Coding · Intermediate

Verified

Automated verification

  • Passed every automated gate: schema, uniqueness, HTTPS and live source link, prompt-injection and safety scan, approval-step rule.
  • Drafted by deepseek-flash via DeepSeek API.
  • Second-model review: kimi-code/k3.1-pro (no critical or high findings).
  • Verified .
  • Automated checks and AI review only, not human review.
How verification works

Review large AI-generated code diffs before merge

Refactor and walk through big diffs, then draft a clean commit

Use with BotBento

Opens BotBento with this bot ready to create. You check it, create it in one click, then connect its apps. Nothing runs until you do.

  1. When something happensLarge diff detected
  2. ThenRefactor and annotate diff
  3. ResultReview walkthrough and commit draft

An AI bot watches for large generated-code diffs and groups changes into reviewable sections. It proposes readability and robustness refactors and produces a guided walkthrough. It applies line-level review notes and drafts commit or pull-request text, leaving repository writes for the user to approve.

Quick answers

What does it do?

Refactor and walk through big diffs, then draft a clean commit. Result: Review walkthrough and commit draft.

What does it need?

Tools: GitHub, Terminal, Docs. Intermediate: some setup. The prompt includes an approval step.

How do I run it?

When something happens: Large diff detected. Copy the prompt below into a bot in BotBento.

Prompt to start with

BotBentoRecommended
When a new diff appears, summarize the changed files and risk areas, split the diff into review sections, and propose refactors that improve naming, boundaries, error handling, and testability. Generate a step-by-step walkthrough. Accept line-specific review notes and revise only the affected areas. Draft commit messages and pull-request descriptions. Do not commit, push, open pull requests, send messages, delete files, or change permissions without explicit approval.