Skip to content
SkillScript-led3,400 tokens in use

story-long-analyze

Breaks a long web novel into golden-chapter notes, chapter summaries, plot lines, pacing, emotion, characters, settings and a style profile.

8,793 stars on the repository MIT Licensezenstory-ai/oh-story-claudecode · skills/story-long-analyze
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-analyze costs

206tokens idle
3,400tokens in use
39,978tokens, 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/build_chapter_index.py, scripts/inspect_existing_assets.py, scripts/inspiration_index.py, scripts/manage_analysis_run.py, scripts/render_relation_chart.py.

Touches

shelldetectedwrites 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 →
Fair
  • Frontmatter8/15
  • Structure16/25
  • Examples9/15
  • Output0/15
  • Size13/15
  • Resources10/15

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 →
Good
  • Writes files−8

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

    scripts/build_chapter_index.py, line 71
  • Hidden characters−20

    characters that render as nothing or reorder the text

    scripts/inspiration_index.py, line 80
  • Runs shell commands−5

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

    scripts/render_relation_chart.py, line 249

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-analyze is a structured teardown of a long web novel. It indexes the chapters, deep-reads the first three, then extracts per-chapter summaries in batches and builds plot, pacing, emotion, character, setting and style files, plus a final report written for the author.

It resumes from saved progress and reuses earlier results, so an interrupted analysis continues where it stopped. It only moves abstract mechanisms across to your own book and does not copy settings, event chains or sentences.

What You Get

  • A full report, an overview and a quick preview of the analyzed book
  • Deep breakdowns of chapters one to three and a summary for every chapter
  • Plot lines, pacing and emotion modules, character and setting files, and relationship charts
  • A style profile file that later writing skills can use
  • Progress and cache files so a long analysis can be resumed

Common Use Cases

  • Studying why a benchmark novel hooks readers in its first three chapters
  • Building a reusable analysis library before outlining your own long novel
  • Extracting pacing and emotion patterns from a hit book to plan your own chapters

What Makes It Unique

It treats analysis as a staged pipeline with saved state: each chapter block is read once, facts are anchored to chapter locators, and the final report is written in author-friendly language with the internal field names kept out of it. It separates events, reader emotion and page space, and it checks existing results before doing any work, so earlier analyses are reused and never overwritten.

Under The Hood

The skill loads one reference file per stage, as that stage begins. It runs bundled Python scripts locally to build the chapter index, inspect existing results, manage analysis runs, render relationship charts and index the inspiration library. It reads the novel text you supply, may dispatch sub-agents for batches, and writes many files into a book analysis folder. It does not call web services itself.

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