Skip to content
Skills Library
Documents & office · Conversion & formats

visual-explainer

/visual-explainer

Renders conversation content (brainstorms, design discussions, walls of text) as a single self-contained, visually-structured HTML page that is easy to grasp at a glance. Use when the user says "visualize this", "make this visual", "turn this into a page", "make a visual explainer", "render as HTML", "this is a wall of text", "hard to read", "make a visual summary", or wants a friendlier visual representation of a technical discussion, architecture, concept explainer, or set of decisions/tradeoffs.

Licence
AGPL-3.0
Last repository change
26.07.2026

Assessment and security

90/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content25 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
3
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 26.07.2026, without references to retired models or APIs.

Licence

AGPL-3.0, copyleft: przeróbki udostępniane innym muszą mieć tę samą licencję.

What it does and when to use it

Renders conversation content (brainstorms, design discussions, walls of text) as a single self-contained, visually-structured HTML page that is easy to grasp at a glance. Use when the user says "visualize this", "make this visual", "turn this into a page", "make a visual explainer", "render as HTML", "this is a wall of text", "hard to read", "make a visual summary", or wants a friendlier visual representation of a technical discussion, architecture, concept explainer, or set of decisions/tradeoffs.

Triggers from the description

visualize thismake this visualturn this into a pagemake a visual explainerrender as HTMLthis is a wall of texthard to readmake a visual summary

Arguments

/visual-explainer [optional topic or focus]
Original author description

Renders conversation content (brainstorms, design discussions, walls of text) as a single self-contained, visually-structured HTML page that is easy to grasp at a glance. Use when the user says "visualize this", "make this visual", "turn this into a page", "make a visual explainer", "render as HTML", "this is a wall of text", "hard to read", "make a visual summary", or wants a friendlier visual representation of a technical discussion, architecture, concept explainer, or set of decisions/tradeoffs.

How it works

  1. Output contract (non-negotiable)
  2. Workflow
  3. Picking the right visual format
  4. Design principles
Original SKILL.md headings · 45 lines, 504 words
SKILL.md preview
---
name: visual-explainer
description: Renders conversation content (brainstorms, design discussions, walls of text) as a single self-contained, visually-structured HTML page that is easy to grasp at a glance. Use when the user says "visualize this", "make this visual", "turn this into a page", "make a visual explainer", "render as HTML", "this is a wall of text", "hard to read", "make a visual summary", or wants a friendlier visual representation of a technical discussion, architecture, concept explainer, or set of decisions/tradeoffs.
allowed-tools:
  - Read
  - Write
argument-hint: [optional topic or focus]
---

# Visual Explainer

Turn dense conversation content into ONE self-contained light-themed HTML page optimized for fast visual comprehension. The audience is a senior DevOps/SRE engineer — technical/architecture rendering matters most.

## Output contract (non-negotiable)

- **One file.** A single `.html` with ALL CSS and JS inlined. Zero external dependencies — no CDN links, no web fonts pulled over the network, no JS libraries. Must open by double-clicking.
- **Location.** Write to `/tmp/` with a descriptive kebab-case filename, e.g. `/tmp/k8s-ingress-tradeoffs.html`.
- **Diagrams** are built with inline SVG or styled HTML/CSS — never an external diagramming lib.
- After writing, report the absolute file path. Do NOT auto-open or start a server.

## Workflow

1. **Source the content.** By default, use the relevant content from the current conversation (the brainstorm/wall-of-text just produced). If the user points at a file, Read it. Use `$ARGUMENTS` as a topic/focus hint if provided.
2. **Decompose into chunks.** Break the content into logical sections. For each chunk, pick the best visual format (see mapping below).
3. **Build from the design system.** Start from `assets/template.html` — it has the full inline CSS design system and JS for tabs/accordions. Copy component patterns from it and from `references/content-shapes.md`. Do not invent a new style; reuse the system so output is consistent.
4. **Adapt density.** Use collapsible `<details>` accordions or tabs where they cut clutter (long detail, alternatives, deep-dives). Keep content static and visible where scanning is better (summaries, key tables, the main diagram).
5. **Lead with a summary.** Top of page = a short orienting summary + key-insight callout(s). Then drill into detail. Highlight key terms inline.
6. **Write + report.** Write the file to `/tmp/`, then give the user the path.

