story-short-scan Skill: Short Story Market Scan

Makes Claude scan short-story listings and report which reader emotions and genres to write next, for authors of short web fiction.

Installs: 17.3K; on skills.sh
Stars: 8.2K; on GitHub
Files: 9; besides SKILL.md
Updated: Nov 2026; last repo commit

story-short-scan looks at short-story listings and sorts the books into six reader emotions, such as unresolved regret or a satisfying comeback. It also reports genre hot spots, word counts, blurb and title habits, and suggests directions you can write. It saves the result in 短篇扫榜结论.md. Output is in Chinese.

Start it with /story-short-scan, /短篇扫榜 or "短篇什么火". Scripts can collect Dianzhong, and Heiyan if you have a Heiyan back-office account. Zhihu Yanyan, Fanqie and Qimao short stories have no script, so you paste charts, text or screenshots. Both scripts need Chrome started through the browser-cdp skill. Without data it uses built-in historical notes and labels them unverified.

Good for

Authors of short web stories picking a topic and an emotion to aim at
Writers with a Heiyan author account or a Dianzhong target who want listing data
Claude Code or Codex users who read Chinese and can run Node.js

Install story-short-scan

Claude Code

Copy this prompt.

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

npx skills add zenstory-ai/oh-story-claudecode --skill story-short-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-short-scan tells you to start Chrome with /browser-cdp for its scripts, 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

短篇网文扫榜。分析知乎盐言、七猫、黑岩、点众等平台热门短篇数据，捕捉风口题材。触发方式：/story-short-scan、/短篇扫榜、「短篇什么火」「知乎故事排行」。

Sections in SKILL.md

核心哲学
原则 1：短篇市场是情绪市场
原则 2：热度只按各平台自己的口径比
原则 3：短篇风口来得快去得快
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
情绪排行
题材热点
关键数据洞察
变化（和 {上期日期} 比）
值得写的方向

Key facts

Author: zenstory-ai
Repo: zenstory-ai/oh-story-claudecode
License: MIT (as listed by the crawl)
Installs on skills.sh: 17,280 (Nov 2, 2026)
GitHub stars: 8,223 (repo, Nov 2, 2026)
Last commit: 2026-11-01
Files: 10 files including SKILL.md: 5 reference guides and 4 scripts
Needs: Node.js; Chrome started by the browser-cdp skill
Works in: Claude Code, Codex CLI, Antigravity, OpenCode, ZCode, OpenClaw, Reasonix
Language: SKILL.md and output are in Chinese

What it includes

Starts a short-story scan; also /短篇扫榜 or "短篇什么火"
Asks which platform, channel (male or female) and kind of short story. If you have an editor call-for-submissions, send it too.
Try: “/story-short-scan 扫点众女频短篇，看现在什么情绪最多”
Runs code · /story-short-scan
Collects Dianzhong male and female short-story listings through Chrome
Reads ishugui.com/browse pages and saves a file per channel. The platform reference says no login is needed.
Runs code · dz-browse-scraper.js
Reads the Heiyan back-office book list, with tags and blurbs if asked
Needs a Heiyan back-office account that you log in to by hand in the Chrome window. It lists recently shelved books, not a popularity chart.
Runs code · heiyan-booklist-scraper.js
Takes pasted charts, text or screenshots for Zhihu Yanyan, Fanqie and Qimao short stories
Formatted per manual-rank-input.md so they merge with script data.
Write · Author-supplied charts
Merges listings into 扫榜聚合.md and samples books by genre, tag or title word
Run with --scale short. The main session reads this summary rather than every raw file.
Runs code · aggregate-rank.js
Sorts books into six emotions from their blurbs and counts them
The six are 意难平, 反转震撼, 爽感释放, 治愈温暖, 细思极恐 and 共鸣感动. A book that cannot be judged is counted as 待定.
Read · Emotion ranking
Writes 短篇扫榜结论.md with the scan result and a topic-match section
States sample date, coverage, confidence and a re-scan date. Asks where you plan to publish, your material and target length.
Write · Report and topic match

From the official docs

Permissions

Medium risk

The skill runs scripts that load live sites in a Chrome window started by browser-cdp, and the Heiyan script works inside your logged-in author back office. Save your tabs first and skip Heiyan if you do not want that.

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 Chrome and may close your Chrome
The scripts need Chrome from the browser-cdp skill, whose setup script can end your running Chrome after you agree. Save your tabs first. github.com
Heiyan scan uses your logged-in back office
The Heiyan script calls the back-office book API (ms.zhangwenpindu.cn) from a Chrome window where you log in by hand. The platform reference says you need a Heiyan back-office account. Use it only on an account you are allowed to use (our advice), or skip Heiyan. 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	ishugui.com. manage.zhangwenpindu.cn. ms.zhangwenpindu.cn

Questions

What does story-short-scan do?

It collects short-story listings and shows which reader emotions and genres are common. It then suggests directions you could write and saves them in 短篇扫榜结论.md. It writes in Chinese.

How do I install story-short-scan?

Use the install box above, which installs it together with browser-cdp because its scripts 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 does it cover?

Scripts cover Dianzhong and Heiyan. For Zhihu Yanyan, Fanqie short and Qimao short you paste charts, text or screenshots, because no script exists for them.

Do I need an account or an API key?

Dianzhong needs no login. Heiyan needs a Heiyan back-office account that you log in to yourself in Chrome. SKILL.md names no API key.

Does it show which stories are hot?

Not from Dianzhong or Heiyan alone. Those scripts list books on shelf, so the report says shelf count and does not say which story is hot. Heat figures come only from charts you paste.

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 scripts need a local Chrome and Node.js.

How is it different from story-long-scan?

story-long-scan covers long-fiction charts on Qidian, Fanqie, Jinjiang, Qimao and Ciweimao. This one is for short stories and sorts them by reader emotion.

Is it safe to run?

It runs Node.js scripts that load live sites in a Chrome window started by browser-cdp. That skill can close your running Chrome if you agree, so save your tabs first. For Heiyan the script reads your back office while you are logged in.

Information

updated Nov 2, 2026

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

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

Sources

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

Show all 10

skills CLI commands · github.com
oh-story-claudecode README · github.com
browser-cdp SKILL.md · github.com
story-short-scan SKILL.md · github.com
skills.sh listing · skills.sh
zenstory-ai/oh-story-claudecode · github.com
platform-heiyan.md · github.com
platform-dianzhong.md · github.com
browser-cdp setup-cdp-chrome.js · github.com
heiyan-booklist-scraper.js · github.com