Does my video have to show my screen?

No. This page came from a video with no screen recording in it at all, one still image behind a talking head. The skill measures whether the screen moves before it writes, and when nothing moves it writes an explainer.

What stops it inventing things the video never said?

Two gates. Voice detection cuts the transcript at the end of real speech, because a run without it produced a fluent closing that was never spoken. Then it asks you four questions before any copy exists.

Can it publish without me watching?

No, and that is the design. It stops to confirm your publish path, stops for the video, and stops again before the deploy. The work between those points it does on its own.

Claude Code blueprint

One line turns every video you post into a live page on your own site.

You post a video. Someone asks for the written version. Any AI will give you a draft, and a draft still needs an editor, a developer and a deploy. This is the blueprint for a Claude Code skill that finishes the job: it transcribes on your own machine, asks you four questions before it drafts a word, clears your gates and ships through your deploy. The video goes in. The page comes out already live.

Watch it in under two minutesOn Instagram. The page below stands on its own if you would rather read.

Line that starts it: 1
Per video after setup: $0
Where your audio stays: Local
Questions before it writes: 4

Where this leaves you

A live page on your own site for the video you posted, at a URL you can drop straight into the comments.
Every video after it gets the same treatment. One line, one pass, and the afternoon you would have spent writing it up goes back to you.
A page that says what you said and nothing you did not. The skill asks before it decides, so the copy never asserts something the video left open.
Your type check, your lint and your build enforced on every page it ships, the same way everything else on your site ships.

Do this once

The builder reads your repository before it proposes anything. Nothing here touches your live site.

You need Claude Code on a paid Anthropic plan, the repository that publishes your site, and ffmpeg plus Python 3.10 or newer for the transcription step. The builder checks for the last two and offers to install what is missing.

01
Get Claude Code onto your machine. It is a separate product from the Claude app and from claude.ai chat, and Anthropic's documentation is blunt about the plan: the free Claude.ai plan does not include Claude Code access. You need Pro, Max, Team, Enterprise or a Console account.
curl -fsSL https://claude.ai/install.sh | bash
Windows PowerShell instead: irm https://claude.ai/install.ps1 | iex
02
Open it at the repository that publishes your site. Not a scratch folder. The builder reads your real files to work out where pages live, and it cannot do that anywhere else.
claude
Commit or stash whatever is in progress first. The builder stops on a dirty tree rather than mixing its work into yours.
03
Paste one line. That is the easy button. It points Claude Code at the builder prompt and hands over.
Read https://www.graniteai.co/prompts/video-guide-builder.md and do exactly what it says.
Open that link yourself first if you would rather read what you are pasting. It is a plain text file.
04
Answer its questions about where your pages go. It works out your framework, the directory a page lives in, whether an index needs a new entry, which branch ships to the live site, and what your gates are called. Then it stops and asks you to confirm, with its own recommendation first. This step decides where every future page lands, so give it the two minutes.
05
Let it set up transcription locally. It checks for ffmpeg and Python, tells you the model download size before it downloads anything, and lets you pick a larger or smaller model depending on whether you have a GPU. Your video never leaves your machine.
No API key and no per-minute charge. faster-whisper is an MIT-licensed reimplementation of OpenAI's open-source Whisper, and it runs on hardware you already own.
06
Hand it a real video and watch the whole run. It stops before the deploy and shows you the page locally. After that the command is yours, and every later video is the same command and the same short round of questions.

The builder never pushes to your production branch. Wiring up your deploy means writing the command into the skill, never running it. The install commands and the plan requirement above were checked against Anthropic's documentation on 1 September 2026.

The specifics

What it costs: Nothing per video beyond the Claude plan that Claude Code already requires. Transcription runs on your own hardware.
Where your audio goes: Nowhere. The video, the audio and the transcript stay on your machine.
Transcription model: faster-whisper, an MIT licensed reimplementation of the open-source Whisper model. You choose the size.
Tested on: A Next.js site, end to end. On another stack you are leaning on the confirmation step, which is why that step exists.
Where the skill lands: At .claude/skills/your-name/SKILL.md in your repository, on a branch you review before merging.
Command or skill: Same thing now. Anthropic merged custom commands into skills, and the directory name becomes the command you type.

Questions people ask

Does my video have to show my screen?
No. This page came from a video with no screen recording in it at all, one still image behind a talking head. The skill measures whether the screen moves before it writes, and when nothing moves it writes an explainer.
What stops it inventing things the video never said?
Two gates. Voice detection cuts the transcript at the end of real speech, because a run without it produced a fluent closing that was never spoken. Then it asks you four questions before any copy exists.
Can it publish without me watching?
No, and that is the design. It stops to confirm your publish path, stops for the video, and stops again before the deploy. The work between those points it does on its own.

Or hand us the video

The video guides under Tools on this site came out of the workflow this blueprint describes: a video in, one pass, a published page out. If you would rather have the output than the build, that is the part we do.

Send us the video See every tool