by petergyang
A visual tool to edit HTML and Markdown files, leave comments like a Google Doc, and send feedback to your AI agent. Works inside your favorite AI harness.
# Add to your Claude Code skills
git clone https://github.com/petergyang/human-reviewLast scanned: 8/6/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-08-06T06:30:43.313Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}See how human-review compares with popular alternatives.
human-review is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by petergyang. A visual tool to edit HTML and Markdown files, leave comments like a Google Doc, and send feedback to your AI agent. Works inside your favorite AI harness. It has 1,271 GitHub stars.
Yes. human-review passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/petergyang/human-review" and add it to your Claude Code skills directory (see the Installation section above).
human-review is primarily written in JavaScript. It is open-source under petergyang on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh human-review against similar tools.
No comments yet. Be the first to share your thoughts!
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
Edit HTML and Markdown files directly, leave comments like a Google Doc, and send all your feedback to your AI agent at once.
https://github.com/user-attachments/assets/7cab09c9-eaa0-4e8b-984d-2925e810b5c2
Giving AI feedback on files in chat is painful.
Sometimes you want to change one sentence yourself. Instead, you end up typing:
In the third paragraph, change X to Y. Cut the third card because it repeats the first one. Also rewrite the CTA.
Then the agent changes the file and you have to check whether it understood every instruction. This gets even harder when you’re reviewing a long plan, Markdown document, landing page, or multi-page website.
The easiest way to install the skill is to paste this into ChatGPT, Claude Code, Codex, or your favorite coding agent:
Install the /human-review skill globally from https://github.com/petergyang/human-review
You can also install it with npx:
npx -y human-review setup --global

Open an HTML or Markdown file:
/human-review (your file)
Review a page running on localhost:
/human-review (localhost URL)
Human Review opens the file in your browser. Make direct edits, leave comments, and click Send. Your agent receives all your feedback in one batch, updates the source, and refreshes the page for another review.
In Claude Code, the agent waits in the background and picks up your feedback the moment you hit Send. In Codex and other agents, it waits during its turn; if the turn already ended, send a message and it picks the feedback up. Closing the tab or clicking End review releases the agent either way. Feedback you never sent is kept, and the next time you open that page you can restore or discard it.
Note: For HTML files, direct edits and resizes save automatically, so closing the tab doesn't undo them — Discard on your next open, or Revert all during the review, puts the file back. For Markdown and localhost pages, click Send so your agent can apply them to the source.
- or 1. at the start of a line, or press ⌘⇧8 / ⌘⇧7. Tab and Shift+Tab indent and outdent.I use Human Review to edit AI-generated plans, update landing pages, review localhost apps, and remove the extra copy AI likes to add to UX.
cli.js contains the human-review, poll, status, and setup commands.server.js runs the local review session.sdk.js handles editing, comments, highlights, and feedback.chrome-client.js contains the visual review interface.markdown.js renders Markdown files for review.SKILL.md teaches Claude Code, Codex, and other agents how to use Human Review.Everything runs on your computer. Human Review doesn’t require an account, cloud service, database, or API key.
Check out Behind the Craft, my personal AI system with over a dozen other quality skills and courses.
Subscribe to my YouTube channel and newsletter for practical AI tutorials and interviews.
MIT