learn-visual
/learn-visual
Make a teaching diagram (usually SVG) for one idea, look at it, and fix it until the picture actually shows the claim. Use when the user runs /learn-visual or /skill:learn-visual, or asks for a figure, diagram, SVG, sketch, visualization, or picture of a concept being taught.
- Author
- vasanthsreeram ↗
- Repository
- Alvarmethod ↗
- Licence
- MIT
- Last repository change
- 16.08.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 1
No signals detected. Repository changed on 16.08.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Make a teaching diagram (usually SVG) for one idea, look at it, and fix it until the picture actually shows the claim. Use when the user runs /learn-visual or /skill:learn-visual, or asks for a figure, diagram, SVG, sketch, visualization, or picture of a concept being taught.
Original author description
Make a teaching diagram (usually SVG) for one idea, look at it, and fix it until the picture actually shows the claim. Use when the user runs /learn-visual or /skill:learn-visual, or asks for a figure, diagram, SVG, sketch, visualization, or picture of a concept being taught.
How it works
- Output
- Loop (do not skip)
- Design
- Failures to catch on the look pass
- After
SKILL.md preview
---
name: learn-visual
description: >
Make a teaching diagram (usually SVG) for one idea, look at it, and fix
it until the picture actually shows the claim. Use when the user runs
/learn-visual or /skill:learn-visual, or asks for a figure, diagram,
SVG, sketch, visualization, or picture of a concept being taught.
license: MIT
metadata:
author: vasanthsreeram
version: "1.0"
source: "Eero Alvar — How I Use AI to Learn Things https://youtu.be/kzcI5F4tGiU"
---
# Learn visual
One idea, one picture. The picture exists so the learner can accept the step — not as decoration.
## Output
Write `.alvar/visuals/<slug>-<n>.svg` (create the folder). Embed or link it in the session file.
Prefer SVG. Use another format only if the harness cannot preview SVG.
## Loop (do not skip)
1. State the claim the picture must make, in one sentence.
2. Draw the smallest picture that makes that claim.
3. **Look at the file** (image/read tool). If you cannot view it, say so and keep the SVG simple enough to audit as text.
4. Fix labels, overlap, wrong arrows, missing units, or a picture that does not match the claim.
5. Look again. Stop after a clean pass, not after the first draft.
## Design
- One claim. No collage of the whole course.
- Large labels. High contrast. No tiny legend the learner needs a second lesson to read.
- If the idea is algebraic, show the objects (arrows, planes, machines), not a screenshot of the equation.
- Do not add decorative gradients, watermarks, or "AI art" backgrounds.
## Failures to catch on the look pass
- Arrow direction disagrees with the prose
- Two symbols for the same object
- 3D that hides the relation
- Cropped text
- A picture of a *different* special case than the one just taught
## After
Tell the learner what to look at first ("the two arrows, then the pairing number"). Do not re-teach the whole node unless they ask.
Versions
The database has no other skills named learn-visual.
Database snapshot: 13.11.2026 · package version 6877765de847 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 84illustrate
Visual explainer for a concept or codebase topic, one idea per diagram, grounded in the real artifact and written as a markdown record plus an interactive page (markdown only on request). Presets: newcomer (default) and zero-knowledge (ELI5). Options: an STE register, and a… - 100visual-explainer
Build a clickable, visual explainer that teaches a hard topic from zero — a single self-contained HTML page with chapters, stepped narration and hand-drawn interactive SVG diagrams instead of walls of text. Use when someone asks to learn or teach a subject properly, wants an… - 100svg-figure
This skill should be used when the user asks to "create an SVG figure", "make a schematic", "draw a diagram", "create a schematic diagram", "draw a flowchart", "draw a process flow", "draw a workflow", "draw a workflow diagram", "make an SVG schematic", "create a process… - 100imagegenskill
Generate renderable, scientific-style SVG graphics directly from natural-language requirements (no image models). Use when users ask for an image/picture/scientific diagram/visualization poster or explicitly request SVG output for web-embeddable vector graphics. - 100build-and-learn
Explain code in plain language while building with an AI agent, so a person without a coding background (a designer, PM, founder or anyone else building with AI) gets a CS-level, big-picture understanding of code and architecture without needing to write code. Labels every piece… - 100drawio-diagram
Generate .drawio architecture diagrams with consistent visual style and export to PNG/SVG/PDF/HTML. Use when user asks to "create a diagram", "draw architecture", "make a drawio file", "build a diagram", or mentions "drawio", "architecture diagram", or "system diagram".