Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

Long-Form Novel Deconstruction (story-long-analyze)

A staged pipeline that deconstructs a full-length web novel into golden-three-chapter analysis, plot/emotion/rhythm modules, character and setting files, and a style profile.

Content & WritingAdvanced★ 7,438⑂ 1,067AI score 9/10Last updated: Oct 10, 2026

What it does

  • Builds a mechanical chapter index (chapter_index.csv) from your raw manuscript, then reads the text once in non-overlapping contiguous chapter blocks to accumulate per-chapter summaries.
  • Produces a deep deconstruction of the opening golden three chapters plus an author-friendly quick-preview document first, before committing to the full run.
  • Runs Stage 0–6: plot units and storyline, three-dimensional rhythm (information progression / reader emotion / page allocation), emotion modules, character profiles and relationship charts, world settings, style profile, and a final master report.
  • Tracks stage state in _progress.md, so runs are resumable across sessions; already-analyzed projects are reused instead of re-read.
  • Optional three-layer "inspiration library" pipeline for extracting atomic ideas and aggregating them across multiple books.

Who it's for

  • Web-novel and long-form fiction authors who want to learn structure by dissecting successful titles.
  • Editors and story planners who need a quantified read on a reference book's hook and pacing.
  • Writing teams facing hundreds of chapters that nobody can realistically read end to end.

Examples

  1. Give it a manuscript path and say "deconstruct this book" → chapter index → golden-three-chapter deep dive + quick preview → it pauses and asks whether to continue.
  2. Ask for "just analyze the golden three chapters" to focus on hooks, information reveal order, and emotional design in the opening.
  3. On a project that already has all chapter summaries, ask to "redo the style profile" → only Stage 6 runs and regenerates the style file.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/zenstory-ai/oh-story-claudecode/HEAD/skills/story-long-analyze/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/story-long-analyze folder from the GitHub repo zenstory-ai/oh-story-claudecode into my ~/.claude/skills/story-long-analyze/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/zenstory-ai/oh-story-claudecode.git && mkdir -p ~/.claude/skills && cp -r oh-story-claudecode/skills/story-long-analyze ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal and clone the repo: git clone https://github.com/zenstory-ai/oh-story-claudecode.git
  2. Copy the skill into your Claude Code skills folder: mkdir -p ~/.claude/skills && cp -r oh-story-claudecode/skills/story-long-analyze ~/.claude/skills/
  3. This skill relies on companion sub-agents and Python scripts, so copy the repo's other skills too — especially story-setup.
  4. Verify Python 3 is available: python3 --version
  5. Start Claude Code inside your project folder and run /story-setup first to deploy the agent bundle.
  6. Place the manuscript at a path like 拆文库/{book name}/原文/原文.txt (UTF-8 text, LF line endings).
  7. Invoke /story-long-analyze, or just say "deconstruct this book" with the file path. If a run is interrupted, invoke it again in the same folder to resume.
View source on GitHub ↗License: MIT