sf-debug

Use this skill when the user needs root-cause analysis from debug logs : governor-limit diagnosis, stack-trace interpretation, slow-query investigation, heap / CPU pressure analysis, or a reproduction-to-fix loop based on log evidence. Use sf-debug when the work involves: Delegate elsewhere when the user is: Ask for or infer: Prefer fixes that are: Expanded workflow: references/analysis-playbook.md Expanded examples: references/common-issues.md When finishing analysis, report in this order: Suggested shape: - .log files from Salesforce - stack traces and exception analysis - governor limits - SOQL / DML / CPU / heap troubleshooting - query-plan or performance evidence extracted from logs - running or repairing Apex tests → sf-testing - implementing the code fix → sf-apex - debugging Agentforce session traces / parquet telemetry → sf-ai-agentforce-observability - org alias - failing transaction / user flow / test name - approximate timestamp or transaction window - user / record / request ID if known - whether the goal is diagnosis only or diagnosis + fix loop - entry point and transaction type - exceptions / fatal errors - governor limits - repeated SOQL / DML patterns - CPU / heap hotspots - callout timing and external failures - Critical — runtime failure, hard limit, corruption risk - Warning — near-limit, non-selective query, slow path - Info — optimization opportunity or...