ai-video-script
Generate a structured short-video shooting script from a topic. Emits a strict, machine-parseable shot list (3 shots by default) with image prompt + video prompt + voiceover + on-screen text per shot. Trigger when the user asks for a video script, 分镜, 短视频文案, AI视频, 短剧脚本, or wants visual prompts ready for image/video generation.
Profile →npx skills add opensquilla/opensquilla --skill ai-video-script --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Turns a topic/keyword + style + duration into a strict-format shooting script with a fixed shot list (3 by default, adjustable to 5) where each shot includes IMAGE_PROMPT, VIDEO_PROMPT, VOICEOVER, and ON_SCREEN_TEXT.
How it works
- Outputs a strict, machine-parseable format with blocks: OVERVIEW and SHOT_1..SHOT_N.
- For each SHOT, it provides DURATION_S, CAMERA, IMAGE_PROMPT, VIDEO_PROMPT, VOICEOVER, ON_SCREEN_TEXT. The IMAGE_PROMPT and VIDEO_PROMPT must begin with the same IDENTITY_ANCHOR text as SHOT_1. The RENDER_STYLE and IDENTITY_ANCHOR are copied from inputs unless missing (then sentinel values are used).
- It requires inputs: Topic/Story, Style, Total duration, Aspect ratio, N_SHOTS override, with.identity_anchor, with.render_style. It does not invent anchors or styles.
- VOICEOVER must appear inside VIDEO_PROMPT as a dialogue/voiceover tag according to the provided VOICEOVER rules; one of Dialogue, Voiceover, or none must be used per shot.
- The output language follows the user’s input language (Chinese or English) across all fields. It enforces no emojis and plain text only.
When to use it
- Triggered when a user asks for a video script, 分镜, 短视频文案, AI视频, 短剧脚本, or requests visual prompts for generation.
- Defaults to 3 shots but can be overridden to 4 or 5 via N_SHOTS; 1-10 is allowed.
What it can touch
- Declared tool: claude-code (for execution or prompting in workflows).
Caveats
- License: Apache-2.0. Risk: low. Do not rely on non-stated outputs; follows strictly the FIELD definitions and sentinels when inputs are missing.
# ai-video-script — structured short-video script generator Turns a topic/keyword + style + duration into a strict-format shooting script the downstream `nano-banana-pro` and `seedance-2-prompt` skills can parse without ambiguity. The default emits 3 shots; the caller may ask for 4 or 5. ## Inputs Free-text via `with.task` / `with.request`: - Topic / product / story - Target audience (optional) - Style (轻松/专业/故事/科普/带货) — narrative style, not render style - Total duration (15s, 30s, 60s default) - Aspect ratio (9:16 default, 16:9 optional) - `N_SHOTS` override (5 default, **1-10 allowed**) Caller-supplied anchors (used verbatim — this skill never invents them): - `with.render_style` — one-line aesthetic the per-shot prompts must end with. Examples: `2D anime illustration, flat colour, soft cel-shading`, `watercolour storybook illustration`, `cinematic photoreal 35mm grain`. If absent / empty, emit the literal sentinel `(render style missing)` into the RENDER_STYLE field so downstream parsers can fail loudly. - `with.identity_anchor` — one-line description of the main character(s) that every shot must reproduce byte-for-byte. Example: `Lin, a 25-year-old East Asian woman with chin-le
- Inputs
- Output format (STRICT — orchestrators parse this)
- Rules
- Style presets (only adjust IMAGEPROMPT/VIDEOPROMPT modifiers)
- Negative defaults (always add to VIDEOPROMPT)
- Example A — Chinese request, all-Chinese script (50s, 5 shots, 9:16)
- Example B — English request, all-English script (50s, 5 shots, 9:16)
- What this skill does NOT do
What does the ai-video-script skill do?
Generate a structured short-video shooting script from a topic. Emits a strict, machine-parseable shot list (3 shots by default) with image prompt + video prompt + voiceover + on-screen text per shot. Trigger when the user asks for a video script, 分镜, 短视频文案, AI视频, 短剧脚本, or wants visual prompts ready for image/video generation.
How do I install it?
Run `npx skills add opensquilla/opensquilla --skill ai-video-script --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From opensquilla/opensquilla, a repository with 6,515 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.