[omh] Ultraperf - find where a system is actually slow, leaking, or expensive across runtime, memory, token cost, storage, rendering, inference, CI, and query domains, then fix one measured hot path at a time behind a regression budget.
SkillScore86Maintained
Automatic
◆Coding pack
Last verified 8/27/2026
What it changes
Passed 17 of 20 test cases with the skill, and 7 of 20 without it.
Without skill36%
With skill86%
Checks it passed that the model alone missed
Re-ranks remaining hot-path hypotheses.
Identifies the Hermes catalog role as tracker.
Routes the optimization task to performance-goal.
and 11 more in the full report
11 fixed8 passed either way3 still failing0 broke
Pass-rate lift
+50 pp
Tokens
+31%
Agent turns
0%
Response time
-30%
Model gemini-3.6-flashMeasured 8/27/2026v319 of 22 cases passed with skill · 20 comparable
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
What is the designated Hermes role and quality tier associated with the ultraperf catalog metadata for measured optimization loops?
What was checked, without and with the skill
Checked
Without skill
With skill
Identifies the Hermes catalog role as tracker.
Missed
Passed
Identifies the quality tier as measurement-gated.
Missed
Passed
case-20 · gemini-3.6-flash · 8/27/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md119 linessingle file
Ultraperf
This is a Hermes-native ultraperf workflow skill.
Why This Exists
ultraperf exists because most performance work starts unlocalized: something is slow, leaking, or expensive and nobody knows where. It forces measurement before edits, one hypothesis at a time, executor-owned changes, and a regression budget, so an optimization loop cannot end in unverified claims.
Do Not Use When
Metric, baseline, budget, and benchmark command are already declared for one measurable goal; use performance-goal.
The ask is to judge code quality, structure, or correctness rather than measured cost; use code-review.
The ask is to score model or agent output quality on a task suite; use agent-evaluation.
The request is a settings-only change, one bounded edit that is explicitly low-risk and has a direct owner and verification path, or one already-identified slow query or hotspot fix; handle it directly instead of opening a performance loop.
Examples
Good example:
Prompt: $ultraperf checkout feels slow and the worker memory keeps climbing - find where and fix it
Expected behavior: Audit the baseline, name the evaluator command, rank hot-path hypotheses, hand the smallest reversible fix to the selected executor, re-measure, and state the budget delta.
Why: The problem is real but unlocalized across more than one domain.
Bad example:
Prompt: $ultraperf make the recommender p95 under 200ms; baseline 340ms, benchmark is 'make bench'
Expected behavior: Route to performance-goal, which owns a declared metric/baseline/budget/benchmark goal.
Why: A single declared measurable goal does not need a discovery loop.
Completion Checklist
Baseline, workload, environment, and evaluator command are recorded before any edit is proposed.
Each accepted fix names the measured hot path, the reversible change, and its owner.