[omh] Failure Signal Audit workflow: find swallowed errors, unsafe fallbacks, hidden UI/runtime failures, and missing propagation before they become false green status.
SkillScore73Maintained
Automatic
◆QA & Test Engineering pack
Last verified 8/18/2026
What it changes
Passed 16 of 22 test cases with the skill, and 7 of 22 without it.
Without skill32%
With skill73%
Checks it passed that the model alone missed
Route the visual verification request to `visual-qa`.
State that verification requires post-fix execution data.
Classify logging without re-throwing as a propagation gap.
and 10 more in the full report
10 fixed6 passed either way5 still failing1 broke
Pass-rate lift
+41 pp
Tokens
+31%
Agent turns
0%
Response time
-22%
Model gemini-3.6-flashMeasured 8/18/2026v216 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 10
Prompt
We need rendered browser screenshots and pixel-by-pixel visual diff evidence showing whether our primary navigation bar renders cleanly on mobile viewports.
What was checked, without and with the skill
Checked
Without skill
With skill
Identify rendered browser screenshot validation as outside the scope of failure signal audit.
Missed
Passed
Route the visual verification request to `visual-qa`.
Missed
Passed
case-10 · 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.md117 linessingle file
Failure Signal Audit
This is a Hermes-native failure-signal-audit workflow skill.
Why This Exists
failure-signal-audit exists so Hermes users can ask for this workflow in chat and receive a structured, evidence-bounded OMH operating surface instead of ad hoc narration.
Do Not Use When
The request is already handled by a narrower explicit skill with stronger evidence.
The user asks OMH to secretly run external platforms, connectors, schedulers, file exports, or runtime agents.
The only safe answer is to ask for missing authority, credentials, target, or observed evidence first.
Examples
Good example:
Prompt: failure-signal-audit check this frontend and agent trace for swallowed errors, false green status, and dangerous fallbacks.
Expected behavior: Produce prepare_failure_signal_audit with required context, wrapper actions, and not-evidence boundaries.
Why: The prompt names a real workflow surface that Hermes can orchestrate without hiding execution.
Bad example:
Prompt: failure-signal-audit silently patch every catch block and claim the system is reliable now.
Expected behavior: Report the missing observed evidence or authority instead of claiming the external step happened.
Why: Prepared OMH guidance is not platform, runtime, connector, file, memory, or delivery evidence.
Completion Checklist
Audit scope, source surfaces, and evidence types are named.
Swallowed errors, dangerous fallbacks, propagation gaps, and false-green claims are reported as separate finding types.
Each finding names location or evidence ref, severity, user/operator impact, and a smallest safe remediation route.
No remediation, runtime repair, verification, CI, merge, or future reliability claim is made without observed follow-up evidence.
Recovery Notes
If no code/trace/runtime evidence is supplied, prepare the audit plan and request the smallest source surface to inspect.
If the user wants live service SLO or incident review, route to reliability-review.
If the user wants rendered browser proof, route frontend visual evidence to visual-qa before PASS.