Long-Form Web Novel Ranking Scan (story-long-scan)

Scrapes and cleans Chinese web-novel platform rankings, then turns the patterns into trend reports and feasibility-checked story pitches.

Content & WritingIntermediate★ 6,873⑂ 979AI score 8/10Last updated: Sep 14, 2026

What it does

Runs bundled Node.js scrapers to collect rankings from Qidian, Fanqie, Jinjiang, Qimao and Ciweimao (monthly-ticket, bestseller, new-book, gold lists, etc.).
Enforces data-quality checks right after scraping: minimum 15 valid rows, required fields (rank/title/author), removal of platform boilerplate, synopsis truncation at 100 characters, and a data quality header block in each output file.
Produces a scan report covering genre distribution, emerging-genre signals, classic-genre momentum, word-count and update-rate bands, title-naming patterns and high-frequency tags.
Finishes with a 选题决策.md topic-decision file offering 2–3 pitches (why it can pop → market evidence → differentiation → feasibility and failure risk), with a hard rule that sparse data or fewer than 15 comparable samples caps feasibility at "medium".

Who it's for

Authors writing (or planning) long-form serials on Chinese web-novel platforms.
Editors and content strategists who need quantitative market research instead of gut feel.
Content analysts who want structured ranking datasets they can reuse.

Examples

Run /story-long-scan, pick Qidian and the "new signed authors" list; the skill executes node scripts/qidian-rank-scraper.js --type newsign via mobile SSR and returns a genre-distribution table plus trend notes.
Ask for "Fanqie male-channel reading list, top 15 per category"; it launches Chrome through browser-CDP, decodes the anti-scrape font obfuscation from detail pages, and compares active-reader counts.
Paste your own ranking screenshots or links; the skill parses them, asks about your material stock and preferred genres, then returns three pitches with feasibility and failure risk.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/zenstory-ai/oh-story-claudecode/HEAD/skills/story-long-scan/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)

Download the ZIP with the button below.
In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.

↓ Download ZIP

Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/story-long-scan folder from the GitHub repo zenstory-ai/oh-story-claudecode into my ~/.claude/skills/story-long-scan/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/zenstory-ai/oh-story-claudecode.git && mkdir -p ~/.claude/skills && cp -r oh-story-claudecode/skills/story-long-scan ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

Open a terminal in any working directory.
Clone the repo: git clone https://github.com/zenstory-ai/oh-story-claudecode.git
Create the skills folder: mkdir -p ~/.claude/skills
Copy just this skill: cp -r oh-story-claudecode/skills/story-long-scan ~/.claude/skills/
Verify Node.js (18+ recommended) with node -v, since the scrapers are Node scripts.
For Fanqie/Qimao/Ciweimao you also need Chrome installed plus the repo's /browser-cdp skill copied over, because those sites require a browser session.
Restart Claude Code and type /story-long-scan (or ask "what's hot in long-form web novels") to confirm it loads.

View source on GitHub ↗License: MIT