`lecture-visualization`¶

Builds small interactive web pages that let students explore the algorithms discussed in a lecture.

Recipe: Write, review and teach
Output check: Expert-checkable The lecturer checks the model behind each plot against the reference values.
Status: brief

Make your own version¶

This skill depends on local details, so the site publishes a brief instead of one institute's skill. Copy the brief and give it to your agent. If your agent has a skill-creation skill, such as Anthropic's skill-creator, it will use it. The agent asks you the questions under "Local details", builds the skill, and runs it once on the test case.

An agent that can read web pages can also fetch the brief itself from https://aiforscientists.eu/skills/lecture-visualization/brief.md.

# Skill brief: lecture-visualization

Source: https://aiforscientists.eu/skills/lecture-visualization/
Recipe: Write, review and teach (https://aiforscientists.eu/recipes/09-write-review-teach/)

Build a skill for my own setting from this brief.
If you have a skill-creation skill or tool, use it.
Before you write anything, ask me each question under "Local details", one at a time.
Do not guess an answer; if I do not know one, leave a marked TODO in the skill.
Keep every rule under "Never" in the skill you write.
Write the check under "How to check the output" into the skill, so that it runs every time.
Then run the skill once on the test case and show me the result.

## Purpose

Builds small interactive web pages that let students explore the algorithms discussed in a lecture.

## Inputs

- The algorithm or model, with its equations or reference code.
- What students should be able to change and observe.

## Output

- A single web page that runs in a browser without a server.
- A short note on the model behind each plot.

## Steps

1. Implement the algorithm from the reference.
2. Test it against known values.
3. Build the page with controls for the parameters students should change.
4. Write the note on the model behind each plot.

## Local details

1. Where will the pages be hosted (course platform, static site)?
2. Which libraries are allowed?
3. Which accessibility rules apply?

## Never

- Never load scripts from sources the course platform does not allow.
- Never collect data from students.

## How to check the output

The lecturer checks the model behind each plot against the reference values.

## Test case

Gradient descent on a two-dimensional function, with step size as a control.

Local details¶

Your version needs answers to these questions:

Where will the pages be hosted (course platform, static site)?
Which libraries are allowed?
Which accessibility rules apply?

Never¶

Never load scripts from sources the course platform does not allow.
Never collect data from students.

Local versions¶

No local version is published yet. If you built one, share it as an example for others.

Discussion

Used this recipe or skill, or seen it fail? Say so here. Comments need a GitHub account; without one, write to aiforscience@googlegroups.com.

lecture-visualization¶