Developer Tools

Video Code Reviewer

by Scrimba AS

Overview

Turn pull requests and repositories into narrated video code reviews, without leaving ChatGPT. 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. See what changed, understand why it matters, and share the explanation with your team. How you can use Video Code Reviewer: - Walk through a pull request (PR) before reviewing or merging - Explain a feature or PR to a non-technical audience - Walk through an app step by step with your own screenshots - Explain a bug, its impact, and a proposed fix - Onboard developers to an unfamiliar repo - Show how your app’s architecture and data flow work - Animate an algorithm step by step - Compare approaches when planning a refactor - Turn code review findings into a video your team can watch Paste the relevant code or use a connected repository tool to provide context. Only the code excerpts shown and explained in the video are included in it. The rest of your repository is not published. Videos are created as unlisted, with a claim link. They are not publicly listed, but anyone with the link can watch without logging in and claim the video to their Scrimba profile. To make your video private, sign in, claim it, and change its privacy setting to Private. Want to make it your own? Keep editing on our platform, then combine your explainers into courses and playlists. Powered by Scrimba, a learning platform with over 2 million users.

Tools

append_explainer_chunk

ChatGPT

Append a chunk of explainer markup to an open explainer stream. Chunks accumulate into one growing document — never resend earlier content. Viewers see it render live. Returns remaining budget. Your first successful append returns the explainer's link, so make it a real playback buffer — an opening section, not just a title slide. Send the link to the user as a non-blocking progress update, then continue appending immediately.

attach_explainer_image

ChatGPT

Attach a picture the user supplied or you generated in the conversation to an open explainer stream, so an ordinary image slide can show it. You need a file reference with a download link. Returns the attachment id to write on an image item: <item type="image" attachment="<id>" anchor="..." title="..."></item>, with no prompt. Call it before the append_explainer_chunk that names the slide — an append naming an id that is not an upload of this explainer is refused. Up to 12 pictures per explainer (each reply says how many more it can take), 8 MB each, png/jpeg/webp/gif; they do not count toward the generated-image cap. If the file only comes as a bare reference with no download link (uploads from the ChatGPT mobile app do), the call fails: build the explainer without that picture, never invent an id.

finish_explainer_stream

ChatGPT

Finalize an open explainer stream. Call this when you are done pushing — the explainer stops showing as generating and narration becomes playable for viewers.

start_explainer_stream

ChatGPT

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. Open an explainer stream where YOU author the content. Scrimba creates an empty explainer and renders whatever explainer markup you push — live, as you push it. Use this for narrated code and feature walkthroughs, uploaded screenshots, side-by-side before/after code diffs, Mermaid diagrams of code flows, and Manim animations. Returns: a stream_token for pushing and the complete explainer markup contract — no link yet. The explainer's link arrives in your first successful append_explainer_chunk result; make that first append a real playback buffer (an opening section, not just a title slide), then send the link to the user as a non-blocking progress update and keep appending (anyone who opens it can watch, no account needed, and holders of the link can claim ownership from the page). The result is large — more than 50KB — so if your client stores or truncates large tool results, use any storage or file tools you have to extract it in full. Read the contract to the end before pushing.

Capabilities

WritesInteractive

Example Prompts

Click any prompt to copy it.

Links

Documentation ↗Privacy Policy ↗

App Stats

Tools

Prompts

ChatGPT

Platforms