Video Code Reviewer

For pull requests (PR) & repos

Turn pull requests and repositories into narrated video code reviews, without leaving your AI. Give it code, a diff, or context from your repository, and Video Code Reviewer turns it into a walkthrough in your language — with voiceover, highlighted code, before-and-after comparisons, diagrams and animations.

What you can ask

Walk me through the changes in this pull request.
·

MCP connector

Server URL: https://scrimba.com/explain/chatgpt/code/mcp
Login: None
Protocol: MCP 2025-11-25
Instructions: Scrimba Code creates narrated code reviews, PR and feature explanations, and step-by-step app walkthroughs with uploaded screenshots.
For one focused explainer, use / / . Scrimba renders the explainer markup you push live. Use these tools for narrated code and feature walkthroughs, uploaded screenshots, side-by-side before/after code diffs, Mermaid diagrams of code flows, and Manim animations.
Check that you have the source material needed for the request. Read supplied code, diffs, links, and screenshots with your available tools. If essential source or screenshots remain inaccessible, ask the user for the missing material and wait before starting. Never invent code, findings, or screens.
When the material is sufficient, start immediately. Use the audience and level of detail the user requested; do not ask optional questions that delay the video.
The flow: initializes the stream and gives you a stream_token plus the explainer markup contract — no link yet. Your first successful returns the explainer's link; that first append is the viewer's playback buffer, not a handshake for the link — give it a real opening section, never just a title slide. When the link arrives, send it to the user as a non-blocking progress update and continue appending immediately, without waiting for a reply — they open it to watch the explainer get built live. The streaming and tokens are internal mechanics for YOU — don't narrate them to the user; just say you're creating their Scrimba explainer.
The second you call you will be given a full description of the streaming format that you can use to send in stream chunks. That result is large — more than 50KB, mostly the explainer markup contract — so if your client stores or truncates large tool results, use any storage or file tools you have to extract the result in full and read it to the end before pushing.

Tools

Changes data4

Skills

1 in the ChatGPT listing

Screenshots

MCP connector

Server URL

https://scrimba.com/explain/chatgpt/code/mcp

None

Protocol

MCP 2025-11-25

Instructions

Scrimba Code creates narrated code reviews, PR and feature explanations, and step-by-step app walkthroughs with uploaded screenshots.

For one focused explainer, use / / . Scrimba renders the explainer markup you push live. Use these tools for narrated code and feature walkthroughs, uploaded screenshots, side-by-side before/after code diffs, Mermaid diagrams of code flows, and Manim animations.

Check that you have the source material needed for the request. Read supplied code, diffs, links, and screenshots with your available tools. If essential source or screenshots remain inaccessible, ask the user for the missing material and wait before starting. Never invent code, findings, or screens.

When the material is sufficient, start immediately. Use the audience and level of detail the user requested; do not ask optional questions that delay the video.

The flow: initializes the stream and gives you a stream_token plus the explainer markup contract — no link yet. Your first successful returns the explainer's link; that first append is the viewer's playback buffer, not a handshake for the link — give it a real opening section, never just a title slide. When the link arrives, send it to the user as a non-blocking progress update and continue appending immediately, without waiting for a reply — they open it to watch the explainer get built live. The streaming and tokens are internal mechanics for YOU — don't narrate them to the user; just say you're creating their Scrimba explainer.

The second you call you will be given a full description of the streaming format that you can use to send in stream chunks. That result is large — more than 50KB, mostly the explainer markup contract — so if your client stores or truncates large tool results, use any storage or file tools you have to extract the result in full and read it to the end before pushing.