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

How to replay a browser flow and check the evidence it shows with Codexqa

Run a UI case in Playwright Chromium and get a report with marked screenshots per step.

Who it is forA QA engineer who needs to confirm that a web flow reaches the visible result named in its goal.

The problemAn agent saying a flow is done does not prove the page shows the expected result.

The outcomeA reports/<run-id>/report.html file showing each step, the control used, and a marked screenshot with the step result.

What you need first

  • One of Cursor, Claude Code, Codex, or OpenClaw installed
  • A local git repository with the branch to check (the README refers to origin/main)
  • Node.js with npx available (inferred from the npx install commands)
  • For browser replay: Playwright Chromium, as named in the README

Steps

  1. Install the browser skill with npx skills add openqa-cn/codexqa --skill codexqa-jev-browser.
  2. Install Playwright Chromium in the environment, as the README names it as the browser; the README does not give the exact command. (inferred, check the README)
  3. Prepare a YAML, Markdown, or API case, or write a goal in plain text.
  4. Run the agent prompt below.
  5. Open reports/<run-id>/report.html and check each marked screenshot against the expected evidence.

Prompt for your agent

Use codexqa-jev-browser to replay the case at <case-path> against <target-url>. Write a report under reports/<run-id>/report.html with a marked screenshot per step. Verify that the final screenshot shows the visible evidence named in the goal.

Caveat. The README says replay does not call a decision model, but generating a case from a goal does, and the README does not say how it behaves on logins or dynamic pages.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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