A code-driven presentation generation framework. 像构建软件工程一样生成演示文稿。
A portable AI agent skill and architecture compiler for polished, editable, evidence-grounded Draw.io diagrams.
专注PPT与Slides制作，讲得漂亮，排得整齐。支持PowerPoint与LaTeX Beamer，多模态AI逐页看图、反复精调，摆脱AI味，打磨复杂图表、公式与代码。21套模板，按需搭配多语言讲稿，上游模板Skill更新自适应保留定制规则。
AI skill for mirroring public webpages into local pixel-perfect replicas with captured assets, visual QA, and rebranding inventories. 像素级复刻公开网站，内置抓取资源、视觉QA能力和品牌替换清单。
AI가 청중에 맞는 HTML 발표자료와 발표 노트를 만들고 Chromium 기반 시각 검증까지 수행하도록 돕는 스킬·플러그인
AI Computer Use for Claude Code — The open-source alternative to OpenAI Codex's playwright-interactive. Dual-engine: Win32 API + Playwright. Control WeChat, DingTalk, Feishu, QQ, Slack, Teams, and any web/Electron app. Automated QA, viewport testing, visual feedback loops.
Rebuild reference images as editable Microsoft Visio diagrams using Codex, MCP, COM/ShapeSheet, resumable rendering, and visual QA.
Codex skills for professional Word and PDF publishing with a reproducible TAIZHOU open-source case.
Agent skill for inspecting, editing, and visually QAing Figma files. Works with any Agent Skills host. Requires Figma Console MCP.
Production-grade Codex v2 pet workflow with reactions, resumable generation, repair, QA, and cache-safe packaging.
Open-source Codex art-direction skill: inspectable references, five real directions, hard selection gates, and evidence-bound visual QA.
A FastAPI-based backend utilizing Google Cloud Vision API to provide intelligent, real-time visual question-answering via REST endpoints and WebSockets.
Turn issues, PR diffs, and git history into Codex-ready maintainer workflows.
Adaptive photo-to-poster skill: scene analysis, identity-anchor preservation, 30-style routing, restrained typography, prompt composition, and visual QA for editorial, travel, cultural, painterly, print, and modern design posters (single or batch).
Agent skill for LaTeX-based bilingual PDF translation with page-level visual QA.
Research-first Codex skill for visually verified slide images with dual generation.
AI-Driven Visual & Functional QA Agent powered by Gemini Multimodal Structured Outputs & Terminal CLI
Reusable skills for Hermes AI Agent: clinical slide decks, Gemini image generation, screenshot-to-Gemini QA pipeline
Rebuild images, dashboards, infographics, and slide screenshots as editable PowerPoint files with visual QA and typo review.
To associate your repository with the visual-qa topic, visit your repo's landing page and select "manage topics."