Skip to content
SkillScript-led2,987 tokens in use

story-long-scan

Scans web novel rankings on Qidian, Fanqie, Jinjiang, Qimao and Ciweimao, then reports genre trends and recommends topics to test.

8,793 stars on the repository MIT Licensezenstory-ai/oh-story-claudecode · skills/story-long-scan
npx skills add zenstory-ai/oh-story-claudecode -y -g
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing story-long-scan costs

111tokens idle
2,987tokens in use
11,604tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Script-led

Script-ledMixedModel-led

Most of this skill is scripts, so it behaves much the same whichever model runs it.

This describes the skill's structure, how much of it is scripts. It does not say how well it works. Scripts: scripts/aggregate-rank.js, scripts/cdp-utils.js, scripts/ciweimao-rank-scraper.js, scripts/fanqie-rank-scraper.js, scripts/jjwxc-rank-scraper.js, scripts/qidian-rank-scraper.js, scripts/qimao-rank-scraper.js.

Touches

shelldetectednetworkdetectedwrites filesdetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter8/15
  • Structure16/25
  • Examples9/15
  • Output0/15
  • Size15/15
  • Resources15/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Fair
  • Hidden characters−20

    characters that render as nothing or reorder the text

    scripts/aggregate-rank.js, line 171
  • Writes files−8

    does this on the machine, and the frontmatter does not say so

    scripts/aggregate-rank.js, line 757
  • Runs shell commands−5

    does this on the machine, and the frontmatter does not say so

    scripts/cdp-utils.js, line 11
  • Reaches the network−10

    does this on the machine, and the frontmatter does not say so

    scripts/jjwxc-rank-scraper.js, line 116

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity100
  • Maintenance100
  • Community60
  • Maturity28
  • Momentum40

story-long-scan collects ranking and new-book data from the main Chinese web novel platforms, aggregates it by genre, word count, titles and tags, and writes a trend report. Each platform’s heat is read on its own terms, so no cross-platform guesses are made.

The report ends with two or three recommended topics, written into a topic decision file with the reasons, risks and validation steps, so the author can pick a direction and move on to analysis or writing.

What You Get

  • A dated scan folder with the collected ranking files and an aggregated summary
  • A trend report with a genre heat table, new-genre signals and new character, setting and plot-device patterns
  • A topic decision file with two or three recommended topics and their risks
  • A fallback mode that works from pasted data or built-in genre knowledge, clearly labeled as unverified

Common Use Cases

  • Choosing a genre for a new Fanqie or Qidian book from current ranking samples
  • Comparing which genres are rising in new-book lists versus long-running leaders
  • Finding title and tag patterns before writing a book description

What Makes It Unique

It keeps single-book ranks as clues and only draws trend conclusions from repeated patterns across lists and books. Heat is compared inside each platform’s own metric, and without author back-end data it declines to claim retention or conversion figures. Output goes straight into a topic decision file that the analysis and writing skills read next.

Under The Hood

The skill reads one platform reference file, then runs bundled Node scripts that fetch ranking and book pages from the platform sites, some through a Chrome remote-debugging session started by the companion browser skill that reuses your logged-in browser. Another script aggregates the files. It writes the scan files and the topic decision file into your working folder. When data cannot be fetched you can paste it in, or the skill falls back to built-in knowledge and says so.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers