What is create-video?

A workflow for creating videos, animations, clips, and motion graphics with video-generation models. It helps turn an idea into a detailed prompt, plan longer sequences, include audio, and preview still frames.

Use it to create short video clips, animate images, plan multi-shot sequences, generate product videos, or replace generated audio with a separate audio pipeline.

It reduces the guesswork in describing shots and helps avoid spending generation time on an unclear sequence.

create-video — Skill for Claude Code by juliandickie

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add juliandickie/creators-studio --skill create-video

Clone the repo

git clone --depth 1 https://github.com/juliandickie/creators-studio

Made for: Claude Code.

Or install creators-studio, the plugin that ships this one along with the rest of its 3 skills, 2 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/juliandickie/creators-studio/create-video.svg)](https://agentmods.dev/skills/juliandickie/creators-studio/create-video)

Your own site

<a href="https://agentmods.dev/skills/juliandickie/creators-studio/create-video"><img src="https://agentmods.dev/badge/skills/juliandickie/creators-studio/create-video.svg" alt="Measured on agentmods" height="20"></a>

Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 5,829 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00056	$0.05829
Opus 5	$0.00028	$0.02915
Sonnet 5	$0.00011	$0.01166
Haiku 4.5	$0.00006	$0.00583

Measured 7d ago against content hash a9e312e88c20, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

create-video scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

The scan reads SKILL.md. This mod also ships 6 executable files (scripts/audio_pipeline.py, scripts/video_extend.py, scripts/video_generate.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/create-video/SKILL.md · 297 lines

How it starts

The opening of the file, as written. The whole thing — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Creators Studio -- Video Creative Director

Core Principles

Creative Director for Video -- NEVER pass raw user text to the video model. Interpret intent, enhance with cinematic language, and construct an optimized video prompt.
Audio is Always Part of the Prompt -- Both Kling v3 Std (default as of v3.8.0) and VEO 3.1 generate synchronized audio. Every prompt should include dialogue (in quotes), SFX (prefix "SFX:"), or ambient sound descriptions. Kling audio works best in English and Chinese per the model card - for other languages, consider generating without audio and using the audio_pipeline.py replacement path.
Clip Length Thinking -- Kling supports 3-15 second single-call clips; VEO supports {4, 6, 8}. For sequences beyond 15 seconds, use video_sequence.py with independent shot calls stitched by FFmpeg.
Storyboard Before Generating -- For sequences, generate still frame previews first. Video generation is expensive even on Kling ($0.16/8s; VEO Standard is $3.20/8s). Preview with images ($0.08/frame) before committing.
Image-to-Video & Character Consistency -- Animate existing assets from /create-image for visual consistency. Both Kling and VEO support start_image; Kling also supports end_image for first-and-last-frame interpolation. For multi-clip character consistency (v3.8.2+): pass the same reference image as --first-frame on every Kling call AND write each prompt to describe the SAME character as the image (matching age, hair, clothing, setting). Mismatched prompts will override the start image's identity within 5 seconds. Works for human and non-human characters. See references/kling-models.md §Character Consistency. Caveat: when passing a start image to Kling, the aspect_ratio parameter is IGNORED - output uses the start image's native aspect ratio per the Kling model card.

Read the full file on GitHub · 297 lines

Files

What ships with it

16 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

7d ago First seen · 297 lines · 56 tokens per session scan A a9e312e88c20

Subscribe to this mod's changes

create-video is a skill published in the GitHub repository juliandickie/creators-studio (2 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 5,829 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude Code Creative and media ai-image-generation ai-video-generation claude-code-plugin creative-director generative-ai

wavespeed

Generate or edit AI media (image, video, audio, 3D) by calling the wavespeed CLI on the user's machine. Use whenever the user asks to create, edit, animate, upscale, or transform a visual asset, generate audio/TTS/music, or produce marketing creatives. Every model on the WaveSpeed platform is one wavespeed run call.

WaveSpeedAI/wavespeed-cli · 79 tokens

create-video

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Creators Studio -- Video Creative Director

Core Principles

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

wavespeed

1688-ecommerce-image-generation-editing

1688-ecommerce-video-generation-editing

ai-model-expert-1688-ecommerce-image-generation-editing

ai-model-expert-1688-ecommerce-video-generation-editing

ai-model-expert-ai-ad-video