Browser Automation Script for Repetitive Web Tasks
Automate allowed web tasks reliably.
The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.
Write a browser automation script for a task I am allowed to automate. Task and site: [TASK_AND_SITE]. Proof that I may automate it (own account, permitted by terms, internal tool): [PERMISSION_BASIS]. Tool and language preference: [TOOL_AND_LANGUAGE]. Steps I do manually: [MANUAL_STEPS]. Before coding, confirm each item. If one fails, stop and tell me: [ ] The site's terms permit automation of this task, or it is my own system [ ] No bypass of logins, bot checks, or paywalls is needed [ ] No personal data of others will be collected without a basis [ ] An official API or export does not already solve it Then write the script to meet these requirements: [ ] Selectors prefer stable attributes (roles, labels, test ids) over brittle paths [ ] Explicit waits for elements, never fixed sleeps as the main strategy [ ] Credentials read from environment variables or a secret store, never in the code [ ] Rate limiting and human-scale delays [ ] Logging of each step with screenshots on failure [ ] Idempotent actions and a dry-run mode [ ] Clean-up of browser sessions [ ] A clear stop condition and a maximum number of items [ ] Tests against a staging site or a recorded page Include setup instructions, the script with comments, a troubleshooting section for the five most common failures, and a maintenance note for when the site changes.
Fill in before use
Optional: type your details and the prompt above updates. Nothing is saved or sent.
Replace each bracketed placeholder with your own details, then paste into ChatGPT, Gemini, Claude or another assistant.