momentic-maintain

SKILL.md

Maintain Momentic tests

Find the earliest point where a run entered a bad state, classify the cause from
evidence, and repair the test when a durable test change is appropriate. Use MCP
for targeted investigation, momentic ai classify for a fresh classifier
verdict, and momentic ai triage for automated repair and verification.

Do not weaken a test to hide an application bug, missing fixture, invalid
credentials, outage, or Momentic defect. Report those causes instead of changing
the test to pass.

Common workflows

What happened on my branch? Call momentic_list_runs with the exact gitBranchName and bounded start/end. Start without a status filter, then narrow to FAILED, CANCELLED, or recovered=true. Open exact candidates and compare with main only for a concrete cross-branch question.

Why is main red? List FAILED runs on the actual main branch over the incident window and paginate through every page needed for the claim. Narrow with failureCategory when investigating a known category, but group symptoms only after inspecting representative runs and step evidence. Read each exact run's saved classification before optionally re-classifying it.

De-flake and reduce recovery latency. Use momentic_quarantine_list for quarantined tests, recovered=true for successful runs that needed recovery, and minAttempts for retry-heavy runs (2 means at least one retry; 3 means at least two). Inspect earlier attempts, prioritize repeated same-intent failures, fix the earliest unstable postcondition, and measure again.

Know the discovery limits: