A code-driven presentation generation framework. 像构建软件工程一样生成演示文稿。
A Codex plugin and local MCP runtime for context-bounded image generation and inspection.
Claude Code shows images and plays videos right in your terminal: screenshots, Playwright recordings, and synced before/after QA. Ghostty & kitty.
A portable AI agent skill and architecture compiler for polished, editable, evidence-grounded Draw.io diagrams.
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.
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。
👻 Ghostfox — the browser that can SEE: Gecko-native agent browser. 52 MCP tools, unhookable a11y/compositor vision, captcha solvers, visual QA for AI-built UIs.
Native AppKit/UIKit-first Pixiv client for macOS, with SwiftUI glue and visual QA.
Claude Code plugin that audits your project before you deploy. 40+ checks across security, visual QA, code quality, testing, error handling, build config, and performance. One command, structured report, actionable fixes. Auto-detects your stack.
Visual QA CLI for AI-built frontends that renders pages, finds design and accessibility issues, and writes agent-ready fix prompts.
Rebuild reference images as editable Microsoft Visio diagrams using Codex, MCP, COM/ShapeSheet, resumable rendering, and visual QA.
Six-skill spec-driven engineering pod for Claude Code — scaffold specs, research, discover direction, generate design variants, implement, and visually verify, with hard handoffs that prevent silent assumptions
Production-focused frontend-design Agent Skill for GPT-6 Astra & OpenAI Codex — responsive UI, design systems, screenshot-to-code, motion, accessibility & visual QA
Reasoning-based, vectorless RAG over a large document using a hierarchical tree (PageIndex) and a Vision-Language Model (Llama 4 Scout), no embeddings, no vector store, no text chunking.
A visual-first web design Skill: explore, approve, decompose, build, and refine.
Production-grade Codex v2 pet workflow with reactions, resumable generation, repair, QA, and cache-safe packaging.
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.
To associate your repository with the visual-qa topic, visit your repo's landing page and select "manage topics."