root-cause-tracing
Trace bugs backward to their origin, not just symptoms
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Trace bugs backward to their origin, not just symptoms
Diagnose and fix TwinMind common errors and exceptions. Use when encountering transcription errors, debugging failed requests, or troubleshooting integration issues. Trigger with phrases like "twinmind error", "fix twinmind", "twinmind not working", "debug twinmind", "transcription failed".
Collect comprehensive diagnostic information for TwinMind issues. Use when preparing support requests, investigating complex problems, or gathering evidence for bug reports. Trigger with phrases like "twinmind debug", "twinmind diagnostics", "collect twinmind info", "twinmind support bundle".
Diagnose and fix common Langfuse errors and exceptions. Use when encountering Langfuse errors, debugging missing traces, or troubleshooting integration issues. Trigger with phrases like "langfuse error", "fix langfuse", "langfuse not working", "debug langfuse", "traces not appearing".
Query and analyze Metro's perfetto compiler traces to find real hot spots and untraced time. Use whenever the user asks about metro compile-time perf, where time is going in a trace, or shares a perfetto screenshot.
BI validator driven by ValidationHook — inspects every dashboard, chart, and dataset delivered in the run, verifies config quality (chart type, metrics, dimensions, dataset wiring) and data presence via get_chart_data when supported
Scheduler validator driven by ValidationHook — read-only static verification of scheduled jobs (schedule correctness, configuration, runtime context already collected by deterministic hook). Does not trigger test runs.
SQL query optimization techniques and best practices
Validate the column contract of a newly written table — column set, types, and nullability match expectations. Object existence and row counts are handled by the builtin layer and are out of scope. Data-content assertions belong to project-level validator skills.
Lightweight post-transfer reconciliation example — verify tool-reported row count parity and run a small target-side sanity check without re-scanning the source.