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

Long-Form Source Novel Analysis (for Vertical Short Drama)

A read-only pipeline that turns a long novel or serialized web fiction into a traceable analysis layer: chapter index, adaptation-value triage, per-chapter function extraction, and episode candidates.

Content & WritingIntermediate★ 1,943⑂ 448AI score 9/10Last updated: Sep 15, 2026

What it does

  • S0 – Chapter index: runs novel_index.py to derive chapter boundaries and flag problems (number gaps, duplicates within a volume, near-empty chapters, table-of-contents residue). This index becomes the single source of truth for every later stage's spans.
  • S1 – Adaptation triage: deterministic sampling (first and last chapters always included) produces a six-point triage.md, then pauses to ask the creator whether a full breakdown is worth the cost.
  • S2–S4 – Full breakdown: per-chapter dramatic-function extraction (batched sub-agents or serial), aggregation into story units plus rhythm/emotion curves, then character merging (alias normalization, tiering) and world/faction rules.
  • S5 – Adaptation value and episode candidates: separates what plays directly on a vertical screen, what needs a different vehicle, and what is prose-only pleasure (interior monologue, unreliable narration, long setups); outputs episode-candidates.jsonl cut by local dramatic outcomes rather than chapter counts, and backfills which triage guesses were falsified.
  • Guardrails: no advancing past coverage gates, skipped chapters must be recorded not hidden, no verbatim prose copied into analysis, input folder stays read-only.

Who it's for

  • Producers and development editors adapting web novel IP into vertical short dramas
  • Story analysts who repeatedly write source-material evaluation reports
  • Teams triaging hundreds or thousands of serialized chapters before committing reading time
  • Users of the $short-drama skill suite running develop → write → assets pipelines

Example uses

  1. "Import this novel and analyze it" with a file path → builds the chapter index, samples ~12 chapters, reports estimated effort for the full pass, and asks whether to continue.
  2. "Can this book work as a short drama?" → stops after S1 with triage.md covering story frame, screen-ready vs prose-only ratios, opening replacement point, production burden, top three adaptation risks, and likely episode count.
  3. "Split this long book into episode candidates" → full run delivering story-units.md, rhythm-and-emotion.md, characters.md, and episode-candidates.jsonl with source spans and open questions, handed off to $short-drama-develop.

· · · 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/drama-skills/HEAD/skills/short-drama-novel-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/short-drama-novel-analyze folder from the GitHub repo zenstory-ai/drama-skills into my ~/.claude/skills/short-drama-novel-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/drama-skills.git && mkdir -p ~/.claude/skills && cp -r drama-skills/skills/short-drama-novel-analyze ~/.claude/skills/

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

  1. Open a terminal and clone the repository: git clone https://github.com/zenstory-ai/drama-skills.git
  2. Copy the skill into your Claude Code skills folder: mkdir -p ~/.claude/skills && cp -r drama-skills/skills/short-drama-novel-analyze ~/.claude/skills/
  3. Confirm Python 3 is available with python3 --version (required by the indexing script).
  4. Run the bundled self-test: python3 ~/.claude/skills/short-drama-novel-analyze/scripts/selftest.py
  5. Create a working folder and place your manuscript .txt in the read-only input directory (originals are never modified).
  6. Start Claude Code and ask with an explicit path, e.g. "Analyze the novel at input/novel.txt".
  7. When the skill pauses after the S1 triage, approve or decline the full breakdown, then review the outputs under source-analysis/.
View source on GitHub ↗License: MIT