From viz
Routes collaborative document editing to the optimal method based on the user's environment. Activated when the user wants to EDIT content (not just view it), or when Claude wants the user to review and modify a draft. Checks terminal type and available tools to choose between browser editor, terminal split editor, or fallback.
How this skill is triggered — by the user, by Claude, or both
Slash command
/viz:viz-routerThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Route document visualization and editing to the best available method.
Route document visualization and editing to the best available method.
Before making any decision, run this command to collect environment signals:
echo "TERM_PROGRAM=${TERM_PROGRAM:-unknown}"
echo "GHOSTTY=$([ "${TERM_PROGRAM}" = "ghostty" ] && echo "yes" || echo "no")"
echo "SSH=$([ -n "${SSH_CLIENT:-}${SSH_CONNECTION:-}" ] && echo "yes" || echo "no")"
echo "EDITOR_MCP=$(command -v node >/dev/null 2>&1 && [ -f "${CLAUDE_PLUGIN_ROOT}/mcp-editor/dist/index.js" ] && echo "available" || echo "unavailable")"
Record the output. Do NOT skip this step.
Use the environment info to choose the editing method:
| Condition | Method | How |
|---|---|---|
EDITOR_MCP=available | viz-editor (browser) | Call edit-document MCP tool with content. Blocks until user clicks Done. Result is the edited markdown. |
GHOSTTY=yes and editor MCP unavailable | collab-edit (terminal split) | Write content to /tmp/viz-collab.md, run bash "${CLAUDE_PLUGIN_ROOT}/skills/collab-edit/lib/ghostty-split.sh" "nvim /tmp/viz-collab.md", wait for user completion signal. |
| Neither available | File fallback | Write content to /tmp/viz-collab.md, tell user the path, ask them to edit in their preferred editor and tell you when done. |
If the user says "open in neovim", "在 terminal 裡編輯" → use collab-edit regardless. If the user says "open in browser", "用瀏覽器" → use viz-editor regardless.
After routing, execute the chosen method. Do not explain the routing decision unless the user asks why.
User: "把這個計畫渲染出來看看" → Intent: view-only → use doc-render skill
User: "幫我產生一份草稿,我想自己改一下" → Intent: collaborative edit → check environment → route to viz-editor or collab-edit
Claude decides to show a complex comparison table: → Intent: view-only → use doc-render skill proactively
User: "我們一起改這份文件" → Intent: collaborative edit → check environment → route
User: "用 neovim 開給我改" → Intent: collaborative edit, explicit method → use collab-edit regardless of environment
npx claudepluginhub musingfox/cc-plugins --plugin vizCreate shareable HTML visual artifacts from markdown, plans, architecture docs, brainstorms, and other structured content. Prefer browser-viewable HTML first when it will materially improve clarity or sharing; otherwise fall back to terminal rendering. Triggers: visualize, mindmap, mind map, show me the structure, draw a map, make this clear, make this visual.
Generates self-contained HTML pages for technical diagrams, architecture reviews, diff reviews, plans, and comparisons. Renders complex tables as styled HTML instead of ASCII.
Writes Markdown documents and text-based Mermaid diagrams with style guides, 24 diagram-type references, and 9 document templates. Use for scientific documents, reports, READMEs, or version-controllable diagrams.