skilld
All skills
oaustegard avatar

/creating-video

@4b31e7d
by Oskar Austegardoaustegard/claude-skills150 stars
6

Create video from prompts by overseeing multi-clip AI generation end to end: write a shot list, generate each scene with Gemini Omni Flash (via the Cloudflare AI Gateway), review the results, and assemble them into a finished cut. Use when the user asks to make/generate a video, a short film, an animatic, or a multi-scene clip from a script or idea; when they mention Omni, Veo, text-to-video, or image-to-video; or when acting as the editing/director agent over generated footage. Triggers on 'make a video', 'generate a clip', 'short film', 'video from this script', 'turn this into a video', 'omni', 'veo', 'text to video', 'storyboard to video'. For transcoding/trimming/merging/GIF/subtitles use processing-video; for reading or summarizing existing video content use parsing-video.

Ask your Agent

Use this Skill: https://skilld.dev/gh/oaustegard/claude-skills/creating-video

This session only. Nothing lands on disk.

CHANGELOG.md

≈215 tokens on demand. Your agent reads this file only when SKILL.md points to it.

creating-video - Changelog

All notable changes to the creating-video skill are documented in this file. The format is based on Keep a Changelog.

[0.2.1] - 2026-07-22

Fixed

  • --keep-audio was a no-op — port audio crossfade from the stale branch (#742)

[0.2.1] - 2026-07-21

Fixed

  • assemble.py: --keep-audio was a no-op — trimmed clips kept audio but the stitch stage mapped only video, so the flag silently produced a silent film. Adds the acrossfade chain, afade out, and explicit [k:v]/[k:a] stream specifiers; pads the held tail with apad so A/V stay equal length.

[0.2.0] - 2026-07-21

Other

  • creating-video: default to Gemini Omni Flash (#739)

[0.1.0] - 2026-07-18

Other

  • Add creating-video skill; extend parsing-video for editing review (#735)

Source: SKILL.md on GitHub

Third-party checks

2 warnings2mo3 checks · Risk MEDIUM
  • Gen Agent Trust Hub2mo

    The skill facilitates video generation and assembly via external AI services. It includes scripts that dynamically install dependencies at runtime and execute shell commands for media processing.

  • Socket2mo

    1 alert: gptAnomaly

  • Snyk2mo

    Risk: LOW · No issues

Provenance

Signed by skilld at 4b31e7d. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 2 months ago

Capability

metadata
{
  "version": "0.2.1"
}

README badge

README badge for oaustegard/claude-skills/creating-video