## Picking the right visual format

Match each content chunk to a format. Full snippets in `references/content-shapes.md`.

| Content shape | Use |
|---|---|
| System/architecture, data flow, request path | Inline-SVG or CSS box-and-arrow **diagram** |
| Sequential process, runbook, pipeline stages | **Stepper** / numbered flow |
| Options, tradeoffs, "X vs Y", decision | **Comparison table** or pros/cons grid + recommendation callout |
| Distinct concepts / components at same level | **Card grid** |
| Caveats, gotchas, key takeaways, warnings | **Callout boxes** (note / tip / warning / key-insight) |
| Hierarchy, taxonomy, mind-map | Nested CSS tree or radial **mind-map** |
| Long detail behind a summary | `<details>` **accordion** or **tabs** |
| Definitions / mental models | Card with highlighted **key term** + short body |

## Design principles

- **Light, clean, minimal.** White/near-white background, generous whitespace, restrained accent palette, strong typography hierarchy. Docs-site feel, not a dashboard.
- **Scannable.** A reader should grasp the structure in ~5 seconds: clear headings, a sticky/visible section nav or TOC for longer pages, consistent component styling.
- **Color carries meaning.** Reserve accent colors for callout semantics (info/tip/warn/insight) and diagram emphasis — don't decorate randomly.
- **Self-contained fonts.** Use a system font stack; never fetch web fonts.

See `references/content-shapes.md` for the component library and `assets/template.html` for the base.
Files in this package (3)
  • SKILL.md 4 KB
  • assets/template.html 13 KB
  • references/content-shapes.md 7 KB

Versions

RepositoryScoreLicence
This page · antoniocascais/claude-code-toolkit90AGPL-3.0
atretyak1985/swarmery100Apache-2.0
salexandr0s/ai-config100MIT
hongguifeng/visual-explainer100MIT
Prahaladha-Reddy/skills100MIT
nicobailon/visual-explainer100MIT
vercel-labs/vgpu100MIT
jscraik/Agent-Skills100Apache-2.0
luanmorenommaciel/agentspec100MIT

Database snapshot: 13.11.2026 · package version 5f9f69b71a56 (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

  • 100explainer-infographic
    Generate an animated, interactive HTML page that explains a complex concept through real-world analogies, visual diagrams, and progressive disclosure. Use this whenever the user says 'explainer infographic,' 'explain how X works,' 'make an explainer for,' 'visualize this…
  • 100visual-doc
    Generate a self-contained, on-brand interactive HTML document from researched or analyzed content (a research brief, repo/code analysis, concept explainer, comparison, design writeup) by composing a bespoke structure from a fixed design-system component palette. TRIGGER when:…
  • 100report-card
    Render a finished BS report as a self-contained HTML page — score hero, filterable claims, readable on a phone, prints to a clean PDF. Use when the user wants to open, share, print, or show a report to someone who is not going to read a markdown table, or asks for "the HTML…
  • 100hk-writeup
    Put what the user asked for, and nothing else, onto one self-contained HTML page in the house voice. Triggers on: 'write this up', 'turn this into a page', 'make an HTML of this', 'turn this into a report', 'I want to show someone this', or /hk-writeup.
  • 100interactive-system-docs
    Build a self-contained interactive HTML visualization that explains how a complex system works — architecture, data flows, state machines, processing pipelines, and search patterns — with D3.js graphs where every node is clickable, all rendered from a single file with no build…
  • 100ak-render
    Show a plan, report, recap, diff review, dashboard, explainer, or comparison as one polished offline HTML page. Write a short YAML Page Spec and compile it with the ak-render CLI (npm package @bestagentkits/render) instead of hand-writing HTML, CSS, or JavaScript. Use when the…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.