story-long-scan Skill: Web Novel Chart Scan in Claude Code

Makes Claude collect web-novel ranking pages and report which genres are rising, so you can pick a topic to write.

Installs: 17.4K; on skills.sh
Stars: 8.2K; on GitHub
Files: 14; besides SKILL.md
Updated: Nov 2026; last repo commit

story-long-scan asks which platform, channel and genre you care about. It then runs Node.js scrapers to save chart pages as files, merges them into 扫榜聚合.md, and writes a market report plus two or three topic picks into 选题决策.md. The report covers genre share, new-genre signals, word counts, title patterns and selling points. Output is in Chinese.

Start it with /story-long-scan, /长篇扫榜 or "起点排行". For Fanqie, Jinjiang and Ciweimao it needs a Chrome window started through the browser-cdp skill. Qidian charts are read from its mobile pages without Chrome. If scraping fails you can paste charts or screenshots, or let it use built-in genre notes, which it labels as unverified.

Good for

Web-novel authors choosing a genre for a new book
Editors and analysts who want a repeatable view of Qidian, Fanqie, Jinjiang, Qimao and Ciweimao charts
Claude Code or Codex users who read Chinese and can run Node.js

Install story-long-scan

Claude Code

Copy this prompt.

Install the story-long-scan skill in Claude Code. Run this command:

npx skills add zenstory-ai/oh-story-claudecode --skill story-long-scan --skill browser-cdp

Then check that it loaded and tell me how to use it.

2
Paste it into Claude Code. It shows the change and asks before running it.

Requires Node.js.

story-long-scan tells you to start Chrome with /browser-cdp for most platforms, so this installs browser-cdp with it. browser-cdp needs Node.js 20+ and a global agent-browser package (see its page). The README also asks you to run /story-setup in your writing project; the full set installs with npx skills add zenstory-ai/oh-story-claudecode -y -g.

From the vendor's docs. Source.

What's in the skill

When it loads

长篇网文扫榜。分析起点、番茄、晋江、七猫等平台排行榜与新书数据，提炼市场趋势与热门题材。触发方式：/story-long-scan、/长篇扫榜、「长篇什么火」「起点排行」「扫七猫新书」。

Sections in SKILL.md

扫榜原则
原则 1：扫榜看模式，别只看排名
原则 2：各平台的热度口径不同
原则 3：扫榜的目的是找到你能写的爆款题材
扫榜流程
Phase 1：确认平台和方向
Phase 2：确定数据来源
Phase 3：数据分析
Phase 4：输出扫榜报告
扫榜结论：{平台名称}
市场概况
题材热度排行
新题材信号
经典题材动态
新元素提取
关键数据洞察

Key facts

Author: zenstory-ai
Repo: zenstory-ai/oh-story-claudecode
License: MIT (as listed by the crawl)
Installs on skills.sh: 17,425 (Nov 2, 2026)
GitHub stars: 8,223 (repo, Nov 2, 2026)
Last commit: 2026-11-01
Files: 15 files including SKILL.md: 7 reference guides and 7 scripts
Needs: Node.js; Chrome started by the browser-cdp skill for most platforms
Works in: Claude Code, Codex CLI, Antigravity, OpenCode, ZCode, OpenClaw, Reasonix
Language: SKILL.md and output are in Chinese

What it includes

Starts a chart scan; also /长篇扫榜 or "起点排行"
Asks for platform (Qidian, Fanqie, Jinjiang, Qimao, Ciweimao or several), channel and whether you want new books or the mature chart.
Try: “/story-long-scan 扫一下番茄男频新书榜，我想写都市异能”
Runs code · /story-long-scan
Runs one scraper per platform into a new 扫榜/<date>/ folder
qidian-rank-scraper.js, fanqie-rank-scraper.js, jjwxc-rank-scraper.js, qimao-rank-scraper.js and ciweimao-rank-scraper.js. Each run uses a new dated folder so old charts do not mix in.
Runs code · Script collection
Takes charts you paste or screenshot, in a set format
Used when scripts cannot get a chart. Each book gets a line with rank, title, author, genre, status, word count and a popularity number.
Write · Author-supplied data
Falls back to genre-trends.md and labels the result unverified
The report opens by saying it is based on past genre candidates with no live chart check.
Read · Built-in knowledge
Merges chart files into 扫榜聚合.md and can sample books by genre or tag
Shows genre spread, de-duplicated counts, popularity and word-count medians, tags, title words and repeat appearances across charts.
Runs code · aggregate-rank.js
Writes the 扫榜结论 section into 选题决策.md
Genre ranking, new-genre signals, classic-genre changes, new elements, key numbers and three directions worth watching. Trend arrows read 未比较 when there is no earlier scan to compare.
Write · Market report
Writes 2 to 3 recommended topics with feasibility, using your materials and limits
Asks for your target platform, existing material, strengths and planned length if they are missing.
Write · Topic decision

From the official docs

Permissions

Medium risk

The skill runs scrapers that load live chart pages and, for most platforms, a Chrome window that browser-cdp starts. Save your tabs before you agree to let it close Chrome.

What it can do

Read your data
Create and change things
Delete things
Read-only mode

Watch out for

Setup copies your Chrome profile
browser-cdp's setup script copies your Chrome Default profile into ~/chrome-debug-profile, including cookies and saved-login files, so the scraper Chrome starts logged in. Its --reset option deletes that folder and copies again. github.com
It drives a Chrome window and may close your Chrome
For most platforms it needs Chrome from the browser-cdp skill, whose setup script can end your running Chrome after you agree. Save your tabs first. github.com
Scrapers fetch live sites
Node.js scrapers load chart pages on five platforms. Sites may block or change. Checking each site's terms before you scrape is our advice, not something SKILL.md says. github.com
Needs a global npm package
browser-cdp requires agent-browser installed with npm install -g. Install only what you recognise. github.com

Technical details

Talks to	qidian.com. fanqienovel.com. jjwxc.net. qimao.com. ciweimao.com

Questions

What does story-long-scan do?

It collects ranking pages from long-fiction platforms and tells you which genres, settings and title patterns repeat. It then proposes two or three topics that fit what you can write. Output is Chinese and saved under 扫榜/<date>/.

How do I install story-long-scan?

Use the install box above, which installs it together with browser-cdp because most platforms need a Chrome window started by that skill. The README installs the whole Oh Story set with npx skills add zenstory-ai/oh-story-claudecode -y -g and asks you to run /story-setup in your writing project.

Which platforms can it scan?

Qidian, Fanqie, Jinjiang, Qimao and Ciweimao. Qidian charts need no Chrome, but its new-book library does. Qidian women's channel cannot be scraped, so you paste those charts yourself.

Do I need to log in or use an API key?

SKILL.md names no API key. The Chrome-based scrapers run in a Chrome profile that browser-cdp copies from your own Chrome. Fanqie and Qidian use anti-scraping, so pages can come back blank or blocked; SKILL.md then asks you to paste the data.

Can I trust the trend it reports?

SKILL.md says one book's rank is only a clue. It wants repeated patterns across recent charts and many books before calling a trend. Retention and subscription numbers sit in author back offices, so it draws no conclusion from them unless you provide them.

Does it work in Claude Code, Codex and the Claude app?

The README names Claude Code, Codex CLI, Google Antigravity, OpenCode, ZCode, OpenClaw and Reasonix. It does not document the Claude app, and the scrapers need a local Chrome and Node.js.

How is it different from story-short-scan?

This one reads long-fiction charts (Qidian, Fanqie, Jinjiang, Qimao, Ciweimao). story-short-scan covers short-story sources: Dianzhong and Heiyan by script, and Zhihu Yanyan, Fanqie and Qimao short stories by pasted data.

Is it safe to run?

It runs Node.js scrapers that fetch web pages and, for most platforms, drive a Chrome window through browser-cdp. That skill can close your running Chrome if you agree, so save your tabs first. The scrapers save chart files into the scan folder.

Information

updated Nov 2, 2026

Repository: zenstory-ai/oh-story-claudecode
Folder: skills/story-long-scan

zenstory-ai/oh-story-claudecode skills.sh

Sources

Docs, issue trackers and discussions this page is built from.

Show all 9

skills CLI commands · github.com
oh-story-claudecode README · github.com
browser-cdp SKILL.md · github.com
story-long-scan SKILL.md · github.com
skills.sh listing · skills.sh
zenstory-ai/oh-story-claudecode · github.com
platform-qidian.md · github.com
platform-fanqie.md · github.com
browser-cdp setup-cdp-chrome.js · github.com