[omh] Hermes adaptation for bounded official/upstream best-practice research.
NewMaintained
Automatic
◆Research pack
Last verified 8/18/2026
What it changes
Passed 18 of 22 test cases with the skill, and 18 of 22 without it.
Without skill82%
With skill82%
Checks it passed that the model alone missed
The response specifies configuring `remote.log.manager.class.name` for remote log management.
The response specifies attaching trace IDs to metric lines using OpenMetrics exemplar syntax.
2 fixed16 passed either way2 still failing2 broke
Pass-rate lift
0 pp
Tokens
+16%
Agent turns
0%
Response time
-5%
Model gemini-3.6-flashMeasured 8/18/2026v318 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 2
Prompt
Check Apache Kafka 3.6 official documentation for enabling remote tiered storage with S3. Provide a source-backed summary of required cluster properties, note how it applies to an on-premise Kubernetes deployment, state recency boundaries, confidence rating, and highlight unverified aspects.
What was checked, without and with the skill
Checked
Without skill
With skill
The response specifies setting `remote.log.storage.system.enable=true` in the Kafka broker configuration.
Passed
Passed
The response specifies configuring `remote.log.manager.class.name` for remote log management.
Missed
Passed
case-06 · 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.md105 linessingle file
Best Practice Research
This is a Hermes-native best-practice-research workflow skill.
Why This Exists
best-practice-research exists to keep research work explicit, evidence-backed, and inside the Hermes/executor boundary instead of relying on ad hoc chat narration.
Do Not Use When
The work needs multi-source current evidence, a market or literature comparison, or a business brief rather than one technology's upstream guidance; use research.
Examples
Good example:
Prompt: best-practice-research: check official docs and upstream examples before we choose the plugin packaging pattern.
Expected behavior: Gather primary-source guidance, compare options, and separate evidence from recommendation.
Why: The request needs citation-backed best-practice research before implementation.
Bad example:
Prompt: best-practice-research: treat casual chat or unaccepted work as if this workflow already produced verified results.
Expected behavior: Ask a clarification question or route to a narrower workflow instead of forcing best-practice-research.
Why: The request lacks the required inputs or would overclaim work that Hermes did not observe.
Completion Checklist
The research question, source boundaries, recency assumptions, and confidence level are named.
Observed sources, inference, synthesis, and unresolved retrieval gaps are separated.
Follow-up planning or handoff uses the research summary without calling it execution evidence.
Recovery Notes
If sources cannot be accessed, state the retrieval gap and use only observed local context.
If evidence is thin or one-sided, lower confidence and ask for a narrower source boundary.
Workflow Lane
Current lane: Research and company ops (source-finder, research, best-practice-research, autoresearch-goal, research-brief, strategy-brief, feedback-triage, research-department, +13 more) - research, signals, ops, and briefings.