deepagents: Skill for Claude Code

Textual Screenshot

Render the real app with Textual's headless test harness, drive it to the requested state, and save the composed terminal as SVG. Prefer this over browser automation or OS-level screenshot tools.

Capture workflow

1. Identify the App class and the shortest trusted local setup that reaches the requested UI.
2. Write a temporary Python script outside the repository. Keep generated screenshots outside the repository unless the user explicitly requests a committed artifact.
3. Start the app with a deterministic terminal size using app.run_test(size=(columns, rows)).
4. Call await pilot.pause() after startup and after every action that changes visible state. Use pilot.press(...) for a realistic interaction path when practical; direct app methods are acceptable for a focused preview.
5. Call app.save_screenshot(output_path) while the desired state is visible. Use an .svg path.
6. Inspect the resulting SVG and confirm its file size is reasonable before sharing it.
7. Delete temporary scripts and captures when they are no longer needed.

Minimal deepagents-code example:

import asyncio
import os
from pathlib import Path
from tempfile import TemporaryDirectory
from unittest.mock import AsyncMock, MagicMock, patch


async def main() -> None:
    output = Path("/tmp/dcode-ui.svg")
    with TemporaryDirectory() as profile:
        os.environ["DEEPAGENTS_HOME"] = profile
        from deepagents_code.app import DeepAgentsApp

        app = DeepAgentsApp(agent=MagicMock())
        with patch.object(app, "_post_paint_init", new=AsyncMock()):
            async with app.run_test(size=(110, 36)) as pilot:
                await pilot.pause()
                await app._handle_command("/model")
                await pilot.pause()
                app.save_screenshot(output)
    print(output)


asyncio.run(main())

Run from libs/code so the project environment and editable package resolve:

uv run python /tmp/capture_dcode_ui.py