Story long analyze: deep structural breakdown of long Chinese web novels
A 7-stage pipeline (index → golden chapters → batched extraction → plot/rhythm → characters → report → style) that deconstructs long web novels into per-chapter facts and reusable story mechanics
- What
- A 7-stage pipeline (index → golden chapters → batched extraction → plot/rhythm → characters → report → style) that deconstructs long web novels into per-chapter facts and reusable story mechanics
- Cost
- Free
- Needs
- the novel text file to analyze (or an existing analysis to reuse/enhance); Python 3 for the pipeline scripts; an agent runtime that can spawn subagents for the batched extraction stages (falls back to solo mode otherwise); expect heavy token use on full-novel runs
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — @zenstory-ai's deep novel-deconstruction skill: it turns a long web novel into per-chapter facts, plot units, character profiles, pacing analyses and a reusable style profile, through a staged pipeline — Stage 0 mechanical chapter index (with sha256 checksums and re-run guards), Stage 1 "golden three chapters" deep dive, Stage 2 batched chapter extraction (subagents, 3 batches per round, resume support), Stage 3 plot, dual timelines and 3D rhythm, Stage 4 characters, settings and relationship graphs, Stage 5 master report, Stage 6 style profile — plus an optional three-layer inspiration library pipeline (per-book atoms, cross-book aggregation, controlled-tag library updates). Hard analysis boundaries: only conclude from readable text ("unknown" when missing), attach chapter locators to hard facts, separate objective event order from reader knowledge, never migrate proprietary settings or copy iconic scenes — migrate abstract mechanics only. Author-facing outputs (快速预览.md, 拆文报告.md, character graphs) are written in plain language, free of script names, field names or internal filenames, with resume/checkpoint support via `_progress.md` and state scripts (`manage_analysis_run.py`). Honest caveats: **the skill is written in Chinese and targets Chinese web-fiction workflows** (chapter naming, story mechanics and the companion `story-long-scan` skill assume that tradition); a full-novel run is a long multi-stage operation — expect heavy token use and unattended batch runs. MIT-licensed. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Install
Prerequisites: the novel text file to analyze (or an existing analysis to reuse/enhance); Python 3 for the pipeline scripts; an agent runtime that can spawn subagents for the batched extraction stages (falls back to solo mode otherwise); expect heavy token use on full-novel runs Install "Story long analyze: deep structural breakdown of long Chinese web novels" for me. It gives my agent @zenstory-ai's 7-stage novel-deconstruction pipeline: Stage 0 mechanical chapter index, Stage 1 "golden three chapters" deep dive, Stage 2 batched chapter extraction via subagents (3 batches per round, resume support), Stage 3 plot/dual-timelines/3D rhythm, Stage 4 characters/settings/relationship graphs, Stage 5 master report, Stage 6 style profile — plus an optional inspiration-library pipeline, hard analysis boundaries (unknown when missing, chapter locators, abstract-mechanics-only migration), author-facing plain-language outputs, and resume support. Written in Chinese; targets Chinese web fiction. MIT-licensed. Repository: https://github.com/zenstory-ai/oh-story-claudecode/blob/main/skills/story-long-analyze/SKILL.md 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder and summarize what it does in one or two sentences. 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "story-long-analyze". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. point the agent at your novel text file or existing analysis directory, then ask it to run the pipeline stages). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.