image2pptxConvert static images (slides, posters, infographics) to editable PowerPoint files. OCR detects text, classical CV textmask detects ink pixels, mask-clip pre...
Install via ClawdBot CLI:
clawdbot install minutemighty/image2pptxGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
eval(Calls external URL not in known-safe list
https://github.com/JadeLiu-tech/px-image2pptxAI Analysis
The skill definition describes a local image processing tool using standard computer vision/OCR libraries with no evidence of data exfiltration, credential harvesting, or hidden malicious instructions. The only external reference is the GitHub source code repository, which is expected for open-source tools and does not indicate runtime data transmission.
Audited Apr 17, 2026 · audit v1.0
Generated Sep 22, 2026
Marketing teams receive speaker decks as flattened images or PDFs and need to quickly rebuild them as editable PowerPoint files for branding updates, translation, or content edits. Using image2pptx, they extract text boxes and colors while preserving the slide background via inpainting.
Professors and students convert screenshots of lecture slides or textbook figures into editable decks for note-taking, translation, or adaptation into new presentations. The OCR pipeline handles multilingual slides with English and Chinese content automatically.
Enterprises digitizing legacy slide libraries stored as scanned images or exported JPEGs can rebuild them into a unified editable template. Batch processing with pre-computed OCR JSON and --skip-inpaint speeds up migration when backgrounds are solid.
Content creators and social media managers convert infographics and posters into editable PowerPoint files so text can be updated for different campaigns without redesigning graphics from scratch. The mask-clip step preserves illustrations and charts while selecting only typographic elements.
L&D teams localize training decks by extracting text from image-based slides, translating it, and reassembling editable text boxes over the original backgrounds. Multilingual OCR support enables quick turnaround across language variants.
Offer the skill as a free open-source CLI while charging for a cloud API that handles large batches, model hosting, and higher-resolution inpainting. Users avoid the 370 MB model download and GPU requirements.
Ship a polished desktop app or PowerPoint/Figma plugin with free limited monthly conversions and paid unlimited tiers. The plugin integrates directly into tools users already have open.
Bundle image2pptx with a managed service that ingests clients' scanned slide libraries, e.g. for law firms, publishers, or training vendors, and returns branded editable decks. Includes human QA for crowded charts or decorative fonts.
💬 Integration Tip
Pre-compute OCR JSON and use --skip-inpaint for solid-background images to cut processing time and avoid the 370 MB model download; always warn users about inpainting artifacts when text overlaps photos or uses very large decorative fonts.
Scored Sep 22, 2026
Generate images using multiple AI models — Midjourney (via Legnext.ai), Flux, Nano Banana Pro (Gemini), Ideogram, Recraft, and more via fal.ai. Intelligently...
Perform image manipulation tasks like background removal, resizing, format conversion, rounding corners, watermarking, and color adjustments using ImageMagic...
A specialized skill for generating high-quality, consistent children's bilingual picture books using 'banana nano'. Supports 18 visual styles across 4 catego...
从图片中提取表格数据并输出为表格和CSV格式;当用户需要从图片提取表格数据、识别表格内容或导出CSV时使用;触发条件:试验图片表格提取,图片表格提取,试验图片数据提取,提取图片数据,提取试验数据
Generate or edit images with Gemini using the Google GenAI SDK. Use when the user asks to create, transform, render, or save one or more images in an OpenCla...
提供图片生成能力:输入文本描述生成图片,可附加风格提示词。支持 1-4 张图片生成,按图片尺寸对应点数计费。Authorization 使用本系统发放的 Bearer Token。