api-watch
Analyze a video URL or local file using the eyeroll hosted API.
Watch a bug video, diagnose the issue, fix the code, and raise a PR
> /plugin marketplace add mnvsk97/eyeroll > /plugin install eyeroll@mnvsk97-eyeroll
How it fires
How this command gets triggered: by you, by Claude, or both.
/fixContext preview
What this command does when you run it.
Watch a bug video, diagnose the issue, fix the code, and raise a PR
description: Watch a bug video, diagnose the issue, fix the code, and raise a PR argument-hint: '<url-or-path> [--context "..."]' allowed-tools: Bash, Read, Write, Edit, Glob, Grep
Watch a video showing a bug, diagnose it, fix the code, and raise a PR.
Raw arguments: `$ARGUMENTS`
Codebase context is auto-discovered from CLAUDE.md, AGENTS.md, .cursorrules, etc.
eyeroll watch $ARGUMENTS --verbose
If the user mentioned context in conversation, add `-c "<their words>"`.
Read the report. Check the **Metadata** block first:
Check **severity** to set urgency expectations (critical/moderate/low).
Read the report. Extract:
Search the codebase using the suggested patterns with `Grep` and `Glob` tools. Cross-reference with the video observations.
If context mentions a regression ("after PR #X", "since last deploy"):
gh pr view <number> git log --since="1 week ago" -- <identified-files>
Implement the fix. Keep changes minimal and focused.
Run the project's test suite. If a test would have caught this bug, write one.
Create a branch, commit, push, and open a PR:
gh pr create --title "Fix: <brief description>" --body "$(cat <<'EOF' ## Summary <what was broken and why> ## Bug Evidence - Video: <source URL if available> - Error: <exact error message> ## Changes - <file>: <what changed> ## Test Plan - <how to verify> EOF )"
If diagnosis confidence is low, present findings and ask the user before implementing. Create the PR as a draft if confidence is medium or lower.
AI eyes that roll through video footage — watch, understand, act. eyeroll is a Claude Code plugin that analyzes screen recordings, Loom videos, YouTube links, and screenshots, then helps coding agents fix bugs, build features, and create skills.
Repo: mnvsk97/eyeroll
Analyze a video URL or local file using the eyeroll hosted API.
List past video analyses from the cache
Set up eyeroll for this project — pick a backend, install dependencies, and generate codebase context
Analyze a video, screen recording, or screenshot and produce a structured report