---
layout: tap
site_name: juejin
tap_name: post
description: "Publish article on Juejin"
intent: write
columns:
  - status
  - url
args:
  - name: title
    type: string
    description: "Article title"
  - name: body
    type: string
    description: "Article body (Markdown)"
  - name: category
    type: string
    description: "Category: Frontend/Backend/Android/iOS/AI/Tools"
  - name: tags
    type: string
    description: "Comma-separated tags (max 3)"
args_json: |
  {"title":{"type":"string","description":"Article title"},"body":{"type":"string","description":"Article body (Markdown)"},"category":{"type":"string","description":"Category: Frontend/Backend/Android/iOS/AI/Tools"},"tags":{"type":"string","description":"Comma-separated tags (max 3)"}}
health_json: |
  {"min_rows":1,"non_empty":[]}
example_args: ""
source_url: https://github.com/LeonTing1010/tap-skills/blob/main/community/juejin/post.plan.json
license: MIT
---

<section>
  <h2>What it does</h2>
  <p>Publish article on Juejin</p>
</section>

<section>
  <h2>Install Taprun once</h2>
  <p>Taprun ships as a single MCP server exposing a catalog of compiled taps. One-time setup on macOS / Linux:</p>
  <pre><code>brew install LeonTing1010/tap/taprun
tap mcp connect</code></pre>
  <p>Or drop this into your <code>claude_desktop_config.json</code> (works identically in Claude Code, Cursor, Cline, Windsurf — any MCP host):</p>
  <pre><code>{
  &quot;mcpServers&quot;: {
    &quot;tap&quot;: {
      &quot;command&quot;: &quot;tap&quot;,
      &quot;args&quot;: [&quot;mcp&quot;, &quot;start&quot;]
    }
  }
}</code></pre>
</section>

<section>
  <h2>Call <code>juejin/post</code></h2>
  <p>Terminal, once installed:</p>
  <pre><code>tap run juejin/post</code></pre>
  <p>From the MCP host — exact same compiled plan, deterministic replay, zero LLM tokens:</p>
  <pre><code>tap.run({ site: &quot;juejin&quot;, name: &quot;post&quot; })</code></pre>
</section>

<section>
  <h2>Why compile it once</h2>
  <p>This plan was forged once — the AI read <code>juejin</code>, picked stable structural addresses (JSON-LD, ARIA, RSS, or declared API endpoints, in that priority order), and saved them to a <code>.plan.json</code>. Every replay since then has used zero LLM tokens. When <code>juejin</code> ships a site change that breaks the extraction, <code>tap verify</code> surfaces it before your data goes stale — not after your pipeline silently writes garbage for a week.</p>
</section>

<section>
  <h2>Related juejin taps</h2>
  <table><thead><tr><th>tap</th><th>description</th></tr></thead><tbody>
    <tr><td><a href="/taps/juejin/hot"><code>juejin/hot</code></a></td><td>Juejin trending articles</td></tr>
  </tbody></table>
</section>