Reads the screen, not the transcript

Feed it a video.
Get a skill it can run.

skillcast turns a tutorial screencast into a skill your coding agent loads and executes — with the exact commands that were on screen.

The narration

“…and now we'll add the test runner and the testing library.”

The screen

npm install -D vitest @testing-library/react

Only one of those runs. Every video-to-text tool reaches for the transcript — the half that loses the executable truth. skillcast reads the screen.

Live

Try it now

Runs entirely in your browser with tesseract.js. Your video is never uploaded, because there is no server to upload it to.

Drop a screen recording mp4, webm or mov — or click to choose
or paste a link

or

starting…

How well it holds up

Measured against a fixture whose contents are known exactly, degraded on purpose. Recall is exact-match, not similarity.

720p terminal, large type5/5
Re-encoded at 360p, crf 305/5
Heavy noise added5/5
IDE-style, 22px type amid code4/5
IDE-style, 16px type amid code4/5
IDE-style, 13px type2/5
IDE-style, 11px type1/5

Compression barely matters. Type size does.

Below roughly 16px the OCR starts dropping commands, and no threshold rescues it — so that limit is published rather than left to be discovered.

If you control the recording: shoot at 1080p and raise the terminal font.

Install the real thing

The demo is the same logic, ported. The CLI is faster, handles long recordings, and writes the files where your agent already looks.

pip install git+https://github.com/obeskay/skillcast
brew install ffmpeg tesseract     # or: apt install ffmpeg tesseract-ocr

skillcast tutorial.mp4

No API key. No model download. Fully offline.