Menu
Use when user reports a bug, broken feature, console error, failed network request, or unexpected page behavior that needs investigation.
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 user asks to automate browser actions, click buttons, fill forms, navigate pages, run a sequence of browser steps, or build a repeatable workflow.
Use when MCP tools fail to connect, user reports "extension not connected", tool calls return errors, or user asks to check their Kaboom setup.
| name | debug |
| description | Use when user reports a bug, broken feature, console error, failed network request, or unexpected page behavior that needs investigation. |
Use this skill when a user reports "it is broken" and needs a root cause, not guesses.
Establish baseline: Run observe calls for page status, tracked tab, console errors, and recent network failures.
Reproduce deliberately: Use small interact actions and keep one correlation ID per high-level step.
Capture evidence at failure point: Use observe for errors, network, and command_result. Use analyze for DOM or API validation only when needed.
Classify failure source: Pick one primary source: frontend runtime, backend/API, auth/session, CSP/extension bridge, or timing/race.
Produce fix-oriented output: Return root cause, confidence, exact evidence, minimal fix, and one verification step.
root_causeevidencefixverify