Menu
Use when user asks to automate browser actions, click buttons, fill forms, navigate pages, run a sequence of browser steps, or build a repeatable workflow.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Use when user asks to check browser state, debug page errors, inspect network traffic, take screenshots, automate clicks or form fills, run accessibility or security audits, measure performance, generate tests, or record browser sessions. Trigger phrases: "check my browser", "debug this page", "take a screenshot", "browser errors", "network requests", "automate the browser", "record a test", "accessibility audit", "performance check", "what's on the page".
Use when the user wants a full Kaboom quality audit of a web app or tracked site, with one polished report covering Functionality, UX Polish, Accessibility, Performance, Release Risk, and SEO.
Use when user says "QA my app", "find all bugs", "check my app for problems", "debug my whole app", "what's broken", or wants a comprehensive quality review of their web application.
Use when user asks to check API responses, validate request/response contracts, compare API behavior against a spec, or detect schema drift.
Use when MCP tools fail to connect, user reports "extension not connected", tool calls return errors, or user asks to check their Kaboom setup.
Use when user reports a bug, broken feature, console error, failed network request, or unexpected page behavior that needs investigation.
| name | automate |
| description | Use when user asks to automate browser actions, click buttons, fill forms, navigate pages, run a sequence of browser steps, or build a repeatable workflow. |
Use this skill for reliable task execution in the browser where flakiness must be minimized.
Validate preconditions: Confirm tracked tab, auth state, and feature flags.
Plan robust selectors: Prefer semantic selectors and stable attributes over brittle CSS chains.
Execute in small steps: After each interact call, inspect command_result and page state.
Apply bounded recovery: Use retry once with alternate selector or wait strategy.
Confirm success: Return explicit pass/fail with final observed state.
planexecution_logretriesfinal_status