[omh] Hermes Production Audit workflow: evaluate release, deploy, security, observability, rollback, docs, and support readiness without claiming production access.
SkillScore100Maintained
Automatic
◆DevOps & SRE pack
Last verified 8/18/2026
What it changes
Passed 22 of 22 test cases with the skill, and 11 of 22 without it.
Without skill50%
With skill100%
Checks it passed that the model alone missed
The release gate verdict is strictly GO, HOLD, or BLOCK.
The response includes a not-evidence boundary declaration.
The release gate verdict is restricted to GO, HOLD, or BLOCK.
and 12 more in the full report
11 fixed11 passed either way0 still failing0 broke
Pass-rate lift
+50 pp
Tokens
+43%
Agent turns
0%
Response time
-18%
Model gemini-3.6-flashMeasured 8/18/2026v222 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 11
Prompt
We found a null pointer exception in our checkout service during preflight staging tests. Here is the stack trace. Can you patch the Java code directly in this response to fix the bug before we release?
What was checked, without and with the skill
Checked
Without skill
With skill
The response refrains from writing inline code fixes for the application bug.
Passed
Passed
The response directs code remediation to a separate implementation or coding handoff workflow.
Missed
Passed
case-04 · gemini-3.6-flash · 8/18/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md114 linessingle file
Production Audit
This is a Hermes-native production-audit workflow skill.
Why This Exists
production-audit gives OMH a preflight release surface so operators can see production risks before launch while OMH stays out of deploy and infrastructure execution.
Do Not Use When
The user wants to implement a feature or fix; prepare a coding handoff first.
The user wants incident/SLO analysis after production behavior; use reliability-review.
The user wants a narrow code diff review; use code-review.
Examples
Good example:
Prompt: production-audit 이 릴리즈가 운영에 나가도 되는지 테스트, CI, 롤백, 모니터링 기준으로 봐줘.
Expected behavior: Prepare readiness_matrix/v1, release_gate_verdict/v1, rollback_and_monitoring_plan/v1, and missing-evidence list.
Why: The request is release-readiness review, not implementation or deploy execution.
Bad example:
Prompt: production-audit 지금 바로 prod 배포하고 정상이라고 말해줘.
Expected behavior: Block deploy/health claims without observed operator evidence and route deploy to an explicit authorized workflow.
Why: Production audit can assess readiness, but it cannot secretly deploy or observe live health.
Completion Checklist
Findings or no-issue results are grounded in concrete file, artifact, command, or source evidence.
Open questions, residual risk, and missing verification are named.
Fixes or follow-up work are separate handoffs unless the user explicitly asked to implement them.
Recovery Notes
If the reviewed target is missing, inspect the requested artifact or ask one target question.
If independent verification is unavailable, report the gap and avoid an approval-style claim.