Self-Contained HTML Pages
SourceWeft/SourceWeft
Builds and revises polished offline HTML reports, landing pages, infographics and interactive visualizations as a single file, with viewport QA before delivery.
Generate beautiful, self-contained HTML pages that visually explain systems, code changes, plans, and data.
$ npx skills add NeverSight/learn-skills.dev --skill visual-explainer -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install NeverSight/learn-skills.dev visual-explainer --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/NeverSight/learn-skills.dev.git skills-src && mkdir -p .claude/skills && cp -r skills-src/data/skills-md/abpai/skills/visual-explainer .claude/skills/visual-explainer && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "visual-explainer" agent skill from https://github.com/NeverSight/learn-skills.dev/tree/main/data/skills-md/abpai/skills/visual-explainer into .claude/skills/visual-explainer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "visual-explainer", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/NeverSight/learn-skills.dev/tree/main/data/skills-md/abpai/skills/visual-explainerType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add NeverSight/learn-skills.dev --skill visual-explainer -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install NeverSight/learn-skills.dev visual-explainer --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NeverSight/learn-skills.dev.git skills-src && mkdir -p .agents/skills && cp -r skills-src/data/skills-md/abpai/skills/visual-explainer .agents/skills/visual-explainer && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "visual-explainer" agent skill from https://github.com/NeverSight/learn-skills.dev/tree/main/data/skills-md/abpai/skills/visual-explainer into .agents/skills/visual-explainer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "visual-explainer", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add NeverSight/learn-skills.dev --skill visual-explainer -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install NeverSight/learn-skills.dev visual-explainer --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NeverSight/learn-skills.dev.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/data/skills-md/abpai/skills/visual-explainer .cursor/skills/visual-explainer && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "visual-explainer" agent skill from https://github.com/NeverSight/learn-skills.dev/tree/main/data/skills-md/abpai/skills/visual-explainer into .cursor/skills/visual-explainer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "visual-explainer", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/NeverSight/learn-skills.dev.git --path data/skills-md/abpai/skills/visual-explainer--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add NeverSight/learn-skills.dev --skill visual-explainer -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install NeverSight/learn-skills.dev visual-explainer --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NeverSight/learn-skills.dev.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/data/skills-md/abpai/skills/visual-explainer .gemini/skills/visual-explainer && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "visual-explainer" agent skill from https://github.com/NeverSight/learn-skills.dev/tree/main/data/skills-md/abpai/skills/visual-explainer into .gemini/skills/visual-explainer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "visual-explainer", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install NeverSight/learn-skills.dev visual-explainerInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add NeverSight/learn-skills.dev --skill visual-explainer -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/NeverSight/learn-skills.dev.git skills-src && mkdir -p .github/skills && cp -r skills-src/data/skills-md/abpai/skills/visual-explainer .github/skills/visual-explainer && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "visual-explainer" agent skill from https://github.com/NeverSight/learn-skills.dev/tree/main/data/skills-md/abpai/skills/visual-explainer into .github/skills/visual-explainer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "visual-explainer", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add NeverSight/learn-skills.dev --skill visual-explainer -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install NeverSight/learn-skills.dev visual-explainer --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NeverSight/learn-skills.dev.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/data/skills-md/abpai/skills/visual-explainer .opencode/skills/visual-explainer && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "visual-explainer" agent skill from https://github.com/NeverSight/learn-skills.dev/tree/main/data/skills-md/abpai/skills/visual-explainer into .opencode/skills/visual-explainer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "visual-explainer", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
visual-explainerGenerate beautiful, self-contained HTML pages that visually explain systems, code changes, plans, and data.
Visual Explainer is an agent skill from NeverSight/learn-skills.dev. Generate beautiful, self-contained HTML pages that visually explain systems, code changes, plans, and data. Use when the user asks for a diagram, architecture overview, diff review, plan review, project recap, comparison table, or any visual explanation of technical concepts. Also use proactively when you are about to render a complex ASCII table (4+ rows or 3+ columns) — present it as a styled HTML page instead.
Its SKILL.md is about 5.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 12 other files (for example `stats.json`). Compatibility notes: Requires a browser to view generated HTML files. Optional surf-cli for AI image generation.
It sits in Frontend & Design, covering HTML artifacts and Infographics. The repository describes itself as: Curated high-quality AI Agent Skills. Search, install, copy and share. Works with Claude Code, Cursor, OpenClaw, and other AI coding tools. The licence is MIT.
4 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 08f9d22. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are css and html).
From the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
fonts.googleapis.comAlso links to:
github.comFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Requires a browser to view generated HTML files. Optional surf-cli for AI image generation.
From compatibility in the SKILL.md frontmatter.
Visual Explainer loads about 5.5k tokens when it runs. Until then it costs about 108 tokens; SKILL.md has 2,761 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from NeverSight/learn-skills.dev at commit 08f9d22, republished under its MIT licence (© NeverSight). 2,761 words, ~5,509 tokens.
.claude/skills/visual-explainer/SKILL.md (or your agent's skills folder). This skill also uses 12 other files; get the full folder from GitHub.Generate self-contained HTML files for technical diagrams, visualizations, and data tables. Always open the result in the browser. Never fall back to ASCII art when this skill is loaded.
Visuals are required. When this skill is loaded, the output must contain at least one primary visual artifact that carries real information, not just decorative styling around prose. Valid primary visuals include:
If the page is a report, review, recap, audit, or plan analysis, include at least two visual forms:
Pure prose sections, even if well-designed, do not satisfy this requirement.
Proactive table rendering. When you're about to present tabular data as an ASCII box-drawing table in the terminal (comparisons, audits, feature matrices, status reports, any structured rows/columns), generate an HTML page instead. The threshold: if the table has 4+ rows or 3+ columns, it belongs in the browser. Don't wait for the user to ask — render it as HTML automatically and tell them the file path. You can still include a brief text summary in the chat, but the table itself should be the HTML page.
Before writing HTML, commit to a direction. Don't default to "dark theme with blue accents" every time.
Who is looking? A developer understanding a system? A PM seeing the big picture? A team reviewing a proposal? This shapes information density and visual complexity.
What type of diagram? Architecture, flowchart, execution flow, code flow, sequence, data flow, schema/ER, state machine, mind map, data table, walkthrough, timeline, or dashboard. Each has distinct layout needs and rendering approaches (see Diagram Types below).
What aesthetic? Pick one and commit:
handDrawn mode, wiggly lines, informal whiteboard feel)Vary the choice each time. If the last diagram was dark and technical, make the next one light and editorial. The swap test: if you replaced your styling with a generic dark theme and nobody would notice the difference, you haven't designed anything.
Read the reference template before generating. Don't memorize it — read it each time to absorb the patterns.
./templates/mermaid-flowchart.html./templates/data-table.html./templates/walkthrough.html./templates/dashboard.html./templates/timeline.html./templates/architecture.html./references/aesthetic-palettes.md for ready-made palettes.For CSS/layout patterns and SVG connectors, read ./references/css-patterns.md.
For pages with 4+ sections (reviews, recaps, dashboards), also read the "Section Navigation" section in ./references/css-patterns.md for sticky sidebar TOC on desktop and horizontal scrollable bar on mobile.
Choosing a rendering approach:
| Diagram type | Approach | Why |
|---|---|---|
| Execution flow / code flow | Excalidraw pipeline (required) | These are flowcharts in practice; Excalidraw output is clearer and less cluttered |
Flowcharts (flowchart/graph) | Excalidraw pipeline | Cleaner hand-drawn output: Mermaid text -> @excalidraw/mermaid-to-excalidraw -> Excalidraw SVG export |
| Other Mermaid diagrams (sequence, ER, state, mind map, data flow) | Mermaid | Broader syntax support where Excalidraw conversion is limited |
| Architecture (text-heavy) | CSS Grid cards + flow arrows | Rich card content (descriptions, code, tool lists) needs CSS control. See templates/architecture.html |
| Architecture (hybrid, 15+ elements) | Mermaid overview + CSS Grid detail cards | Simplified 5-8 node Mermaid for the big picture, then detail cards below. See hybrid pattern in templates/architecture.html |
| Data table | HTML <table> | Semantic markup, accessibility, copy-paste behavior |
| Walkthrough / tutorial | Vanilla JS step-through | Progressive disclosure with visual + text per step |
| Timeline | CSS (central line + cards) | Simple linear layout doesn't need a layout engine |
| Dashboard | CSS Grid + inline SVG | Card grid with sparklines and progress bars |
Report composition rule. For reports, reviews, recaps, audits, and plan explainers, do not build a page that is mostly stacked text cards. Start by choosing the visual anchor first, then add supporting sections around it. The default shape is:
Visual anchor rule. Put the main diagram, timeline, walkthrough, or dashboard in the first screenful when possible. If the most important thing on load is a paragraph, the page is under-visualized.
