菜单
Capture per-slide screenshots for PPTX cross-validation. Use when a presentation needs slide-level screenshots captured through a simulator-visible viewer surface, then reused as image inputs for caption validation.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Export deterministic component-level OCR evidence for one transparent or semi-transparent image by splitting alpha-connected components, writing a component table, and running OCR on each component. Use when bounded component evidence must be exported before any downstream refinement or caption rerun.
Extract bounded OCR evidence from local image files with macos-ocr-mcp, using macOCR only as a fallback reference when MCP coverage is insufficient. Use when downstream refinement or review needs visible-text evidence, not final semantic decisions.
Wrap object-isolation correction as a repo-specific workflow. Use when a local image already exists, the current isolation result is imperfect, and the next step is to choose between ImageSorcery-first, imagegen-first, or a hybrid correction path with a bounded correction packet and worker run.
Promote a bounded parser raw sidecar artifact into the canonical Table -> Row -> Cell schema. Use when a parser MCP returned markdown plus nested JSON sidecars and the project must normalize that output before any downstream wrapper, worksheet, or RAG consumer reads it.
Triage a bounded batch of PPT-extracted images to find the small subset that is mechanically sufficient for alpha-only component splitting. Use when conservative preprocessing is required and only review-gated deterministic candidates should advance beyond the full-image baseline.
Operate an existing markdown review surface in VS Code with fabriqa for same-page image editing and Foam for backlinks and graph navigation, without redefining machine-truth semantics.
| name | pptx-slide-screenshot-capture |
| description | Capture per-slide screenshots for PPTX cross-validation. Use when a presentation needs slide-level screenshots captured through a simulator-visible viewer surface, then reused as image inputs for caption validation. |
Use this skill for the third validation path in the presentation image pipeline:
PPTX -> slide viewer surface -> simctl screenshot -> image-to-API caption validation
This skill is separate from raw PPTX media extraction. Use it when slide-level visual appearance matters and the validation target should match what a viewer sees on screen.
.pptx file is already available locally.xcrun simctl is available and a simulator can be used for capture.control/project_domain/resources/cross_validation/<job_name>/xcrun simctlview_image for spot checks after capturepptx for any PPTX-specific handling before captureios-demo-capture-loop as an operational reference for simulator screenshot habitsreferences/viewer-surface-requirements.md for what must already exist before simctl screenshot is usefulreferences/troubleshooting.md for known sandbox and simulator failure patternsscripts/capture_simctl_slide_screenshots.py captures the current simulator-visible slide sequence and writes slide_screenshots_simctl_dataset.jsonlcontrol/project_domain/resources/cross_validation/<job_name>/cross_validation_manifest.json.control/project_domain/resources/cross_validation/<job_name>/slide_screenshots_simctlpython3 <path-to-skill>/scripts/capture_simctl_slide_screenshots.py --job-manifest <cross_validation_manifest> --udid <UDID> --slide-count <N> --manual-advanceview_image.slide_no, screenshot_path, and source_pptx.slide-0001.png.slide_screenshots_simctl/slide-*.pngslide_screenshots_simctl_dataset.jsonlxcrun simctl reliably and raise a CoreSimulatorService connection invalid error.
If that happens, rerun the helper unsandboxed rather than changing the capture logic first.control/project_domain/resources/pptx_jobs/<job_name>/manifest.json.