diagnoselisted

# Diagnose ## Purpose Use this skill for product, code, test, and runtime failures where the cause is not obvious. The core discipline is to build a fast, trusted pass/fail loop before fixing anything. Do not use this for agent self-recovery, repeated tool loops, or context drift. Use `agent-introspection-debugging` for those. ## Workflow ### 1. Build The Feedback Loop Find the smallest repeatable signal that shows the bug. Prefer, in order: 1. A failing test at the seam that reaches the bug. 2. A CLI command, fixture, or HTTP request that reproduces the symptom. 3. A browser automation script for UI, console, or network failures. 4. A replayed artifact such as a log, event payload, HAR file, trace, or saved input. 5. A throwaway harness that exercises the failing code path in isolation. 6. A stress, property, fuzz, or looped reproduction for nondeterministic failures. 7. A human-in-the-loop script only when manual steps cannot be automated. If no credible loop can be built, stop and report what was tried. Ask for the missing artifact, environment access, or permission for temporary instrumentation. ### 2. Reproduce Run the loop until it shows the user's failure, not a nearby failure. Confirm: - the symptom matches the user's report - the failure is repeatable, or frequent enough to debug - the exact error, wrong output, or slow timing is captured ### 3. Rank Hypotheses Write 3 to 5 ranked hypotheses before probing. Each hypothesis must be falsifiable: ```tex