answer-me-with-html vs. ScreenCI

An agent skill for Claude Code, Codex, Cursor and more. The model writes a short Markdown draft; a bundled CLI turns it into one offline HTML page with diagrams. About 1/8 of the tokens. Answer me with HTML — an agent skill that answers hard questions with a one-page HTML you can actually read. 让 AI Agent 用一页 HTML 回答复杂问题。

Tutorial videos of your app, made by your coding agent. Describe the feature in one sentence and paste one prompt into Claude Code, Codex, or Cursor. It records a narrated walkthrough of your real app on your own machine, and the finished video opens in your browser, ready for your help center or docs, where anyone edits the narration, voices, and 79 languages. Engineers can keep the videos in the repository as Playwright tests that CI re-records on every release. Hi HN, I'm Olli. My friend Patrik and I are bootstrapping ScreenCI: tutorial videos of your web app that you can re-record in your CI on every release. If the video is out of date, the run fails like any E2E test.I've been on teams where the tutorial videos were outdated, or even where we held back UI improvements due to manually maintained videos. That's why we built system where you can describe the videos as Playwright E2E test code. Coding agents are very good with writing tests and you can run these scripts against your app on your machine. ScreenCI converts them into narra...