steelmorgan/screenshot
framework/skills/tool-usage/browser-ui/screenshot/SKILL.md
Use for захвата скриншота рабочего стола или окна на уровне ОС (полный экран, конкретное приложение/окно, пиксельная область). Helps получить снимок когда инструментно-специфичный захват (Playwright, Figma MCP) недоступен.
$ install --global
skillsauthnpx skillsauth add steelmorgan/1c-agent-based-dev-framework screenshotInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jun 13, 2026, 5:37 AM50.6s9 files scanned
SKILL.md
- name:
- screenshot
- description:
- Use for захвата скриншота рабочего стола или окна на уровне ОС (полный экран, конкретное приложение/окно, пиксельная область). Helps получить снимок когда инструментно-специфичный захват (Playwright, Figma MCP) недоступен.
Screenshot Capture
Save-location rules:
- User specifies path → save there.
- User asks without path → OS default location.
- Codex self-inspection → temp directory.
Prefer tool-specific captures (Figma MCP, Playwright, agent-browser) when available. Use this skill for explicit requests, whole-system desktop captures, or when tool-specific capture cannot get what you need.
macOS permission preflight
Run once before window/app capture. Combine preflight + capture to reduce sandbox prompts:
bash <path-to-skill>/scripts/ensure_macos_permissions.sh && \
python3 <path-to-skill>/scripts/take_screenshot.py --app "<App>" --mode temp
Python helper (macOS and Linux)
python3 <path-to-skill>/scripts/take_screenshot.py [OPTIONS]
| Option | Example | Note |
|--------|---------|------|
| (none) | | OS default location |
| --mode temp | | Codex visual check |
| --path <path> | --path output/screen.png | Explicit location |
| --app "<Name>" | --app "Codex" | macOS only, substring match |
| --app "<Name>" --window-name "<Title>" | | macOS only |
| --list-windows --app "<Name>" | | macOS only, discover window ids |
| --region x,y,w,h | --region 100,200,800,600 | |
| --active-window | | Frontmost window |
| --window-id <id> | --window-id 12345 | |
The script prints one path per capture. Multiple windows/displays produce multiple paths with -w<id> or -d<display> suffixes.
Linux tool selection (automatic)
Priority: scrot → gnome-screenshot → ImageMagick import → ffmpeg (x11grab). For X11 virtual displays, ffmpeg is often the most practical option in containers:
ffmpeg -y -f x11grab -video_size 1920x1080 -i :99 -frames:v 1 /tmp/screen.png
Display dimensions: DISPLAY=:99 xdpyinfo | grep dimensions
--app, --window-name, --list-windows are macOS-only. On Linux use --active-window or --window-id.
PowerShell helper (Windows)
powershell -ExecutionPolicy Bypass -File <path-to-skill>/scripts/take_screenshot.ps1 [OPTIONS]
| Option | Example |
|--------|---------|
| (none) | Default location |
| -Mode temp | Codex visual check |
| -Path "<path>" | Explicit |
| -Region x,y,w,h | Pixel region |
| -ActiveWindow | Ask user to focus first |
| -WindowHandle <id> | Specific window |
Direct OS fallbacks
macOS
screencapture -x output/screen.png # full screen
screencapture -x -R100,200,800,600 output/region.png # region
screencapture -x -l12345 output/window.png # window id
Linux
scrot output/screen.png # full
scrot -a 100,200,800,600 output/region.png # region
scrot -u output/window.png # active window
import -window root output/screen.png # ImageMagick full
ffmpeg -y -f x11grab -video_size 800x600 -i :99+100,200 -frames:v 1 output/region.png
Error handling
- macOS sandbox errors ("screen capture blocked",
ModuleCache) → rerun with escalated permissions - macOS no matches →
--list-windows --app "Name"→ retry with--window-id - Linux tool missing →
command -v scrot,command -v import - Always report saved file path
Related Skills
steelmorgan/source-of-truth
testing
VerifiedTrustedCommunity
MUST use BEFORE making a judgment about the cause of a conflict, a test failure, or an artifact dispute. Defines the end-to-end verification method L1→L6 and the classification of the first broken link.
69SKILL.mdUpdated Jun 13, 2026
steelmorgan/skill-learning
development
VerifiedTrustedCommunity
MUST use AFTER a work cycle with ≥2 iterations (wrote → error → fixed → success). Provides the retrospective procedure and the format for recording practice/anti-patterns in references/learned-patterns.md or {project}/.context/learned-patterns.md.
69SKILL.mdUpdated Jun 13, 2026
steelmorgan/rlm-workflow
tools
VerifiedTrustedCommunity
MUST use WHEN you are writing reusable knowledge into RLM (pattern / architectural decision / stable domain fact) OR reading it before a non-trivial task/solution in the domain. Provides the breakdown of native-push vs RLM-pull, tools for writing and reading RLM, H-MEM levels, and hygiene.
69SKILL.mdUpdated Jun 13, 2026
steelmorgan/quick-fix
testing
VerifiedTrustedCommunity
MUST use WHEN the task is classified as simple (< 20 lines, 1 file, no new metadata objects, no architectural decisions). Provides a short cycle of 3 steps with a guard on the self path and mandatory verify.
69SKILL.mdUpdated Jun 13, 2026