doc-visual

# doc-visual Read a markdown document and write a visual report with diagrams that match each section's meaning. Output is HTML (default) or markdown. You write the output directly — no templates, no intermediate JSON, no agent chains. ## Why this matters The previous version of this skill passed text through a pipeline of agents — each one only saw the output of the stage before it. By the time the report was assembled, the original content had been compressed into summaries of summaries. That's the failure mode you're replacing. You see the original document in full. That's the core advantage. If you find yourself writing "this section discusses X" instead of explaining X — that's compression, and it's the exact failure this redesign exists to fix. ## Input Argument = single markdown file path. Directories, URLs, stdin not supported. 1. Validate file exists + markdown extension (`.md`, `.markdown`, `.txt`) 2. Missing/no permission → abort immediately 3. Read the full file content ### Format detection | Flag | Values | Default | |---|---|---| | `--format` | `html` / `md` | `html` | | `--lang` | ISO code | auto-detected from document | | `--local` | switch | off — capable HTML **publishes to an Artifact by default** | | `--artifact` | switch | retained no-op alias (already the default on capable HTML) | The report language must match the source document's language. **Channel is decided by the shared contract**, not re-derived here — read `${CLAUDE_PLUGIN_ROOT}/refer...