understanding-ladder skill
Skills that choose the simplest explanation format: ASD-STE100 text, a diagram, an interactive page or a video
- 122 ★ on the repository
- Last commit
- MIT
Minimal access
Why this level
- The skills hold only instructions; HTML pages and diagrams are created as files in the working folder.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/understanding-ladderDetects 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 skills hold only instructions; HTML pages and diagrams are created as files in the working folder.
This is third-party code. Review the repository files before installing.
What it does
understanding-ladder helps an agent explain so that people understand faster. The skill classifies the content and picks the lowest rung of the ladder that fully answers the question: a definition or procedure goes as ASD-STE100 text, processes and causality as a Mermaid or SVG diagram, parameter dependence as an HTML page with sliders, and a derivation over time as a storyboard and narration for video. Three rules hold on every rung: nothing is cut, start from a checkable text draft and end with a what-to-check item. The second skill, `plain-chinese`, sets fifteen plain Chinese rules for the first rung. The answer arrives in the language of the request, English or Chinese.
Who it is for. People who get long walls of text from an agent and want what is easier to understand right away: a diagram, an interactive page or short text.
Good fit when
- An agent's status report or reasoning is too dense and the facts must be rewritten more simply with no loss.
- A TLS handshake or other process is explained with a diagram instead of paragraphs.
- A parameter's effect, such as learning rate, is shown with a slider page.
- Chinese text must be simplified by clear rules while keeping numbers and caveats.
Not a fit when
- You need text compression: the skill simplifies language and does not shorten content.
- You need a verified result: easier to understand does not mean verified and checking stays with you.
- You need finished video: the video rung outputs a storyboard and narration and a separate tool renders it.
Example request
Explain how the TLS handshake works choosing the right format and show what I should check in the answer.Limitations
The video rung outputs a storyboard and narration text and rendering is done by the separate showtime tool version 0.4.0 or newer. Plain text rules for English rest on ASD-STE100 norms for about 80 percent of wording, and for Chinese on fifteen own rules. The skill does not check truth: every answer ends with a what-to-check item. The four-format ladder builds on a third-party post that the repository links to. Examples live in the `examples` directory. The latest commit is from October 2026.
How to disable. Run `/plugin uninstall understanding-ladder@understanding-ladder` or delete the `understanding-ladder` and `plain-chinese` folders from the agent's skills directory.
FAQ
What are the four rungs?
First: ASD-STE100 text with one idea per sentence. Second: a diagram. Third: an interactive HTML page. Fourth: an explainer video with animation and narration.
How do I install the skill?
With `npx skills add ChangWenC/understanding-ladder`. For Claude Code there is a plugin: `/plugin marketplace add ChangWenC/understanding-ladder`, then `/plugin install understanding-ladder@understanding-ladder`.
Does it work for Chinese?
Yes, the `plain-chinese` skill sets fifteen rules: words, sentences, paragraphs, what to delete and what to keep. `understanding-ladder` calls it automatically for Chinese output.
Does the skill shorten content?
No, language gets simpler and every number, condition and caveat stays. Each diagram, page or video starts from a checkable text draft.
Is there a demo?
Yes, the project site shows one explanation on every rung, and the repository holds examples in English and Chinese.
Discussion
No questions or reviews yet.
Related
SkillsA skill that makes an agent write docs and replies in plain English on ASD-STE100 rules: short sentences, one term per meaning, condition before command
A skill that rewrites dense, ambiguous English into ASD-STE100 Simplified Technical English so another agent cannot misread it
Skill that rewrites Chinese technical text into controlled language: one action per sentence, active voice, one term per idea.
A skill for Chinese technical writing: rewrites docs, interface strings and API descriptions, keeps the facts intact and checks output with a linter
A skill with a controlled Chinese for technical writing: 40 rules, a banned-word vocabulary and a checker modeled on ASD-STE100.
A skill that rewrites technical text in ASD-STE100 Simplified English: short sentences, active voice, warnings before the step.
README in short
The four rungs, three cross-cutting rules and two skills are described in detail. There is a live demo and before and after pairs for Chinese.