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.