skills/screenshot/SKILL.md
Take screenshots from the terminal using the screenshot CLI tool. Use this skill when the user wants to capture the screen or a region, save screenshots to files, or integrate screenshot capture into scripts. Supports cross-platform (Windows/macOS/Linux) with automatic fallback to native tools.
npx skillsauth add lirrensi/agent-cli-helpers screenshotInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Take screenshots from the terminal.
screenshot --help
If not installed:
uv tool install "git+https://github.com/lirrensi/agent-sommelier"
screenshot
# Outputs: C:\Users\...\Temp\agentcli_screenshots\screenshot_20260305_160405.png
screenshot output.png
screenshot /path/to/screenshot.png
The command outputs the path to the saved screenshot, making it easy to use in scripts:
# Capture and open
screenshot | xargs open
# Capture and send
screenshot | xargs curl -F "image=@-" http://api/upload
# Capture with timestamp
SCREENSHOT=$(screenshot)
echo "Saved to: $SCREENSHOT"
# Quick capture
screenshot
# Save to specific location
screenshot ~/Desktop/bug_report.png
# In a script
screenshot "/tmp/screenshot_$(date +%s).png"
# Capture and notify
notify "Screenshot" "$(screenshot)"
Uses the mss library for cross-platform screenshots:
If mss is not available, falls back to native tools:
data-ai
Portable SSH profile manager for agents. Run remote commands on saved hosts by friendly name instead of typing user@host -i key every time. Type less crap around your SSH commands.
development
Autonomous execution mode triggered by the word "engage". Use when the user has finished planning and wants the agent to execute autonomously without further questions until the workflow is fully complete. The agent must build, test, verify, and deliver proof of work — never exiting with an incomplete or unverified result. Trigger on: "engage", "go autonomous", "execute the plan", "run it", "make it happen", or any explicit signal to switch from planning mode into fully autonomous build-and-verify mode.
tools
Use this skill when you need to manage project tasks — create, update, complete, prioritize, filter, review, track dependencies, or find unblocked work. Trigger on: 'add a task', 'create task', 'show tasks', 'what's next', 'mark done', 'update task', 'task status', 'task history', 'next task', 'task inbox', 'list tasks', 'init tasks', 'task deps', 'ready tasks', 'blocked tasks', 'search tasks', 'tag-any', 'dependency graph'. Also use proactively when starting a new work session — check `tasks status` and `tasks ready` to orient yourself. This skill covers the project's static, file-based task system (persistent, in-repo history) with typed dependency tracking, ready queue, and priority management — NOT ephemeral runtime task tools.
tools
Control tmux/psmux sessions for interactive CLIs, SSH connections, and parallel agent orchestration. Works cross-platform: tmux on Linux/macOS, psmux on Windows. Provides sync commands that send keys and automatically capture output. Triggers: "run in tmux", "create tmux session", "tmux", "SSH session", "parallel terminals", "run multiple agents".