Can I vibecode Tango?

Build a personal replacement for Tango in an empty repository, focusing on automatically generating step-by-step documentation from recorded workflows.
Use Tauri 2, React, TypeScript, ffmpeg, and SQLite; do not offer alternative stacks.
The core loop is: capture a screen workflow (tracking mouse clicks and keyboard inputs), automatically generate a sequence of screenshots for each action, allow the user to annotate these screenshots, and export a concise step-by-step Markdown guide with embedded images.
Make the first run work locally with one documented command. Store all user data locally by default and make export straightforward.
Put secrets in .env, ship .env.example, and never commit credentials.
Offer screen or window capture that listens for global click events to take a screenshot and guess the context (e.g., "Click on [Element]").
Create an editor view where the user can review the captured steps, crop/zoom the screenshots, draw highlights/boxes around clicked areas, blur sensitive information, and edit the auto-generated text descriptions.
Generate the final output as a local Markdown file beside a folder of optimized WebP images.
Provide copy-markdown and reveal-in-folder actions instead of mandatory cloud upload.
Include clear empty, loading, success, and recoverable error states. Add input validation, safe filenames, and graceful handling of filesystem permissions.
Write focused tests for the image processing queue and data model transformation. Add one end-to-end happy path testing the step generation logic.
Create a README with setup, architecture, OS permissions (screen recording/accessibility), data location, and backup steps.
Do not add accounts, billing, telemetry, analytics, or a hosted control plane.
Deliberately leave out public cloud hosting, viewer analytics, interactive web players, and enterprise workspaces.
Finish by running the tests and listing the exact commands used.