session-debug_skill

Overview

This skill analyzes session debugging data to identify errors and issues that may have caused a user-reported problem. It combines GitHub issue context with a fetched session JSON, surfaces suspicious events, and ranks likely causes. The goal is a concise, evidence-backed investigation that points engineers to the most promising next steps.

How this skill works

It validates two arguments: a session-data URL and a GitHub issue identifier. It fetches the issue metadata to understand the user report, then downloads the session JSON and inspects logs, errors, network requests, timings, and user actions. Findings are correlated with the issue timeline and ranked by likelihood, with concrete recommendations for code investigation and fixes.

When to use it

• A user files a bug report and a session trace URL is available.
• You need to triage a single-session failure to determine root cause quickly.
• Reproductions are intermittent and you want evidence from the user's actual session.
• You must prioritize fixes by likelihood and impact.
• You want step-by-step correlation between reported steps and session events.

Best practices

• Ensure the session JSON is accessible via HTTPS and contains timestamps, logs, and request/response details.
• Include the full GitHub issue number or URL so the tool can fetch title, body, comments, and labels.
• Provide sessions shortly after failures to preserve timing and context.
• Enrich session logs with user actions and request IDs to improve correlation accuracy.
• Use this analysis as a starting point; reproduce high-confidence findings in a controlled environment before deploying fixes.

Example use cases

• A user reports a payment flow failure; analyze session traces to find network 502s or backend errors at the same timestamp.
• Intermittent UI freezing: detect long-running operations or blocking synchronous tasks in the session logs.
• API authorization errors: surface 401/403 responses correlated with user actions and token refresh attempts.
• Null reference exceptions in production: locate stack traces and the exact input/state that triggered them.
• Timeouts on third-party services: identify repeated failed requests and recommend retries or fallback logic.