DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to mark up a localhost page and send fixes back to the app source with Human Review

Review a running local page in the browser and have your agent apply the changes to the code.

  • Content
  • Intermediate
  • 30 minutes
  • From the README
  • Claude Code
  • Codex

Who it is forA developer or designer building a landing page or small app locally who wants to point at exact spots instead of describing them in chat.

The problemDescribing visual fixes in chat, such as which card repeats or which button text to change, loses detail and needs several rounds.

The outcomeYour agent receives comments anchored to exact text and elements, plus your direct edits, and applies them to the app source.

What you need first

  • A coding agent that can install skills, such as Claude Code or Codex
  • A web browser
  • An HTML or Markdown file on your computer, or a page running on localhost
  • npx available on your computer if you use the npm install option

Steps

  1. Install the skill by pasting this into Claude Code or Codex: Install the /human-review skill globally from https://github.com/petergyang/human-review
  2. Start your local page so it runs on a localhost URL
  3. Ask your agent to run /human-review with the localhost URL
  4. Click an image, chart, or section to comment on it, or select a phrase to comment on that text
  5. Click Send, then let the agent update the source and refresh the page

Prompt for your agent

Using the petergyang/human-review skill, open the localhost page at <localhost-url> with /human-review. After I click Send, check that the agent changed the app source for each comment and report which files were edited.

Caveat. On localhost pages, pasted images are staged for the agent to place in the app source rather than saved beside a document, and changes only reach the source after you click Send.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page