Menu
Use when user reports a broken page, unexpected behavior, or error and needs fast root-cause identification across multiple signal sources.
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-triage |
| description | Use when user reports a broken page, unexpected behavior, or error and needs fast root-cause identification across multiple signal sources. |
Use this skill when a feature is broken and the user needs root cause with proof.
Capture baseline:
Run observe for page, tabs, errors, and network_waterfall.
Reproduce in controlled steps:
Use interact actions one step at a time and keep correlation IDs.
Capture failure evidence:
Read error_bundles first, then targeted logs, network_bodies, and command_result.
Verify state assumptions:
Use analyze(dom) or analyze(computed_styles) only where evidence suggests mismatch.
Classify root cause: Pick one primary class: UI runtime, API contract, auth/session, bridge/transport, timing/race, or third-party.
Propose smallest fix and verify: Give one minimal change and one pass/fail validation step.
root_causeevidenceminimal_fixverification_step