Agent-Skills.md

Agent Skills: Screenshot Capture

Use when the user explicitly asks for a desktop or system screenshot (full screen, specific app or window, or a pixel region), or when tool-specific capture capabilities are unavailable and an OS-level capture is needed.

UncategorizedID: bahayonghang/my-claude-code-settings/screenshot

Repository

bahayonghang/my-claude-code-settings
bahayonghangLicense: MIT
11

Install this agent skill to your local

pnpm dlx add-skill https://github.com/bahayonghang/my-claude-code-settings/tree/HEAD/content/skills/visual-media-design/screenshot

Skill Files

Browse the full folder contents for screenshot.

Download Skill

Loading file tree…

content/skills/visual-media-design/screenshot/SKILL.md

Skill Metadata

Name
"screenshot"
Description
"Use when the user explicitly asks for a desktop or system screenshot (full screen, specific app or window, or a pixel region), or when tool-specific capture capabilities are unavailable and an OS-level capture is needed. Prefer a more specialized capture tool first for browsers, Figma, or other supported apps."

Screenshot Capture

Use this skill for OS-level capture when the user explicitly wants a screenshot or when a more specialized capture tool cannot reach the target.

Workflow

  1. Classify the request: full screen, specific app/window, active window, or pixel region.
  2. Resolve the save target:
    • explicit user path -> save there
    • user asked for a screenshot with no path -> use the OS default screenshot location
    • Codex needs the capture for its own inspection -> use the temp directory
  3. Prefer a tool-specific capture path when it exists and can reach the target cleanly.
  4. Otherwise run the bundled helper for the current platform.
  5. If multiple files are produced, inspect or report them in order instead of pretending there was only one output.
  6. Always return the saved path or paths and the capture mode used.

Output Contract

Return:

  • capture mode used
  • saved file path or paths
  • any important caveat such as multi-display output or app-window matching behavior

Follow these save-location rules every time:

  1. If the user specifies a path, save there.
  2. If the user asks for a screenshot without a path, save to the OS default screenshot location.
  3. If Codex needs a screenshot for its own inspection, save to the temp directory.

Tool priority

  • Prefer tool-specific screenshot capabilities when available (for example: a Figma MCP/skill for Figma files, or Playwright/agent-browser tools for browsers and Electron apps).
  • Use this skill when explicitly asked, for whole-system desktop captures, or when a tool-specific capture cannot get what you need.
  • Otherwise, treat this skill as the default for desktop apps without a better-integrated capture tool.

macOS permission preflight (reduce repeated prompts)

On macOS, run the preflight helper once before window/app capture. It checks Screen Recording permission, explains why it is needed, and requests it in one place.

The helpers route Swift's module cache to $TMPDIR/codex-swift-module-cache to avoid extra sandbox module-cache prompts.

bash <path-to-skill>/scripts/ensure_macos_permissions.sh

To avoid repeated permission checks, combine preflight + capture in one command when possible:

bash <path-to-skill>/scripts/ensure_macos_permissions.sh && \
python3 <path-to-skill>/scripts/take_screenshot.py --app "Codex"

For Codex inspection runs, keep the output in temp:

bash <path-to-skill>/scripts/ensure_macos_permissions.sh && \
python3 <path-to-skill>/scripts/take_screenshot.py --app "<App>" --mode temp

Use the bundled scripts to avoid re-deriving OS-specific commands.

macOS and Linux (Python helper)

Run the helper from the repo root:

python3 <path-to-skill>/scripts/take_screenshot.py

Common patterns:

  • Default location (user asked for "a screenshot"):
python3 <path-to-skill>/scripts/take_screenshot.py
  • Temp location (Codex visual check):
python3 <path-to-skill>/scripts/take_screenshot.py --mode temp
  • Explicit location (user provided a path or filename):
python3 <path-to-skill>/scripts/take_screenshot.py --path output/screen.png
  • App/window capture by app name (macOS only; substring match is OK; captures all matching windows):
python3 <path-to-skill>/scripts/take_screenshot.py --app "Codex"
  • Specific window title within an app (macOS only):
python3 <path-to-skill>/scripts/take_screenshot.py --app "Codex" --window-name "Settings"
  • List matching window ids before capturing (macOS only):
python3 <path-to-skill>/scripts/take_screenshot.py --list-windows --app "Codex"
  • Pixel region (x,y,w,h):
python3 <path-to-skill>/scripts/take_screenshot.py --mode temp --region 100,200,800,600
  • Focused/active window (captures only the frontmost window; use --app to capture all windows):
python3 <path-to-skill>/scripts/take_screenshot.py --mode temp --active-window
  • Specific window id (use --list-windows on macOS to discover ids):
python3 <path-to-skill>/scripts/take_screenshot.py --window-id 12345

