Menu
Capture clipboard image and let the agent view it directly with multimodal vision. Trigger with /x4:ps.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Use when x4-e2e-test-doc-details needs fixture patch rules or helper guidance for X4 E2E test data.
Use when refining X4 `e2e_tests.md` into detailed E2E task, fixture, and implementation knowledge documents before Playwright implementation.
Use when creating or updating only the high-level X4 E2E test plan `e2e_tests.md` before detail expansion.
Review X4 E2E test documentation draft and gate x4-e2e-test-doc completion. Must run in a dedicated isolated subagent. Trigger with /x4:e2e-test-doc-viewer <change-name>.
Implement Playwright E2E tests for X4 changes from `e2e_test_tasks.md` and validate task-to-test mapping. Trigger with /x4:e2e-test-impl <change-name>.
Run change-scoped X4 Playwright E2E tests and validate implementation coverage against `e2e_test_tasks.md`. Trigger with /x4:e2e-test-run <change-name>.
| name | x4-ps |
| description | Capture clipboard image and let the agent view it directly with multimodal vision. Trigger with /x4:ps. |
Use this skill for /x4:ps when the user wants the agent to see an image quickly.
/x4:psCapture the current clipboard image into a file, then inspect it with multimodal vision (not OCR by default).
bash skill-scripts/copy-img-clip.sh
1, stop and report failure (clipboard has no image or capture failed).0, read the stdout path (full image path).Image: <full-path>Result: <what is visible>Confidence/limits: <if small or unclear regions exist>