capture-screen
An agent skill by daymade, from daymade/claude-code-skills. Tags: automation, macos, screenshot, visual-art.
What it does
Programmatic screenshot capture on macOS. Find window IDs with Swift CGWindowListCopyWindowInfo, control application windows via AppleScript (zoom, scroll, select), and capture with screencapture. Use when automating screenshots, capturing application windows for documentation, or building multi-shot visual workflows.
Install
With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:
npx skills add daymade/claude-code-skills --skill capture-screen
Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):
git clone --depth 1 https://github.com/daymade/claude-code-skills
cp -r claude-code-skills/daymade-macos/capture-screen ~/.claude/skills/capture-screen
Safety box score
Grade C, moderate risk: 26 of 100 risk points, rated 2026-10-19. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.
This skill captures macOS window screenshots and can control app windows through Swift, AppleScript, and `screencapture`. The main risks are local code execution, foreground UI manipulation, and a troubleshooting path that may use `sudo` to inspect Apple’s TCC privacy database.
| Category | Level | Why |
|---|---|---|
| Code & shell execution | 2 (moderate) | It shells out to `swift`, `osascript`, `screencapture`, and `sips`, including inline code like `swift -e '...'` and multiple `osascript -e '...'` examples. |
| Network access | 0 (none) | There is no downloading, uploading, or remote API use in the shipped files. |
| Filesystem reach | 1 (low) | It writes screenshot files such as `output.png`, `section_a.png`, and `output_1x.png` in user-chosen locations, but does not touch broad system paths. |
| Secrets & credentials | 0 (none) | It does not access keychains, tokens, `.env` files, browser sessions, or other credential stores. |
| Privilege & persistence | 2 (moderate) | The bundled permission template explicitly uses `sudo sqlite3 '/Library/Application Support/com.apple.TCC/TCC.db' ...`, which requires root to inspect system privacy state. |
| Instruction hijack surface | 1 (low) | The skill contains strong behavior directives for the agent, including "proceed without asking again" after explicit idle-desktop authorization and rules about stopping or not restoring focus. |
| Irreversible actions | 0 (none) | It controls and captures windows locally but does not send messages, publish, deploy, pay, book, or delete anything. |
| Transparency | 0 (none) | All shipped content is readable text or Swift source; there are no binaries, base64 blobs, or downloaded installers. |
Before installing
- Read `references/permission-triage-template.md` and decide whether you are comfortable with a skill that may inspect `TCC.db` via `sudo`.
- Confirm you want an automation skill that can run `swift`, `osascript`, and `screencapture` on your Mac.
- Test `scripts/get_window_id.swift` in a scratch account with Screen Recording denied so you understand the permission flow and prompts.
Rated 2026-10-19 by an automated review of 3 files from the skill's repository.
Source
- Repository
- daymade/claude-code-skills (all skills from this repository)
- Path
- daymade-macos/capture-screen/SKILL.md
- Branch
- main
- Updated
- 2026-09-20
Related skills
- excel-automation — Create, parse, and control Excel files on macOS.
- macos-watchdog — Design, deploy, and discipline macOS launchd watchdogs — LaunchAgents/LaunchDaemons that detect a recurring problem and auto-remediate it.
- agentic-actions-auditor — Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex.
- agents-build — Use to extend an existing agent project with memory, app integration, VPC, multi-agent, migration, model, browser, code interpreter, payments.
- agents-connect — Use when connecting your agent to external APIs, tools, or services via Gateway, or restricting tool access with Cedar policies.
- agents-deploy — Use when deploying your agent to AWS, or when a deploy has failed.