The script prints one path per capture. When multiple windows or displays match, it prints multiple paths (one per line) and adds suffixes like -w<windowId> or -d<display>. View each path sequentially with the image viewer tool, and only manipulate images if needed or requested.

Workflow examples

  • "Take a look at <App> and tell me what you see": capture to temp, then view each printed path in order.
bash <path-to-skill>/scripts/ensure_macos_permissions.sh && \
python3 <path-to-skill>/scripts/take_screenshot.py --app "<App>" --mode temp
  • "The design from Figma is not matching what is implemented": use a Figma MCP/skill to capture the design first, then capture the running app with this skill (typically to temp) and compare the raw screenshots before any manipulation.

Multi-display behavior

  • On macOS, full-screen captures save one file per display when multiple monitors are connected.
  • On Linux and Windows, full-screen captures use the virtual desktop (all monitors in one image); use --region to isolate a single display when needed.

Linux prerequisites and selection logic

The helper automatically selects the first available tool:

  1. scrot
  2. gnome-screenshot
  3. ImageMagick import

If none are available, ask the user to install one of them and retry.

Coordinate regions require scrot or ImageMagick import.

--app, --window-name, and --list-windows are macOS-only. On Linux, use --active-window or provide --window-id when available.

Windows (PowerShell helper)

Run the PowerShell helper:

powershell -ExecutionPolicy Bypass -File <path-to-skill>/scripts/take_screenshot.ps1

Common patterns:

  • Default location:
powershell -ExecutionPolicy Bypass -File <path-to-skill>/scripts/take_screenshot.ps1
  • Temp location (Codex visual check):
powershell -ExecutionPolicy Bypass -File <path-to-skill>/scripts/take_screenshot.ps1 -Mode temp
  • Explicit path:
powershell -ExecutionPolicy Bypass -File <path-to-skill>/scripts/take_screenshot.ps1 -Path "C:\Temp\screen.png"
  • Pixel region (x,y,w,h):
powershell -ExecutionPolicy Bypass -File <path-to-skill>/scripts/take_screenshot.ps1 -Mode temp -Region 100,200,800,600
  • Active window (ask the user to focus it first):
powershell -ExecutionPolicy Bypass -File <path-to-skill>/scripts/take_screenshot.ps1 -Mode temp -ActiveWindow
  • Specific window handle (only when provided):
powershell -ExecutionPolicy Bypass -File <path-to-skill>/scripts/take_screenshot.ps1 -WindowHandle 123456

Direct OS commands (fallbacks)

Use these when you cannot run the helpers.

macOS

  • Full screen to a specific path:
screencapture -x output/screen.png
  • Pixel region:
screencapture -x -R100,200,800,600 output/region.png
  • Specific window id:
screencapture -x -l12345 output/window.png
  • Interactive selection or window pick:
screencapture -x -i output/interactive.png

Linux

  • Full screen:
scrot output/screen.png

gnome-screenshot -f output/screen.png

import -window root output/screen.png
  • Pixel region:
scrot -a 100,200,800,600 output/region.png

import -window root -crop 800x600+100+200 output/region.png
  • Active window:
scrot -u output/window.png

gnome-screenshot -w -f output/window.png

Error handling

  • On macOS, run bash <path-to-skill>/scripts/ensure_macos_permissions.sh first to request Screen Recording in one place.
  • If the current runtime blocks the helper, or you hit Swift ModuleCache / display-access errors, report that the helper could not run and fall back to the direct OS command or ask the user to run it locally.
  • If macOS app/window capture returns no matches, run --list-windows --app "AppName" and retry with --window-id, and make sure the app is visible on screen.
  • If Linux region/window capture fails, check tool availability with command -v scrot, command -v gnome-screenshot, and command -v import.
  • If saving to the OS default location fails, switch to an explicit path or temp path and tell the user where the file was saved.
  • Always report the saved file path in the response.