video-creator

Name: video-creator
Author: outscal

github.com/outscalCreative & media6940 installsUpdated 27w ago

About video-creator

A skill for managing a video workflow from script input through final video components. It supports creating, executing, regenerating selected scenes, and resuming in-progress work.

Key features

01Create videos from scripts and style choices
02Run audio, direction, asset, design, and coding steps
03Regenerate design or code for selected scenes
04Resume workflows and check progress
05Track step state with utility scripts

Use cases

01Starting a video from a script
02Running a specific production step
03Reworking design or code for selected scenes
04Continuing or checking an unfinished video

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/outscal/video-generator --skill video-creator

After installing, type/video-creatorin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

create-video.md

execute-regen-scenes-step.md

execute-video-step.md

resume-video.md

scripts/

get_video_step_metadata.py

list-topics.py

path_manager.py

validate_json.py

video-status.py

video-step-sub-status.py

steps/

assets-step.md

audio-step.md

code-step.md

design-step.md

direction-step.md

regenerate-code-step.md

regenerate-design-step.md

user-input-step.md

templates/

video-status-template.json

Details

From the project README

Video Creator Skill

Manages the complete video creation pipeline from script input to final video components.

Execution Modes

Determine which workflow to follow based on user input:

Mode 1: Execute Video Step

When: Immediately read when user wants to execute a specific workflow step (audio, direction, assets, design, or coding). Workflow: execute-video-step.md

Mode 2: Execute Regenerate Scenes Step

When: Immediately read when user wants to regenerate specific scenes for a step (design or coding) with scenes parameter. Workflow: execute-regen-scenes-step.md

Mode 3: Resume Video

When: Immediatly read when user wants to continue an existing video workflow from where it left off or check the status of an in-progress video Workflow: resume-video.md

Mode 4: Create Video

When: User wants to create a completely new video from scratch, starting with script input and style selection Workflow: create-video.md

Step References

Individual step implementations (referenced by execution modes):

user-input-step.md - Gather script and video style
audio-step.md - Generate audio from script
direction-step.md - Create video direction
assets-step.md - Generate SVG assets
design-step.md - Generate design specifications
code-step.md - Create video components
regenerate-design-step.md - Regenerate design for specific scenes
regenerate-code-step.md - Regenerate code for specific scenes

Utility Scripts

video-status.py: Manages workflow state and step progression

Available actions:

create-video-status-file: Initialize new video workflow and return first step
get-incomplete-step: Get current pending step
complete-step: Mark step done and advance to next

Output Format:

All actions output a single line

list-topics.py: Get all topics with video workflows

Usage:

python .claude/skills/video-creator/scripts/list-topics.py

When user doesn't specify a topic, use this script to get all available topics, display them to the user, and ask them to specify which topic they want to work with

Comments

Markdown supported

Details

Author: outscal
Repository: outscal/video-generator
Category: Creative & media
Installs: 40
GitHub stars: 69

Report

More skills

All skills

ai-video-generation

github.com/inference-sh

1.7M

Generate AI videos with Google Veo, Seedance 2.0, HappyHorse, Wan, Grok and 40+ models via inference.sh CLI. Models: Veo 3.1, Seedance 2.0, HappyHorse 1.0, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo. Capabilities: text-to-video, image-to-video, reference-to-video, video editing, lipsync, avatar animation, video upscaling, foley sound. Use for: social media videos, marketing content, explainer videos, product demos, AI avatars. Triggers: video generation, ai video, text to video, image to video, veo, animate image, video from image, ai animation, video generator, generate video, t2v, i2v, ai video maker, create video with ai, runway alternative, pika alternative, sora alternative, kling alternative, seedance, happyhorse

ai-image-generation

github.com/inference-sh

1.7M

Generate AI images with GPT-Image-2.5, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2.5 Flare, GPT-Image-2.5 Sunburst, GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to image, stable diffusion, generate image, ai art, midjourney alternative, dall-e alternative, text2img, t2i, image generator, ai picture, create image with ai, generative ai, ai illustration, grok image, gemini image, gpt image, openai image, chatgpt image

ai-avatar-video

github.com/inference-sh

1.7M

Create AI avatar and talking head videos via inference.sh CLI. Recommended: P-Video-Avatar (fastest, cheapest, built-in TTS). Also: OmniHuman, Fabric, PixVerse. Audio: Inworld TTS-2 (100+ languages, emotion steering for characters), ElevenLabs, Kokoro. Capabilities: audio-driven avatars, text-to-avatar, lipsync videos, talking head generation, virtual presenters, UGC content. Use for: AI presenters, explainer videos, virtual influencers, dubbing, marketing videos, UGC ads, gaming avatars, NPC dialogue. Triggers: ai avatar, talking head, lipsync, avatar video, virtual presenter, ai spokesperson, audio driven video, heygen alternative, synthesia alternative, talking avatar, lip sync, video avatar, ai presenter, digital human, ugc, ugc video, ugc ad, avatar ugc

remotion-render

github.com/inference-sh

1.6M

Render videos from React/Remotion component code via inference.sh. Pass TSX code, get MP4. Supports all Remotion APIs: useCurrentFrame, useVideoConfig, spring, interpolate, AbsoluteFill, Sequence. Configurable resolution, FPS, duration, codec. Use for: programmatic video generation, animated graphics, motion design, data-driven videos, React animations to video. Triggers: remotion, render video from code, tsx to video, react video, programmatic video, remotion render, code to video, animated video, motion graphics code, react animation video