Teachable figures skill
A skill that turns a lesson claim into an interactive figure where learners predict, change a cause and explain a new case.
- 314 ★ on the repository
- Last commit
Extended access
Why this level
- The agent creates files and runs browser check scripts on your machine.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/teachable-figuresDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The agent creates files and runs browser check scripts on your machine.
This is third-party code. Review the repository files before installing.
What it does
Teachable figures turns a claim from a lesson into an experiment the learner operates. The agent builds an HTML figure with controls, counters and an explanation prompt. The learner predicts the outcome first, then changes a cause and reads the effect. The repository holds rendering kits, reviewed examples and browser checks for the finished figure. The skill works with a lesson schema of your app or produces a standalone HTML file.
Who it is for. Teachers, parents and self-learners who explain a mechanism and want a figure to try it on.
Good fit when
- You need to show why an idler gear does not change the speed ratio.
- A lesson hinges on a common misconception that a prediction question should expose first.
- A cut-away or rotation explains the object better than a flat picture.
- A lessons app needs a figure that follows its existing lesson schema.
Not a fit when
- You need a chart or report figure with nothing to predict.
- A finished video or animation with no learner input is required.
- The result must be verified but the agent cannot run browser checks.
Example request
Explain to middle-school students why an idler gear does not change the speed ratio. Build standalone HTML with a prediction step, turn counters and a reset button.Limitations
The skill suits mechanisms you can change and observe and fits data without a causal link poorly. It needs an agent that reads `SKILL.md`. Figure quality depends on how precisely the claim and the learner's typical mistake are stated. Code license is reported as NOASSERTION and content sits under a separate `LICENSE-CONTENT`, so read both before reusing the kits. Three-dimensional and anatomy kits are heavier than simple figures and take longer to check in a browser.
How to disable. Delete the `teachable-figures` folder from the agent's skills directory and restart the agent. HTML files already produced stay with you.
FAQ
How do I invoke it in Claude Code and Codex?
In Claude Code type `/teachable-figures` or describe the teaching task. In Codex use `$teachable-figures` instead of the slash.
How does guided mode differ from direct mode?
Guided mode asks at most five questions with recommended answers and builds after you confirm the plan. Saying just build it switches to direct mode with assumptions the agent lists in its note.
Do I need a lessons app?
No. Without an app the skill writes a standalone HTML file with prediction, controls and reset.
How do I update the installed skill?
After a Git install run `git pull` in the skill folder. For an archive download the newer one and replace the folder, keeping your edits first.
Who is the skill best for?
It targets teachers, parents and self-learners. For a self-learner the agent adds two to four diagnostic questions about prerequisites.
Discussion
No questions or reviews yet.
Related
SkillsA tutoring skill for STEM and AI: it finds the knowledge gap first, then teaches one step and checks understanding
The socratic-tutor skill turns an agent into a strict tutor: a diagnostic, a skill map with levels 0-5 and a final assessment
A skill that replaces terminal ASCII with self-contained HTML pages: diagrams, diff reviews, plan reviews, tables and slide decks
Learn 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 set of skills that turn an AI agent into a tutor built on cognitive science, from school to career and social skills
Education Agent Skills
education-agent-skills
165 evidence-based skills for teachers, school leaders and EdTech, installed locally with an optional self-hosted MCP server
README in short
The skill starts from a lesson claim and a misconception, then builds a figure with prediction, controls and an explanation prompt. Guided mode reads the learner workspace and skips what it already knows.