TateZhouSiu

Convert slide/page images into editable PowerPoint PPTX decks by using Image Split visual layers, region schemas, transparent editable text, and QA gates. Use when Codex is given PNG/JPG/Image2/AI-generated slide images and asked to reconstruct image-based PPT pages, keep text editable, preserve layout, or turn flat slide screenshots into PPTX with selectable text and movable image objects.

Split generated slide/page images into editable-ready transparent visual element layers. Use when Codex needs to extract PPT/Image2/AI-generated slide visuals into PNG assets, separate text from visual components, preserve original slide layout, build a "visual elements" folder, create CopySlides-like region schemas, run OCR-racing evidence, rebuild slide visuals before adding editable text, or avoid OCR/OpenCV fragmentary split failures.

Create tight, auditable task briefs for multi-agent or sub-agent work. Use when Codex needs to plan, delegate, scope, or review work across roles such as read-only explorer, scoped implementation worker, auth/security reviewer, verification agent, or handoff agent; especially when the user provides or asks for a Role/Goal/Context/Allowed actions/Ownership/Forbidden actions/Output format/Stop condition template.