[omh] Hermes adaptation for durable research-goal execution.
SkillScore77Maintained
Automatic
◆Research pack
Last verified 8/18/2026
What it changes
Passed 17 of 22 test cases with the skill, and 12 of 22 without it.
Without skill55%
With skill77%
Checks it passed that the model alone missed
Requests additional independent source access
Marks third-party blog performance benchmarks as out-of-boundary sources
Classifies missing worker sub-query returns as missing runtime delegation state
and 4 more in the full report
6 fixed11 passed either way4 still failing1 broke
Pass-rate lift
+23 pp
Tokens
+9%
Agent turns
0%
Response time
-22%
Model gemini-3.6-flashMeasured 8/18/2026v317 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
Give me a quick status update on whether the latest CI pipeline run passed for the repository.
What was checked, without and with the skill
Checked
Without skill
With skill
Provides a direct status response without starting an iterative research workflow
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.md106 linessingle file
Autoresearch Goal
This is a Hermes-native autoresearch-goal workflow skill.
Why This Exists
autoresearch-goal 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 request is casual chat, a status-only acknowledgement, or another workflow has stronger routing evidence.
The user needs implementation, review, CI, merge, or external publishing evidence that has not been delegated or observed.
Examples
Good example:
Prompt: autoresearch-goal: keep researching AI agent memory practices until the evidence gaps are closed or logged.
Expected behavior: Run a durable research loop with critic checks, source gaps, and a stop or checkpoint condition.
Why: The request is research that needs persistence and review, not a one-shot brief.
Bad example:
Prompt: autoresearch-goal: 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 autoresearch-goal.
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.