debug-run-transcript-maintainer

What problem does it solve?

This Skill helps you debug Rudder agent runs by reconstructing what actually happened across transcripts, run logs, and execution traces so you can pinpoint the first failure point rather than guessing from partial summaries.

Core Features & Use Cases

• Reconstructs the execution story: diagnoses failures using run-intelligence evidence, transcript outlines, and fallback log reconstruction.
• Handles partial identifiers and batch audits: supports full run IDs, ID prefixes, and “recent runs” requests at org/runtime/time-window scope.
• Evidence-first debugging: keeps root-cause evidence separate from product-fix proof, helping you avoid claiming a fix works without lifecycle verification.

Quick Start

Use this skill when you want to understand why a Rudder agent run failed by providing a run ID, a run ID prefix, or a recent-run timeframe and asking for the first clear failure point with evidence.