Fanqie Publish logo

Fanqie Publish

Community
ricky-theseus
fanqie-publish

Publish novel chapters from local Markdown files to the Fanqie Novel writer backend via browser automation. Supports single/batch/scheduled publish with login state persistence.

Overview

Publisherricky-theseus
RepositoryDaisyWriter
Skill namefanqie-publish
Stars
77
Forks
5
Bundled files
16
LicenseGPL-3.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 16 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by ricky-theseus on GitHub. Read the source before you install it.

Installation

Install the Fanqie Publish AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/ricky-theseus/DaisyWriter/tree/master/skills/fanqie
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/ricky-theseus/DaisyWriter.git /tmp/DaisyWriter
mkdir -p .claude/skills
cp -r /tmp/DaisyWriter/skills/fanqie .claude/skills/fanqie-publish
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Fanqie Publish in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Fanqie Publish on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Fanqie Publish is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Fanqie Publisher (OpenCode Edition)

Use this skill to publish chapter title + body from local Markdown files to the Fanqie writer backend via Playwright browser automation.

Original project: amm10090/fanqie-publisher-skill — MIT license. This fork: adapted from OpenClaw Skill to OpenCode project-level skill.

Scope

This skill is for:

  • uploading one chapter from a .md file
  • batch publishing chapters from a directory
  • immediate publish and scheduled publish
  • saving and reusing browser login state

This skill is not for guessing selectors blindly. If the page changes, inspect first, then update references/selectors.md and {baseDir}/scripts/publish_fanqie.js.

Source content

Expected source content shape:

  • one .md file = one chapter
  • filename example: 第001章_标题.md
  • first line: chapter title (e.g. 第001章 标题)
  • body starts after the heading

Files

  • scripts/prepare_chapters.py — parse .md files into normalized chapter data
  • scripts/browser_page_picker.js — pick an existing Fanqie writer tab or open a safe fallback page
  • scripts/fanqie_login_flow.js — shared login helpers
  • scripts/login_fanqie.js — open browser, detect login page, capture QR code, and save login state
  • scripts/publish_fanqie.js — publish one or more chapters with Playwright
  • scripts/state.py — persist publish history and prevent duplicates
  • references/workflow.md — current known backend workflow
  • references/selectors.md — selectors and page reconnaissance notes

Prerequisites

  1. Node.js (18+) and Python (3.8+)
  2. Install npm dependencies:
bash
cd "{baseDir}"
npm install
npx playwright install chromium
  1. Chrome started with remote debugging:
bash
"C:\Program Files\Google\Chrome\Application\chrome.exe" --remote-debugging-port=9222
  1. First-time login: node "{baseDir}/scripts/login_fanqie.js" --cdp http://127.0.0.1:9222

Quick Start

Preview chapters

bash
python "{baseDir}/scripts/prepare_chapters.py" --dir "/path/to/chapters" --preview

Upload a single chapter as draft

bash
node "{baseDir}/scripts/publish_fanqie.js" \
  --cdp http://127.0.0.1:9222 \
  --book-id "7654770364014136344" \
  --file "/path/to/第001章-标题.md"

Upload a range of chapters as drafts

bash
node "{baseDir}/scripts/publish_fanqie.js" \
  --cdp http://127.0.0.1:9222 \
  --book-id "7654770364014136344" \
  --dir "/path/to/chapters" \
  --range "第0005章-第0010章"

Or use chapter numbers:

bash
node "{baseDir}/scripts/publish_fanqie.js" \
  --cdp http://127.0.0.1:9222 \
  --book-id "7654770364014136344" \
  --book-name "书名" \
  --dir "/path/to/chapters" \
  --range "5-10"

Upload all chapters as drafts

bash
node "{baseDir}/scripts/publish_fanqie.js" \
  --cdp http://127.0.0.1:9222 \
  --book-id "7654770364014136344" \
  --book-name "书名" \
  --dir "/path/to/chapters"

Actually publish (default is draft-only)

bash
node "{baseDir}/scripts/publish_fanqie.js" \
  --cdp http://127.0.0.1:9222 \
  --book-id "7654770364014136344" \
  --book-name "书名" \
  --dir "/path/to/chapters" \
  --range "第001章-第003章" \
  --confirm-publish

All Commands

Preview

bash
python "{baseDir}/scripts/prepare_chapters.py" --dir "/path/to/chapters" --preview

Login

bash
node "{baseDir}/scripts/login_fanqie.js" --cdp http://127.0.0.1:9222

Upload as draft (default — no extra flag needed)

bash
# Single chapter
node "{baseDir}/scripts/publish_fanqie.js" --cdp http://127.0.0.1:9222 --book-id "..." --file "/path/to/chapter.md"

# Range
node "{baseDir}/scripts/publish_fanqie.js" --cdp http://127.0.0.1:9222 --book-id "..." --dir "/path/to/chapters" --range "5-10"

# All
node "{baseDir}/scripts/publish_fanqie.js" --cdp http://127.0.0.1:9222 --book-id "..." --dir "/path/to/chapters"

Publish for real (skip draft)

bash
node "{baseDir}/scripts/publish_fanqie.js" --cdp http://127.0.0.1:9222 --book-id "..." --file "/path/to/chapter.md" --confirm-publish

node "{baseDir}/scripts/publish_fanqie.js" --cdp http://127.0.0.1:9222 --book-id "..." --dir "/path/to/chapters" --range "1-3" --confirm-publish

Scheduled publish

bash
node "{baseDir}/scripts/publish_fanqie.js" --cdp http://127.0.0.1:9222 --book-id "..." --file "/path/to/chapter.md" --confirm-publish --mode scheduled --schedule-at "2026-03-13 21:00"

# Batch schedule with 30min intervals
node "{baseDir}/scripts/publish_fanqie.js" --cdp http://127.0.0.1:9222 --book-id "..." --dir "/path/to/chapters" --range "第018章-第020章" --confirm-publish --mode scheduled --schedule-at "2026-03-13 21:00" --schedule-step-minutes 30

Flag reference

FlagPurpose
--cdpChrome DevTools Protocol endpoint
--book-idBook ID from Fanqie writer URL
--book-nameBook name (for URL construction)
--fileSingle chapter file
--dirDirectory containing chapter files
--rangeChapter range, e.g. "5-10" or "第05章-第10章"
--start-fromStart from this chapter (used alone or with --limit)
--end-atEnd at this chapter (used with --start-from)
--limitMax chapters to process
--confirm-publishActually publish (default is save as draft)
--modeimmediate or scheduled (only with --confirm-publish)
--schedule-atSchedule datetime, e.g. "2026-03-13 21:00"
--schedule-step-minutesMinutes between chapters in batch schedule
--skip-publishedSkip already-published chapters
--volumeVolume name to assign

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Fanqie Publish AI skill do?

Publish novel chapters from local Markdown files to the Fanqie Novel writer backend via browser automation. Supports single/batch/scheduled publish with login state persistence.

Why use Fanqie Publish on TypingMind?

Because you install it once and use it with any model. Fanqie Publish is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Fanqie Publish in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ricky-theseus/DaisyWriter/tree/master/skills/fanqie. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Fanqie Publish?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Fanqie Publish?

As many as you like. As long as a model supports skills, you can use Fanqie Publish with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Fanqie Publish AI skill free?

Yes. It is published on GitHub by ricky-theseus under the GPL-3.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