Short-Drama Image Prompt Writer
Writes and revises copy-ready image prompts for short-drama characters, looks, locations, props and state variants in a standardized Markdown sheet.
Image & VideoIntermediate★ 1,822⑂ 438AI score 7/10Last updated: Sep 12, 2026
What it does
It turns your established visual facts into reusable, copy-ready image prompts stored in 剧集/<EP>/图片提示词.md:
- Every entry gets a stable
IMG-...heading; the prompt body lives in a### 可复制提示词quote block so it can be pasted straight into an image model. - Fixed prompt order: subject & identity anchors → current variant → composition/angle → light, color, material → background boundary → prohibitions.
- Each reference image (
REF-...) must declare exactly what it controls — identity, look, geography, composition or style. - Visible text, logos, watermarks, UI and subtitles are always explicitly allowed or forbidden; no placeholders, file paths or QA notes leak into the prompt body.
- Covers identity plates, look/state variants, location plates, prop plates, multi-subject production sheets, Lookdev comparison frames and localized edit prompts with preserve sets.
- It never generates images and calls no vendor API — actual rendering is handed off to
$short-drama-producewith explicit confirmation.
Who it's for
- Short-form drama / web-series creators doing AI-assisted visual pre-production
- Teams that must keep character appearance and locations consistent across episodes and shots
- Existing users of the
zenstory-ai/drama-skillspipeline
Examples
$short-drama-image-prompts write copy-ready prompts for all confirmed characters, locations and props in EP001- Produce three state variants of the lead (daily outfit / rain-soaked / wedding dress) sharing the same identity anchors
- Promote an accepted storyboard end keyframe into a standalone
IMG-...state entry to serve as the render source
· · · 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-image-prompts/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.
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-image-prompts folder from the GitHub repo zenstory-ai/drama-skills into my ~/.claude/skills/short-drama-image-prompts/. 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-image-prompts ~/.claude/skills/⚠ This is a third-party skill. Check the source repository before installing.
- Open a terminal.
- Clone the repo:
git clone https://github.com/zenstory-ai/drama-skills.git - Create the skills folder:
mkdir -p ~/.claude/skills - Copy the skill:
cp -r drama-skills/skills/short-drama-image-prompts ~/.claude/skills/ - (Optional) Copy sibling skills such as
short-dramaandshort-drama-produceso the full pipeline works. - (Optional) Verify the install:
cd ~/.claude/skills/short-drama-image-prompts && python3 scripts/selftest.py - Restart Claude Code and invoke it with
$short-drama-image-prompts.
View source on GitHub ↗License: MIT