whatis
Skill428 starsChanged 7 months agoMITView on GitHub
What Is This — explain anything as a picture-first HTML page. Use when the user types /whatis <topic>, or asks what something is / how it works and would be better served by big diagrams than by paragraphs.
In this repository3 other files it gives its agents.
- break-ai-slopSkill
- claude-cleanupSkill
- get-bijiSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 10
No Artifact tool in this environment: write a self-contained HTML file (inline SVG/CSS, no external deps) to a temp directory (e.g.
- Distinctive: line 12
If the current context is not enough to explain the topic, gather enough context yourself before drawing.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
whatis
Explain like I'm someone who knows nothing about this topic, using an HTML page with big pictures and few words.
No Artifact tool in this environment: write a self-contained HTML file (inline SVG/CSS, no external deps) to a temp directory (e.g. $TMPDIR or /tmp), then open it.
If the current context is not enough to explain the topic, gather enough context yourself before drawing. Every node in a diagram must be backed by evidence; never fabricate.
Draw real diagrams in SVG, freely picking and combining whatever fits: flowchart, sequence diagram, state diagram, architecture/block diagram, C4, dependency graph, call graph, ER diagram, class diagram, DFD, swimlane, deployment diagram, timeline, Gantt, git graph, before/after comparison, bar/line chart, treemap, heatmap... If none fits, design your own — expression comes before templates. Tables are for enumerations only and don't count as diagrams.
A diagram exists to make structure visible: who talks to whom, what causes what, what changes when. Draw each one in the shape the reader's eye already knows — boxes for parts, arrows for actions, lanes for actors, time flowing one way. Make each diagram read at two distances: at a glance only the backbone shows — a name per box, a verb per arrow, one path the eye can follow; the detail lives in a quieter layer of smaller, dimmer annotations that never competes with the backbone. Color like a print magazine: warm paper background, ink for text and lines, one muted accent doing all the pointing; status reads from marks and line weight, tinted from the same palette. One diagram, one point: when the content outgrows the shape, split it or summarize the tail — shrinking the type is never the answer. The test: someone who reads only the diagrams and captions still gets the whole story.
Give the page a wide content column with visible margins on both sides: diagrams span the column (each SVG gets a viewBox and width:100% so it scales with the window), prose sits in a narrower measure within it.
Match the user's language in the explanation. Keep technical terms, API names, CLI commands, and exact error strings verbatim in English.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

