#7171st of 85 in Skills, plugins and rules
visual-explainer
Agent skill that renders diagrams, diff reviews and tables as styled HTML pages
- Stars
- 10.3k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- JavaScript
Missed the latest GitHub check; these facts may be older.
Overview
An agent skill that makes a coding agent write a self-contained HTML page and open it in the browser, instead of printing ASCII diagrams and pipe tables. It ships command templates such as /diff-review and /plan-review, plus a local stdio MCP server, a native Pi tool, and optional PPTX and MP4 export. It installs as a Claude Code plugin or by copying the skill directory for Codex, Cursor, OpenCode and Antigravity.
Who it is for: Developers using coding agents who want readable diagrams and reviews
Strengths
- Normal skill use needs only a browser: no build step, no runtime dependencies
- Works across many harnesses: Claude Code, Codex, Cursor, OpenCode, Pi, Antigravity
- MCP server is local stdio only, no LLM calls, writes confined to an output directory
- Bundled commands for diff review, plan review, slides, fact-check and project recap
Weaknesses
- Non-Claude harnesses need manual copy installs; prompt support varies by build
- Video export needs ffmpeg, Chrome and playwright-core installed separately
- PPTX export is a static utility for simple HTML slide decks only
- Output quality depends on the agent model following the skill instructions
What it needs
- no GPU
- Needs Web browser, Node.js (optional MCP and PPTX utilities), ffmpeg, Chrome, playwright-core (optional video export)
Also in Skills, plugins and rules
See all 85| Rank | Project | Score |
|---|---|---|
| 1 | skillsAgent skills for planning, TDD, debugging and code review | 94 out of 100 |
| 2 | eccAgents, skills, hooks and rules bundle for Claude Code, Codex and other harnesses | 94 out of 100 |
| 3 | cavemanCuts token use in coding agents with terse replies and compressed inputs | 94 out of 100 |
| #4 | ponytailSkill prompt that makes coding agents write less code and add tests | 92 out of 100 |
| #5 | impeccableDesign skill with 24 commands and a detector for AI-generated frontends | 92 out of 100 |