Visual fallback ladder. If the ideal diagram type is blocked by missing data or rendering limits, downgrade to the next best visual form instead of dropping to prose:
Never skip the visual entirely.
For code-heavy pages (reviews, architecture docs), add Prism.js for syntax highlighting (see libraries.md).
Mermaid theming (fallback path): Use theme: 'base' with custom themeVariables so colors match your page palette. Use look: 'classic' unless the user asks for sketch style. Use layout: 'elk' for complex graphs (requires @mermaid-js/layout-elk — see ./references/libraries.md). Override Mermaid SVG classes with CSS for pixel-perfect control.
Mermaid zoom controls: Always add zoom controls (+/−/reset buttons) to every .mermaid-wrap container. Complex diagrams render at small sizes and need zoom to be readable. Include Ctrl/Cmd+scroll zoom on the container. Prefer CSS zoom over transform: scale() for static base scaling — see CSS Zoom section in css-patterns.md. See the zoom controls pattern in ./references/css-patterns.md and the reference template at ./templates/mermaid-flowchart.html.
AI-generated illustrations (optional). If surf-cli is available, generate images via surf gemini "prompt" --generate-image /tmp/ve-img.png --aspect-ratio 16:9, base64 encode, and embed as data URIs. Check with which surf; skip gracefully if unavailable. See ./references/css-patterns.md for image container styles.
Apply these principles to every diagram:
Typography is the diagram. Pick a font pairing from the 5 named pairings in libraries.md and commit to it for the page:
Editorial default (Threaded/Medium-style): When the request asks for Medium/editorial aesthetics, default to Merriweather (content/heading) + Inter (UI/meta), slate-heavy palette, generous line-height, and restrained borders.
Forbidden as generic primary body font: Roboto, Arial, Helvetica. These are invisible defaults — they say "no design decision was made." Use only as system fallbacks in the font-family stack.
Load via <link> in <head>. Include a system font fallback in the font-family stack for offline resilience. The heading font should always have character — if you swapped it for Arial and nobody noticed, you haven't designed anything.
Color tells a story. Use CSS custom properties for the full palette. Define at minimum: --bg, --surface, --border, --text, --text-dim, and 3-5 accent colors. Each accent should have a full and a dim variant (for backgrounds). Name variables semantically when possible (--pipeline-step not --blue-3). Support both themes. Put your primary aesthetic in :root and the alternate in the media query:
/* Light-first (editorial, paper/ink, blueprint): */
:root { /* light values */ }
@media (prefers-color-scheme: dark) { :root { /* dark values */ } }
/* Dark-first (neon, IDE-inspired, terminal): */
:root { /* dark values */ }
@media (prefers-color-scheme: light) { :root { /* light values */ } }Surfaces whisper, they don't shout. Build depth through subtle lightness shifts (2-4% between levels), not dramatic color changes. Borders should be low-opacity rgba (rgba(255,255,255,0.08) in dark mode, rgba(0,0,0,0.08) in light) — visible when you look, invisible when you don't.
Backgrounds create atmosphere. The editorial default is flat white (#ffffff) — whitespace IS the atmosphere. For dark-first aesthetics, use subtle gradients or faint grid patterns. The background should feel intentional, not accidental.
Visual weight signals importance. Not every section deserves equal visual treatment. Executive summaries and key metrics should dominate the viewport on load (larger type, more padding, subtle accent-tinted background zone). Reference sections (file maps, dependency lists, decision logs) should be compact and stay out of the way. Use <details>/<summary> for sections that are useful but not primary — the collapsible pattern is in ./references/css-patterns.md.
Surface depth creates hierarchy. Vary card depth to signal what matters. Hero sections get elevated shadows and accent-tinted backgrounds (ve-card--hero pattern). Body content stays flat (default .ve-card). Code blocks and secondary content feel recessed (ve-card--recessed). See the depth tiers in ./references/css-patterns.md. Don't make everything elevated — when everything pops, nothing does.
Links are explicit. Never rely on browser default link colors. Style all <a> elements with color: var(--accent) and keep underlines. See the Link Styling section in css-patterns.md.
Animation earns its place. Use staggered fadeUp for cards, fadeScale for KPIs and badges, countUp for hero numbers. Always respect prefers-reduced-motion. CSS transitions and keyframes handle all cases.
Forbidden visual defaults — these make every AI-generated page look the same:
#8b5cf6, #7c3aed, #6366f1 (indigo/violet — the Tailwind "AI purple"); #06b6d4, #22d3ee (cyan — overused in dark-mode AI dashboards); #ec4899, #f472b6 (magenta/pink — the gradient mesh cliche)... buttons at the top of fake code windows); gradient text for headingsProse quality — prose in generated pages must not read like AI wrote it:
Default to one file. The ideal output is one self-contained HTML file that includes the visuals, narrative, styling, and any lightweight interactivity in a single deliverable.
