Skip to content
Agentmart
Submit a tool

vs-eli5

Explain a topic like I'm a 5 year old.

Skill by vltansky

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/vltansky-vs-eli5

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Explain a topic like I'm a 5 year old. Use when the user types /vs-eli5, /eli5, or asks for a dead-simple picture explainer of how something works.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Node.js package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/vs-eli5

What's inside

Skill name
vs-eli5
Description
Explain a topic like I'm a 5 year old. Use when the user types /vs-eli5, /eli5, or asks for a dead-simple picture explainer of how something works.
License
MIT
Instructions
61 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (7)

  • SKILL.md
  • openai.yaml · agents/
  • eli5.eval.ts · test/
  • eli5.static.eval.ts · test/
  • mention-only-write-slop-skill.md · test/fixtures/
  • tldr-clean.md · test/fixtures/
  • tldr-slop.md · test/fixtures/

SKILL.md (first lines)

# eli5

Explain like I'm someone who knows nothing about this topic, using an HTML artifact with big pictures and few words. Use `/vs-show-me` for that artifact, not raw HTML. Start from `../vs-show-me/assets/artifact.html`
`/vs-show-me` owns capture: inherit its URL + first-screen shot handoff. Pointer only.
When the topic is logic, branching, or a mechanism, `/vs-show-me` stacks diagram + short fenced pseudocode — inherit that; do not pick one.
`/vs-show-me` owns MCP Apps progressive enhancement (`ui://vs/eli5` when the host supports Apps; otherwise HTMDX file + URL + shot + TLDR). Inherit only. Pointer: [../vs-internal-shared/references/mcp-apps-host.md](../vs-internal-shared/references/mcp-apps-host.md).
For an eli5 artifact, call `mcp__vs_artifact__vs_eli5` after saving it when that tool is available; use the inherited file handoff if it is unavailable or fails.

Teach one tightly scoped mental model that gives the user a tangible win. Ground
it in why the topic matters from the ask and available context; do not block on
a question when that context is enough. Start with a familiar analogy, then map
each part of the analogy to the real thing and show only the causal steps needed
to use the model. Beginner-friendly means no assumed vocabulary, not childish
language.

End the page with one quick prediction or recall prompt. When changing an
input makes the mental model clearer, use `/vs-show-me`'s `<Prediction>`:
change the setup, predict, reveal the outcome and its one-sentence reason.
Inherit its interactive explanation contract and standalone fallback; do not
invent a separate quiz framework. Keep the core explanation visible before
interaction and provide immediate feedback. For a static fact, keep the plain
prompt and nearby answer. This is one explanation, not a stateful course: do not
create `MISSION.md`, learning records, lesson directories, or other
teaching-workspace files.

`/vs-show-me` owns the page write-slop pass. Inherit only. Pointer:
[../vs-show-me/SKILL.md](../vs-show-me/SKILL.md). Run
`skills/vs-show-me/scripts/run-write-slop.mjs` on the page. Do not paste
that write procedure here.

Also run `skills/vs-write/scripts/reject-slop.mjs` on the 2-4 line chat
TLDR. Exit 1: rewrite the tells. Do not claim `READY_FOR_REVIEW` if
the runner did not run or exited 1.

Write the page copy and the TLDR in STE mode: a beginner reads every sentence
once. `/vs-write` owns the rules. Pointer only:
[../vs-internal-shared/references/ste-writing.md](../vs-internal-shared/references/ste-writing.md). Run
`skills/vs-write/scripts/check-ste.mjs` on the saved page. Exit 1: split or
rewrite the reported sentences. Technical names stay as they are.

Always produce a chat TLDR of that page: two to four short lines with the
answer and the next action. Do not call `/vs-tldr`.

Direct: write that TLDR to chat with the opened page. Composed: return those
2-4 lines to the caller as the single close item-1 TLDR and write nothing else
to chat.

Topic: $ARGUMENTS

Apply the [shared output style](../vs-internal-shared/references/output-style.md)
to every user-facing message.

## Workflow

Direct: emit **Next** only. Composed: return to caller.

**Prev:** user ask or tldr offer
**Next:** done
**Relevant:** `/vs-show-me` | `/vs-shape-it`

From vltansky/vs, MIT.

More from vltansky/vs

Signals

Stars
0
Forks
1
Open issues
1
Last commit (this folder)
Oct 3, 2026 (25 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from vltansky

Cite this page

vs-eli5 skill. Agent Mart. https://agentmart.dev/skills/vltansky-vs-eli5 (last updated 2026-10-24)