visual-explainer
Generate rich HTML pages or slide decks for diagrams, diff reviews, plan audits, data tables, and project recaps
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Generate rich HTML pages or slide decks for diagrams, diff reviews, plan audits, data tables, and project recaps
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
Read a business card image, extract contact details (name, phone, email, company, etc.), append them to a Google Sheet, then send a welcome email and WhatsApp message to the contact.
>-
Fetch and summarize YouTube video transcripts using a residential IP proxy to bypass cloud IP blocks.
Create, inspect, and edit Microsoft PowerPoint presentations and PPTX decks with reliable layouts, templates, placeholders, notes, charts, and visual QA.
Perform JIRA operations using the MCP server as primary, with automatic fallback to REST API for operations that don't work via MCP (e.g., story points via Agile estimation endpoint, epic linking via parent field). Includes sprint workflow helpers.
Produce thoughtful design artifacts (slide decks, prototypes, mockups, landing pages, dashboards) using HTML/CSS/JS/SVG as the medium.
| name | visual-explainer |
| description | Generate rich HTML pages or slide decks for diagrams, diff reviews, plan audits, data tables, and project recaps |
| version | 1.0.1 |
| author | main |
| tools | ["filesystem","exec","documents"] |
| commands | [] |
| icon | 🖼️ |
A skill that turns complex terminal output, diagrams, comparisons, and tables into styled HTML pages you actually want to read.
This skill generates beautiful, interactive HTML pages for:
Instead of ASCII art and monospace tables in your terminal, you get proper typography, dark/light themes, interactive Mermaid diagrams with zoom and pan, and responsive layouts.
Any command can generate a slide deck instead of a scrollable page by adding a "--slides" parameter:
Ask for a visual representation of any complex topic:
The skill will:
Features automatically applied:
Outputs are written to visual-explainer/ at the root of the agent's workspace (e.g., visual-explainer/).
The skill automatically selects the best visualization based on content:
| Content Type | Visualization | Library/Tech |
|---|---|---|
| Flowcharts & Diagrams | Interactive SVG | Mermaid.js |
| System Architecture | Grid Layout | CSS Grid + Custom SVG |
| Data Tables | Styled HTML Tables | HTML + CSS |
| Comparisons | Side-by-side Cards | Flexbox Layout |
| Metrics & Stats | Charts & Graphs | Chart.js |
| Slide Decks | Reveal.js Style | Custom Animation System |
Request: "Draw a diagram of our user authentication flow"
Output: An HTML page with an interactive Mermaid diagram showing the authentication flow, with proper styling and responsive design.
Request: "Review this implementation plan against our requirements"
Output: An HTML page with a side-by-side comparison of requirements vs. plan items, with color-coding for coverage and risk assessment.
Request: "Create a project recap for the last 2 weeks of work"
Output: An HTML page with sections for completed work, pending items, blockers, and next steps, with proper styling and interactive elements.
Request: "Generate slides for our new feature presentation"
Output: An HTML slide deck with animated transitions, proper typography, and responsive design.
Every generated HTML file is self-contained with:
<style> tags<script> tagsIf the input is too complex or ambiguous:
If technical limitations prevent rendering:
This skill follows these design principles: