[omh] Hermes Reliability Review workflow: postmortems, SLOs, error budgets, incident follow-ups, and service reliability evidence.
SkillScore91Maintained
Automatic
◆DevOps & SRE pack
Last verified 8/18/2026
What it changes
Passed 20 of 22 test cases with the skill, and 14 of 22 without it.
Without skill64%
With skill91%
Checks it passed that the model alone missed
Identifies missing SLO logs as unobserved inputs.
Explicitly states the smallest next verification task.
Assigns an unverified status to remediation ticket JIRA-402.
and 5 more in the full report
6 fixed14 passed either way2 still failing0 broke
Pass-rate lift
+27 pp
Tokens
+26%
Agent turns
0%
Response time
-28%
Model gemini-3.6-flashMeasured 8/18/2026v320 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 6
Prompt
A Jira ticket JIRA-402 is listed in the postmortem as 'Fix connection pool leak'. No pull request or test report is attached. What status must be assigned to this remediation item in the review?
What was checked, without and with the skill
Checked
Without skill
With skill
Assigns an unverified status to remediation ticket JIRA-402.
Missed
Passed
case-21 · 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.md108 linessingle file
Reliability Review
This is a Hermes-native reliability-review workflow skill.
Why This Exists
reliability-review exists to make SRE-style review strict: service reliability claims must point to metrics or references, and remediation remains separate from the review narrative.
Do Not Use When
The user only needs a generic status report or leadership deck.
No service, incident, SLO, metric, or reliability source boundary is available.
The request is implementation of remediation rather than review of reliability evidence.
Examples
Good example:
Prompt: reliability-review 장애 포스트모템과 SLO 에러버짓 상태를 검토해줘.
Expected behavior: Prepare a reliability artifact that separates metrics/references, assumptions, missing evidence, and remediation follow-ups.
Why: The request is reliability evidence review with closure-sensitive claims.
Bad example:
Prompt: reliability-review make a monthly PPT report for leadership.
Expected behavior: Use report-package unless the report specifically asks for reliability evidence review.
Why: Report packaging and reliability validation are independent operations surfaces.
Completion Checklist
Confirm the workflow target, evidence boundary, and stop condition are named.
Report which outputs are prepared, observed, blocked, or missing.
Name the smallest next verification or handoff instead of claiming completion from narration.
Recovery Notes
If required context is missing, ask one blocking question or route back to the narrower workflow.
If runtime or wrapper evidence is unavailable, keep the status as not_observed and expose the next observable action.