victoralfred

Design and implement `whatifd`, a trust-first LLM experiment runner that produces defensible verdicts (Ship / Don't Ship / Inconclusive) from forked production traces, replayed against a proposed change, scored, and reported. Use this skill whenever the user asks to design, architect, implement, plan, or build any part of whatifd — including the runner contract, trust floor, failure taxonomy, scorer cache, JSON schema, decision policy, report rendering, GitHub Action wrapper, or any milestone of the v0.1 → v1.0 trajectory. Also use this skill when discussing similar trust-first experiment-runner systems, CI-grade verdict tooling for LLM behavior changes, or any architectural question about replay-based regression testing for AI agents.

Deferred-work catalog for `whatifd`. Use when triaging whether an idea belongs in the active plan now or as future work, when proposing a refactor, or when looking for post-v0.1 candidates.

Source-code investigation skill for Datadog Technical Escalation Engineering. Use this skill whenever investigating bugs, malfunctions, customer-reported symptoms, feature behavior, or unexplained system behavior across Datadog repositories checked out locally. Triggers on: "investigate this escalation", "trace this issue", "find the root cause", "why is this metric missing", "why is this alert not firing", "trace the code path for X", "what changed that broke Y", "investigate this customer issue", any request to trace behavior end-to-end through Datadog source code, any request involving cross-repo code path analysis, any request to produce an investigation report with evidence classification. Also triggers when the user provides a stack trace, error message, metric name, log line, or symptom and asks for source-code-level analysis. Use this skill even for seemingly simple questions about Datadog system behavior if the answer requires tracing through actual source code rather than general knowledge.