kivimedia

Videographer Skill — Development skill for Claude Code

Development community

Decide which video tool to use before editing.

How to install Videographer Skill

This entry records only its repository, not the path inside it, so there is no exact command to give. Open kivimedia/videographer-skill and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Videographer Skill does

Decide which video tool to use before editing. A Claude Code skill that asks 6 questions, surfaces 3 options with tradeoffs, and dispatches the right one (or runs all in parallel).

Alternatives in Development

OpenAI Codex CLI — (Rust implementation) 67.8k ★
Research Codebase — You are tasked with conducting comprehensive research across the codebase to answer user questions by spawning 10k ★
Part 1 — Deep Research Prompt Builder — I'm going to help you create a research prompt for your project 2.1k ★

README

video-orchestrator

[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE) [![Claude Code Skill](https://img.shields.io/badge/Claude%20Code-Skill-orange.svg)](https://www.claude.com/product/claude-code) [![Tools wired](https://img.shields.io/badge/tools-6-green.svg)](#which-tool-fits-what) [![Status](https://img.shields.io/badge/status-stable-brightgreen.svg)](#)

**Stop picking the wrong video tool.**

There are so many ways to edit your video, but it can be overwhelming to know which tool to choose and when. The FOMO of video editing has never been so difficult. Is this a job for revideo or remotion? For Cutsense or hyperframes? Should I use the claude skill video or maybe a pipeline with a few tools chained together?

All this FOMO ends here and now.

Introducing video-orchestrator.

It asks 3 questions, surfaces 6 tool options with real tradeoffs, and dispatches the right one. Or runs all recommended ones in parallel so you can compare side-by-side.

videographer demo: 3 questions, 6 tool options, parallel dispatch

Which tool fits what

You have...	It usually picks...
A long talking-head video	CutSense (silence/filler removal, brand captions)
A URL or website	website-to-hyperframes (page capture to animated promo)
A script and a portrait image	HeyGen or Hedra (avatar lipsync)
Many takes / raw transcript	video-use (LLM-driven cut picking)
A branded title card or outro	Remotion (pixel-perfect, fast)
Three hooks to A/B test	Fork mode (all 3 in parallel, compare)

Why this exists

Most video edits don't fail at the rendering step. They fail at the planning step. People grab the first tool they think of, render something, then realize a different tool was the better fit. Time spent re-rendering is the most expensive kind. The orchestrator pauses for thirty seconds at the start to ask, surface