From ai-maestro-orchestrator-agent
Provides evidence-based verification patterns—exit code proof, E2E testing, integration verification—for proving code works correctly with measurable evidence.
How this skill is triggered — by the user, by Claude, or both
Slash command
/ai-maestro-orchestrator-agent:amoa-verification-patternsamoa-mainThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Evidence-based verification for proving code and systems work correctly. Collect measurable, reproducible evidence -- not assumptions.
README.mdreferences/automation-scripts.mdreferences/combining-patterns.mdreferences/cross-platform-support.mdreferences/docker-troubleshooting.mdreferences/end-to-end-testing.mdreferences/evidence-based-verification.mdreferences/evidence-format.mdreferences/examples.mdreferences/exit-code-proof.mdreferences/github-integration.mdreferences/integration-verification.mdreferences/op-collect-evidence.mdreferences/op-format-verification-report.mdreferences/op-generate-test-report.mdreferences/op-notify-orchestrator.mdreferences/op-run-test-suite.mdreferences/op-update-github-issue.mdreferences/op-validate-evidence-record.mdreferences/op-verify-exit-code.mdEvidence-based verification for proving code and systems work correctly. Collect measurable, reproducible evidence -- not assumptions.
Verification reports with pass/fail status, collected evidence, and formatted results per test-report-format.md.
See: verification-principles.md
Copy this checklist and track your progress:
Input: Agent receives verification request for a new function. Output: Verification report with pass/fail, collected evidence, formatted results.
See examples.md for worked examples.
Fail-fast: failures propagate immediately, no fallbacks. See troubleshooting.md and docker-troubleshooting.md in Resources.
npx claudepluginhub emasoft/ai-maestro-orchestrator-agentEnforces strict verification methodology for code quality, requiring actual evidence of working code before shipping. Used with claudikins-kernel:verify and cross-command gates.
Enforces evidence-based completion claims by requiring fresh command output before reporting success. Use when finishing any task, fixing a bug, running tests, building, deploying, or making any "it works" claim.
Enforces evidence-based completion discipline: run verification commands (tests, lints, type checks, builds) before claiming work is done. Prevents false completion by requiring captured output.