Stats
Actions
Tags
From engineering-team
Use for read-only debugging and root-cause investigation: reproduce or reason about failures, build hypothesis matrices, identify next probes, and avoid edits until a fix is requested.
How this skill is triggered — by the user, by Claude, or both
Slash command
/engineering-team:debugging-forensicsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use when the user asks to investigate, debug, triage, or explain a failure without yet asking for a fix.
Use when the user asks to investigate, debug, triage, or explain a failure without yet asking for a fix.
Read-only by default. Inspect code, tests, configs, stack traces, and diagnostic output; do not patch code, rewrite tests, or change runtime state beyond safe local diagnostics unless implementation is authorized.
../engineering-team/templates/debugging-hypothesis-matrix.md.../engineering-team/templates/next-probe-plan.md.Use runtime tracing for stack/call/async/state paths, reproduction engineering for deterministic probes, and Evidence Skeptic to disprove weak-but-attractive hypotheses.
Return a hypothesis matrix plus next-probe plan. If the user later asks for a fix, hand off the confirmed root cause, affected contract, and verification plan to engineering-team implementation mode.
Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.
npx claudepluginhub daeon/engineeringteam --plugin engineering-team