with one click
markdown-novel-viewer
// [Content] Use when you need background HTTP server rendering markdown files with calm, book-like reading experience.
// [Content] Use when you need background HTTP server rendering markdown files with calm, book-like reading experience.
[HINT] Download the complete skill directory including SKILL.md and all related files
| name | markdown-novel-viewer |
| version | 1.0.0 |
| description | [Content] Use when you need background HTTP server rendering markdown files with calm, book-like reading experience. |
| disable-model-invocation | true |
Goal: Background HTTP server that renders markdown files with a calm, book-like reading UI and browses directories.
Workflow:
Key Rules:
npm install before first use (marked, highlight.js, gray-matter)/preview slash command for quick accessBe skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).
Background HTTP server rendering markdown files with calm, book-like reading experience.
This skill requires npm dependencies. Run one of the following:
# Option 1: Install via ClaudeKit CLI (recommended)
ck init # Runs install.sh which handles all skills
# Option 2: Manual installation
cd .claude/skills/markdown-novel-viewer
npm install
Dependencies: marked, highlight.js, gray-matter
Without installation, you'll get Error 500: Error rendering markdown.
Universal viewer - pass ANY path and view it:
# View a markdown file
node .claude/skills/markdown-novel-viewer/scripts/server.cjs \
--file ./plans/my-plan/plan.md \
--open
# Browse a directory
node .claude/skills/markdown-novel-viewer/scripts/server.cjs \
--dir ./plans \
--host localhost \
--open
# Background mode
node .claude/skills/markdown-novel-viewer/scripts/server.cjs \
--file ./README.md \
--background
# Stop all running servers
node $HOME/.claude/skills/markdown-novel-viewer/scripts/server.cjs --stop
Use /preview for quick access:
/preview plans/my-plan/plan.md # View markdown file
/preview plans/ # Browse directory
/preview --stop # Stop server
T - Toggle themeS - Toggle sidebarLeft/Right - Navigate phasesEscape - Close sidebar (mobile)| Option | Description | Default |
|---|---|---|
--file <path> | Markdown file to view | - |
--dir <path> | Directory to browse | - |
--port <number> | Server port | 3456 |
--host <addr> | Host to bind | localhost |
--open | Auto-open browser | false |
--background | Run in background | false |
--stop | Stop all servers | - |
scripts/
├── server.cjs # Main entry point
└── lib/
├── port-finder.cjs # Dynamic port allocation
├── process-mgr.cjs # PID file management
├── http-server.cjs # Core HTTP routing (/view, /browse)
├── markdown-renderer.cjs # MD→HTML conversion
└── plan-navigator.cjs # Plan detection & nav
assets/
├── template.html # Markdown viewer template
├── novel-theme.css # Combined light/dark theme
├── reader.js # Client-side interactivity
├── directory-browser.css # Directory browser styles
| Route | Description |
|---|---|
/view?file=<path> | Markdown file viewer |
/browse?dir=<path> | Directory browser |
/assets/* | Static assets |
/file/* | Local file serving (images) |
http, fs, path, netmarked, highlight.js, gray-matter (installed via npm install)Light mode variables in assets/novel-theme.css:
--bg-primary: #faf8f3; /* Warm cream */
--accent: #8b4513; /* Saddle brown */
Dark mode:
--bg-primary: #1a1a1a; /* Near black */
--accent: #d4a574; /* Warm gold */
--content-width: 720px;
Start on localhost unless you have explicitly accepted the network exposure of serving local files:
# Start locally
node server.cjs --file ./README.md --host localhost --port 3456
The server returns the local URL in its output:
{
"success": true,
"url": "http://localhost:3456/view?file=...",
"port": 3456
}
Port in use: Server auto-increments to next available port (3456-3500)
Images not loading: Ensure image paths are relative to markdown file
Server won't stop: Check /tmp/md-novel-viewer-*.pid for stale PID files
Remote access denied: This viewer is intended for local use; keep --host localhost unless you have explicitly accepted the network exposure.
[IMPORTANT] Use
TaskCreateto break ALL work into small tasks BEFORE starting — including tasks for each file read. This prevents context loss from long files. For simple tasks, AI MUST ATTENTION ask user whether to skip.
AI Mistake Prevention — Failure modes to avoid on every task: Check downstream references before deleting. Deleting components causes documentation and code staleness cascades. Map all referencing files before removal. Verify AI-generated content against actual code. AI hallucinates APIs, class names, and method signatures. Always grep to confirm existence before documenting or referencing. Trace full dependency chain after edits. Changing a definition misses downstream variables and consumers derived from it. Always trace the full chain. Trace ALL code paths when verifying correctness. Confirming code exists is not confirming it executes. Always trace early exits, error branches, and conditional skips — not just happy path. When debugging, ask "whose responsibility?" before fixing. Trace whether bug is in caller (wrong data) or callee (wrong handling). Fix at responsible layer — never patch symptom site. Assume existing values are intentional — ask WHY before changing. Before changing any constant, limit, flag, or pattern: read comments, check git blame, examine surrounding code. Verify ALL affected outputs, not just the first. Changes touching multiple stacks require verifying EVERY output. One green check is not all green checks. Holistic-first debugging — resist nearest-attention trap. When investigating any failure, list EVERY precondition first (config, env vars, DB names, endpoints, DI registrations, data preconditions), then verify each against evidence before forming any code-layer hypothesis. Surgical changes — apply the diff test. Bug fix: every changed line must trace directly to the bug. Don't restyle or improve adjacent code. Enhancement task: implement improvements AND announce them explicitly. Surface ambiguity before coding — don't pick silently. If request has multiple interpretations, present each with effort estimate and ask. Never assume all-records, file-based, or more complex path.
Critical Thinking Mindset — Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act. Anti-hallucination: Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination.
MUST ATTENTION apply critical thinking — every claim needs traced proof, confidence >80% to act. Anti-hallucination: never present guess as fact.
MUST ATTENTION apply AI mistake prevention — holistic-first debugging, fix at responsible layer, surface ambiguity before coding, re-read files after compaction.
IMPORTANT MUST ATTENTION break work into small todo tasks using TaskCreate BEFORE starting
IMPORTANT MUST ATTENTION search codebase for 3+ similar patterns before creating new code
IMPORTANT MUST ATTENTION cite file:line evidence for every claim (confidence >80% to act)
IMPORTANT MUST ATTENTION add a final review todo task to verify work quality
[TASK-PLANNING] Before acting, analyze task scope and systematically break it into small todo tasks and sub-tasks using TaskCreate.