Output location: Write to ~/.agent/diagrams/. Use a descriptive filename based on content: modem-architecture.html, pipeline-flow.html, schema-overview.html. The directory persists across sessions.
If multiple files are truly needed, make one main file. The main HTML file must:
Do not generate a loose set of sibling files with no clear starting page.
Open in browser:
open ~/.agent/diagrams/filename.htmlxdg-open ~/.agent/diagrams/filename.htmlTell the user the file path so they can re-open or share it.
In the chat response, name the visuals you included. Example: "Created a report with an execution flow diagram and a risk table at ~/.agent/diagrams/foo.html." This makes the visual output explicit and nudges future runs away from prose-only reports.
If companion files were generated, name the main file first and mention that it links to the supporting files.
Use Excalidraw for flowcharts first. For flowchart/graph syntax, convert Mermaid text to Excalidraw and render exported SVG. This is the default because it produces cleaner, less AI-looking diagrams.
Execution/code flows are flowcharts. Command pipelines, runtime execution paths, pre-commit chains, CI/CD step maps, and function call flow summaries should use this Excalidraw flowchart path.
Use Mermaid for non-flowchart types. Sequence, ER, state, mind map, and data-flow diagrams should use Mermaid directly (or fallback to Mermaid if Excalidraw conversion fails).
stateDiagram-v2 label caveat: Transition labels have a strict parser — colons, parentheses, <br/>, HTML entities, and most special characters cause silent parse failures. If your labels need special characters, use flowchart LR instead with rounded nodes and quoted edge labels (|"label text"|).
Topology-focused (connections matter more than card content): Use Mermaid. Text-heavy overviews (card content matters more than connections): CSS Grid with explicit row/column placement. Sections as rounded cards with colored borders. Vertical flow arrows between sections. Use when cards need descriptions, code references, tool lists, or other rich content that Mermaid nodes can't hold.
Use a real <table> element — not CSS Grid pretending to be a table. Tables get accessibility, copy-paste behavior, and column alignment for free. The reference template at ./templates/data-table.html demonstrates all patterns.
Use proactively. Any time you'd render an ASCII box-drawing table in the terminal, generate an HTML table instead. This includes: requirement audits, feature comparisons, status reports, configuration matrices, test result summaries, dependency lists, permission tables, API endpoint inventories.
Interactive step-through for progressive disclosure of concepts, processes, or tutorials. Each step has a visual element and explanatory text. Navigation via prev/next buttons, clickable dots, and keyboard arrows. The reference template at ./templates/walkthrough.html demonstrates the pattern — vanilla JS, no framework dependencies.
Vertical or horizontal timeline with a central line (CSS pseudo-element). Phase markers as circles on the line. Content cards branching left/right. Date labels on the line. Color progression from past (muted) to future (vivid).
Card grid layout. Hero numbers large and prominent. Sparklines via inline SVG <polyline>. Progress bars via CSS linear-gradient. KPI cards with trend indicators.
Every diagram is a single self-contained .html file. No external assets except CDN links (fonts, optional libraries). Structure:
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Descriptive Title</title>
<link href="https://fonts.googleapis.com/css2?family=...&display=swap" rel="stylesheet">
<style>
/* CSS custom properties, theme, layout, components — all inline */
</style>
</head>
<body>
<!-- Semantic HTML: sections, headings, lists, tables, inline SVG -->
<!-- No script needed for static CSS-only diagrams -->
<!-- Optional: <script> for Mermaid or interactive walkthroughs -->
</body>
</html>Before delivering, verify:
min-width: 0. Side-by-side panels need overflow-wrap: break-word. See the Overflow Protection section in ./references/css-patterns.md.css-patterns.md for print styles.Hard rules — not guidelines. Violating these creates broken or unusable output.
subgraph to group, split into multiple diagrams, or use the hybrid pattern (simplified Mermaid overview + CSS Grid detail cards). For systems with 15+ elements, the hybrid pattern in templates/architecture.html is preferred.flowchart TD for 5+ nodes. Top-down vertical flow reads naturally and scales on narrow viewports. Use flowchart LR only for simple 3-4 node linear flows.css-patterns.md and include the TOC. Long pages without navigation are hostile to readers.<details>.innerHTML with user-provided content. Use textContent or DOM APIs. This prevents XSS in interactive elements.© NeverSight, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 12 other files in data/skills-md/abpai/skills/visual-explainer of NeverSight/learn-skills.dev.
