案"
# 錯誤分析
/screenshot --window
"告诉我這個錯誤消息的原因和解決方法"
# 設計審查
/screenshot --full
"從 UX 角度評估這個設計"
# 代碼分析
/screenshot --crop
"指出這段代碼的問題"
# 數據可視化分析
/screenshot --crop
"分析從這個圖表中可以讀取的趨勢"
```
## 詳细示例
```bash
# 從多個角度分析
/screenshot --window
"分析這個画面的以下方面:
1. UI 的一致性
2. 可訪問性問題
3. 改進建議"
# 為比较分析多次截圖
/screenshot --window
# (保存 before 圖像)
# 進行更改
/screenshot --window
# (保存 after 圖像)
"比较 before 和 after 圖像,分析變更點和改進效果"
# 聚焦特定元素
/screenshot --crop
"評估選中按钮的設計是否與其他元素協調"
```
## 禁止事項
- **禁止在未截圖的情况下說"已截圖"**
- **禁止尝試分析不存在的圖像文件**
- **`/screenshot` 命令不會實際執行截圖**
## 注意事項
- 未指定選項時,請提示以下選擇:
```
"請選擇截圖方式?
1. 選擇窗口 (--window) → screencapture -W
2. 整個屏幕 (--full) → screencapture -x
3. 選擇範圍 (--crop) → screencapture -i"
```
- 請在用戶執行 screencapture 命令後開始圖像分析
- 指定具體問題或觀點可以進行更有针對性的分析
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling