Short Drama Reference Breakdown

Breaks down benchmark short dramas into measurable numbers and compares them with your own plan or cut using the same ruler.

Image & VideoIntermediate★ 3,784⑂ 681AI score 9/10Last updated: Nov 4, 2026

What it does

Takes a reference short drama's video/subtitles and measures episode length, shot length, dialogue density, opening, episode endings, and next-episode hooks.
Uses the bundled breakdown_tool.py to measure durations, detect cuts, build representative-frame contact sheets, attach SRT transcripts to the timeline, and aggregate per series.
Distills recurring patterns into transferable "mechanism candidates": audience state, dramatic problem, visible effect, applicable conditions, failure boundaries, and what must not be copied.
Measures your own script/storyboard/cut with the same tool to produce a gap table, confirms with the creator whether each gap is intentional, then routes fixes to the responsible sibling skill.
Includes a render-verification loop: generate before/after versions of a representative scene and re-measure blindly.

Who it's for

Creators of vertical short dramas or webtoon-based animated series who want structured competitor analysis.
Writers/directors who need data instead of gut feel to argue that "the pacing drags".
Teams building a pipeline with $short-drama-develop and $short-drama-produce.

Example uses

"Break this series down" → assign a REF-ID, sample episodes 1–3, measure shot-length distribution and the first-3-minute opening structure.
"Why does our episode 1 lose viewers?" → measure the benchmark opening alongside yours and surface the information-density gap in the first 15 seconds.
"Where does our fight scene lag?" → compare average shot lengths, then after edits generate before/after takes and re-measure with the same metrics.

· · · 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-breakdown/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)

Download the ZIP with the button below.
In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
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 AI Skill Mart.
Copy the skills/short-drama-breakdown folder from the GitHub repo zenstory-ai/drama-skills into my ~/.claude/skills/short-drama-breakdown/.
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-breakdown ~/.claude/skills/

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

Verify ffmpeg is available: run ffmpeg -version and ffprobe -version (install with brew install ffmpeg on macOS or sudo apt install ffmpeg on Ubuntu).
Clone the repository: git clone https://github.com/zenstory-ai/drama-skills.git
Copy the skill into your Claude skills folder: mkdir -p ~/.claude/skills && cp -r drama-skills/skills/short-drama-breakdown ~/.claude/skills/
Run the self-test: python3 ~/.claude/skills/short-drama-breakdown/scripts/selftest.py
Restart Claude Code and try a prompt like "break down this short drama" to confirm the skill triggers.
Place the reference video/subtitle files in a per-reference input folder (e.g. 输入/对标/<REF-ID>/) and keep them out of any published deliverables.

View source on GitHub ↗License: MIT