Open the folder on GitHubat commit 08f9d22
We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in NeverSight/learn-skills.dev, which our catalogue first saw on October 7, 2026.
Visual Explainer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Visual Explainer this skillNeverSight/learn-skills.dev | 216 | 1 repos | ~5.5k | Automated safety check: Pass | MIT | |
| Self-Contained HTML PagesSourceWeft/SourceWeft | 158 | — | ~817 | Automated safety check: Pass | Custom licence | |
| Static Web Artifacts BuilderMathews-Tom/armory | 327 | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | |
| Math ExplainerGordenSun/mathVideoMaker | 289 | 1 repos | ~2.4k | Automated safety check: Pass | None | |
| HTML DesignNimaChu/html-design | 101 | — | ~2.7k | Automated safety check: Pass | None | |
| Tufte Reportglebis/claude-skills | 388 | — | ~2.4k | Automated safety check: Pass | MIT |
SourceWeft/SourceWeft
Builds and revises polished offline HTML reports, landing pages, infographics and interactive visualizations as a single file, with viewport QA before delivery.
Mathews-Tom/armory
Build self-contained static HTML artifacts opened in a browser: interactive diagrams, dashboards, infographics.
GordenSun/mathVideoMaker
Generate math explanation videos (animated with Manim) and interactive web pages from a user's request.
NimaChu/html-design
Create, redesign, repair, validate, preview, and package lightweight standalone HTML deliverables.
glebis/claude-skills
Create Tufte-inspired data reports and infographic dashboards as standalone HTML files.
shaun8149/sdf-js
Generate sdf-js code from a natural-language scene description.
NeverSight/learn-skills.dev
Create AI marketing videos for ads, promos, product launches, and brand content.
NeverSight/learn-skills.dev
Interact with Google Calendar via the Google Calendar API – list upcoming events, create new events, update or delete them.
NeverSight/learn-skills.dev
Meta-agent skill for orchestrating complex tasks through autonomous sub-agents.
NeverSight/learn-skills.dev
Build automated AI workflows combining multiple models and services.
NeverSight/learn-skills.dev
Build multi-step AI content creation pipelines combining image, video, audio, and text.
NeverSight/learn-skills.dev
Create AI-powered podcasts with text-to-speech, music, and audio editing.
Categories
Generate beautiful, self-contained HTML pages that visually explain systems, code changes, plans, and data. dev. Generate beautiful, self-contained HTML pages that visually explain systems, code changes, plans, and data.
Visual Explainer fits situations like: the user asks for a diagram; architecture overview; comparison table; any visual explanation of technical concepts.
Run `npx skills add NeverSight/learn-skills.dev --skill visual-explainer -a claude-code`. Or copy the skill folder (data/skills-md/abpai/skills/visual-explainer in NeverSight/learn-skills.dev) into .claude/skills/visual-explainer in your project. Claude Code loads it when a task matches its description.
Run `npx skills add NeverSight/learn-skills.dev --skill visual-explainer -a codex`. Or copy the skill folder (data/skills-md/abpai/skills/visual-explainer in NeverSight/learn-skills.dev) into .agents/skills/visual-explainer in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add NeverSight/learn-skills.dev --skill visual-explainer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/visual-explainer, .gemini/skills/visual-explainer, .github/skills/visual-explainer and .opencode/skills/visual-explainer in your project.
SKILL.md names no scripts, command-line tools or credentials: Visual Explainer is instructions for the agent only. Compatibility (from SKILL.md): Requires a browser to view generated HTML files. Optional surf-cli for AI image generation..
SKILL.md names 2 domains. In commands or code: fonts.googleapis.com; the agent is likely to contact it when it follows the instructions. As links in the text: github.com. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Visual Explainer is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 5.5k tokens (SKILL.md is roughly 22k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Visual Explainer: Self-Contained HTML Pages (SourceWeft/SourceWeft, 158 stars), Static Web Artifacts Builder (Mathews-Tom/armory, 327 stars), Math Explainer (GordenSun/mathVideoMaker, 289 stars) and HTML Design (NimaChu/html-design, 101 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
NeverSight (a GitHub organization) maintains it in NeverSight/learn-skills.dev, which has 216 GitHub stars. The repository holds 43 skills in this directory. The repository was last updated on October 6, 2026.
Source: NeverSight/learn-skills.dev on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.