ReadingText2html skill
The reading-courseware skill turns an English textbook passage into a three-stage HTML lesson and a printable student worksheet.
- 108 ★ on the repository
- Last commit
Minimal access
Why this level
- The skill runs local Node.js scripts and writes files to the chosen folder.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/readingtext2htmlDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewMinimal accessThe tool runs nothing and makes no network calls.
- The skill runs local Node.js scripts and writes files to the chosen folder.
This is third-party code. Review the repository files before installing.
What it does
The `reading-courseware` skill accepts an English passage, a textbook page screenshot or OCR output. The agent sorts the content into two JSON files, `content.json` and `worksheet.json`, and `scripts/build.js` builds interactive HTML from them. The lesson has pre-reading, while-reading and post-reading stages. The worksheet reuses language items from the middle stage: matching, fill-in, imitation and summary. Edits go into JSON rather than HTML, so the layout stays uniform. `scripts/validate.js` checks the result.
Who it is for. English teachers preparing reading lessons from a textbook who want an interactive screen and a worksheet from one source.
Good fit when
- A reading lesson is built from a textbook page screenshot.
- An on-screen lesson needs a worksheet with the same words and structures.
- A three-stage lesson structure is applied as one template across texts.
- Finished HTML must be validated automatically before class.
Not a fit when
- The class is not English reading.
- The page must be hand-built from scratch.
- Node.js 18 or newer is not installed.
Example request
Turn this screenshot into a reading lesson with pre, while and post stages plus a worksheet, output to ./output/lesson-01.Limitations
Requires Node.js 18 or newer. The skill covers English reading lessons only and does not create arbitrary HTML pages or CSS. The agent must not invent missing paragraphs; with a poor screenshot the text is requested again. The repository has no license. Documentation is in Chinese. Lesson quality depends on screenshot sharpness and OCR. Read the generated tasks before class, as with any model-made material.
How to disable. Delete the skill folder from the agent's skills directory. Generated lessons and worksheets remain plain HTML files in the chosen output folder.
FAQ
What files come out?
An interactive HTML lesson and an HTML worksheet, both built from two JSON files with one command.
Where does the skill live in Cursor?
In `.cursor/skills/reading-courseware/` inside the project. Invoke it with `@reading-courseware` or by describing the task.
What does `validate.js` check?
The structure and consistency of lesson and worksheet JSON, including the matching `meta.filenameStem`.
Where do worksheet tasks come from?
From the language items of the reading stage: words, phrases and structures. The skill adds no tasks outside the lesson material.
Are packages required?
No, Node.js 18 or newer is enough: build and validation run with scripts from `scripts/`.
Discussion
No questions or reviews yet.
Related
SkillsLearn from materials
learn-from-materials
A skill that turns books, PDFs, slides and documents into a traceable knowledge base and an interactive learning page with sources, maps and self-check
A skill that turns a manuscript into a designed HTML book and a print-ready Letter PDF, checking every rendered page.
Skill that translates English and French course handouts into Chinese and builds HTML, DOCX or Markdown with terminology.
A skill that rewrites dense, ambiguous English into ASD-STE100 Simplified Technical English so another agent cannot misread it
A skill set for building interactive MkDocs textbooks: concept graph, chapters, simulations, quizzes and glossary.
A skill and methodology that turn scanned learning materials into interactive practice apps: transcription, grading and cost.
README in short
Three steps: prepare material, generate JSON and build HTML, then validate. Placement paths are given for several agents.