# AI Short Drama Director

> Orchestrate an end-to-end AI short-film and short-drama production workflow from script review and shootability optimization through character look development, Segment-based shot planning, professional storyboard execution tables in XLSX and HTML, element image generation, storyboard grids, Seedance-ready prompts, and per-Segment asset packages. Use when Codex needs to turn a Chinese-language script into an AI-video production package, continue a partially completed short-drama project, audit production artifacts, or generate GPT Image 2 visual assets and independent Seedance prompts for 15-second-or-shorter Segments.

- Skill: `niandunye-create/ai-short-drama-director` (Agent Skill, multi-file: 15 files)
- Install (CLI): `npx skillmds@latest add niandunye-create/ai-short-drama-director`
- Raw SKILL.md: https://api.skillmd.com/api/skills/niandunye-create/ai-short-drama-director/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Web & Frontend
- Author: niandunye-create (https://skillmd.com/u/niandunye-create)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/niandunye-create/ai-short-drama-director

---


# AI Short Drama Director

## Overview

Run a staged AI short-drama production pipeline. Preserve the story while turning it into stable, reviewable artifacts for GPT Image 2 and Seedance generation.

## Start Every Project

1. Read [references/00-workflow.md](references/00-workflow.md).
2. Inspect the project folder before generating anything. Reuse existing scripts, character images, scene images, prop images, effect images, plans, and Segment packages.
3. If the project has not been initialized, run:

```bash
python3 scripts/init_project.py <project-folder> --episode 第一集 --mode confirm-each
```

4. Ask the user to choose one execution mode:
   - `confirm-each`: pause after every stage and offer both `确认后继续` and `从这里自动完成`.
   - `auto-from-current`: lock accepted artifacts and finish all remaining stages automatically.
5. Even in automatic mode, pause on any hard-stop condition defined in [references/00-workflow.md](references/00-workflow.md).

## Run the Pipeline

Execute stages in order. Resume from the first incomplete stage when artifacts already exist.

| Stage | Name | Read before executing | Required output |
| --- | --- | --- | --- |
| `01` | Script review | [references/01-script-preprocess.md](references/01-script-preprocess.md) | Shootability diagnosis and optimization strategy |
| `02` | Director-ready script | [references/01-script-preprocess.md](references/01-script-preprocess.md) | Engineering-enhanced script |
| `03` | Character look development | [references/04-visual-assets.md](references/04-visual-assets.md) | Approved identity sheets and expression sheets |
| `04` | Internal shot planning | [references/02-shot-planning.md](references/02-shot-planning.md) | Scene, Segment, duration, continuity, and shot design |
| `05` | Execution plan table | [references/03-plan-table.md](references/03-plan-table.md), [references/07-sd-vertical-v2-1.md](references/07-sd-vertical-v2-1.md) | `.xlsx` table and HTML preview with new and legacy AI prompt columns |
| `06` | Element images | [references/04-visual-assets.md](references/04-visual-assets.md) | Reused or generated scene, prop, and effect assets |
| `07` | Storyboard grids | [references/05-storyboards.md](references/05-storyboards.md) | One labeled storyboard grid per Segment |
| `08` | Seedance prompts | [references/06-seedance-delivery.md](references/06-seedance-delivery.md) | One independent Markdown prompt per Segment |
| `09` | Segment packages | [references/06-seedance-delivery.md](references/06-seedance-delivery.md) | Prompt, numbered assets, and mapping manifest per Segment |

## Apply Global Rules

- Preserve plot direction, character relationships, scene settings, key props, and every original spoken-text string.
- Treat dialogue, inner monologue, voice-over, narration, and authored subtitles as immutable source text. Preserve their wording, pronouns, sentence order, punctuation, repetitions, hesitations, and code-switching verbatim unless the user explicitly authorizes a rewrite.
- Add visible performance detail, spatial clarity, and camera logic. Do not add major events, reversals, relationships, or character-changing behavior.
- When generating Seedance prompts or prompt columns, enforce the director reasoning gate in [references/06-seedance-delivery.md](references/06-seedance-delivery.md). Do not create final prompts by template filling, row-field paraphrase, keyword expansion, or unattended batch scripting. Each final prompt must be reasoned from the source script beat, a fixed scene floor plan, shot-appropriate camera design, visible screen composition, character intention, and dramatic purpose.
- Limit each Segment to at most `15` seconds. Permit a shorter final Segment at the end of a scene. Start every new scene in a new Segment.
- Keep shot-to-shot and Segment-to-Segment continuity explicit. End Segments on stable framing or completed action whenever possible.
- Use concrete names instead of ambiguous Chinese pronouns in action descriptions, blocking, asset mappings, and other production instructions. Never apply this rule inside dialogue, inner monologue, voice-over, narration, or authored subtitles.
- Prefer existing visual assets. Generate only missing identities, missing views, or missing execution-critical details.
- Use GPT Image 2 for generated visual assets. If GPT Image 2 is unavailable, pause and tell the user; do not silently substitute another model.
- When creating spreadsheet outputs, use the available spreadsheet capability and deliver both `.xlsx` and HTML.
- Auto-select the strongest visual candidate in automatic mode and keep rejected candidates in `淘汰图/` for review.

## Validate and Package

Before delivery:

1. Before accepting Stage `02`, run the dialogue fidelity check against the original source and the director-ready script:

```bash
python3 scripts/check_dialogue_fidelity.py <original-script> <director-ready-script>
```

Stop and restore the original wording if this check reports any missing or changed spoken text. Do not continue downstream with a failed Stage `02`.

2. Verify that the XLSX and HTML tables represent the same rows and required columns.
3. Run prompt checks:

```bash
python3 scripts/check_segment_prompts.py <project-folder>/06-Seedance提示词
```

4. Create each Segment package from a JSON manifest:

```bash
python3 scripts/package_segment.py <manifest.json> <project-folder>/07-Segment素材包
```

5. Check that asset order matches `@Image1`, `@Image2`, and subsequent references in that Segment prompt.
6. Report reused assets, generated assets, automatically selected images, rejected images, prompt-length warnings, and any unresolved hard stops.

## Use Resources Selectively

- Read only the reference file needed for the current stage.
- Use `scripts/init_project.py` to create a predictable project structure and workflow state.
- Use `scripts/check_dialogue_fidelity.py` to block any unauthorized spoken-text rewrite at Stage `02`.
- Use `scripts/check_segment_prompts.py` to enforce prompt independence and delivery constraints.
- Use `scripts/package_segment.py` to copy and rename Segment assets deterministically.

