performance-goal

Name: performance-goal
Author: rlaope

61stars2forks

How to install performance-goal?

rlaope/oh-my-hermes/performance-goal

$npx -y skills add rlaope/oh-my-hermes --skill performance-goal

Installs into the current project.

Summary

[omh] Hermes adaptation for measurable performance-goal execution.

Files · 1

View on GitHub

SKILL.md

1	# Performance Goal
2
3	This is a Hermes-native `performance-goal` workflow skill.
4
5	## Why This Exists
6
7	`performance-goal` exists to keep `optimization` work explicit, evidence-backed, and inside the Hermes/executor boundary instead of relying on ad hoc chat narration.
8
9	## Do Not Use When
10
11	- The request is casual chat, a status-only acknowledgement, or another workflow has stronger routing evidence.
12	- The user needs implementation, review, CI, merge, or external publishing evidence that has not been delegated or observed.
13
14	## Examples
15
16	Good example:
17
18	- Prompt: performance-goal: benchmark recommendation latency, optimize hot paths safely, and prove no regressions.
19	- Expected behavior: Create a measurement-led optimization loop with baseline, change, verification, and regression evidence.
20	- Why: The request is performance optimization and needs measured before/after proof.
21
22	Bad example:
23
24	- Prompt: performance-goal: treat casual chat or unaccepted work as if this workflow already produced verified results.
25	- Expected behavior: Ask a clarification question or route to a narrower workflow instead of forcing `performance-goal`.
26	- Why: The request lacks the required inputs or would overclaim work that Hermes did not observe.
27
28	## Completion Checklist
29
30	- Confirm the workflow target, evidence boundary, and stop condition are named.
31	- Report which outputs are prepared, observed, blocked, or missing.
32	- Name the smallest next verification or handoff instead of claiming completion from narration.
33
34	## Recovery Notes
35
36	- If required context is missing, ask one blocking question or route back to the narrower workflow.
37	- If runtime or wrapper evidence is unavailable, keep the status as not_observed and expose the next observable action.
38
39	## OMH Context Rail
40
41	- This skill is part of OMH's Hermes workflow layer, not a standalone executor.
42	- Product context: OMH is a Hermes-native workflow pack: choose skills, shape work, prepare artifacts, show status, and hand off with evidence boundaries.
43	- Current lane: Intent -> plan (`oh-my-hermes`, `deep-interview`, `plan`, `ralplan`, `codebase-onboarding`, `codegraph-refresh`, `ultragoal`, `ultraprocess`, `+3 more`) - clarify, plan, ship, or loop goals.
44	- If the user intent belongs to another OMH lane, hand back to `oh-my-hermes` or name the adjacent workflow instead of force-fitting this skill.
45	- Cross-skill context: every OMH skill: match lane; generic tool can render or execute.
46	- Generic-tool checkpoint: image->img-summary; frontend->frontend/a11y/visual-qa; paper->paper-learning; content->content-operator; media->media-input-operator; file->materials-package; search->web-research; live->live-info-operator; audit->workspace/production/security; failures->build-failure; verify->verification-gate; code->codegraph/onboarding/ultraprocess.
47	- Coverage: Every generated workflow skill carries this rail.
48	- Normal users talk to Hermes; OMH CLI is infra.
49	- Boundary: Prepared OMH routing, cards, handoffs, or artifacts are not observed execution, image generation, delivery, review, CI, merge-readiness, or merge evidence.
50
51	## Use When
52
53	Use when the goal is measurable performance improvement with evaluator evidence.
54
55	Strong routing signals: `performance-goal`, `performance goal`, `latency`, `throughput`, `benchmark`
56
57	## Catalog Metadata
58
59	Category: `optimization`
60	Phase: `measurement`
61	Hermes role: `tracker`
62	Quality tier: `measurement-gated`
63
64	Quality bar:
65
66	- Name the metric, baseline, budget, and benchmark command before optimizing.
67	- Treat code-level optimization as executor work when edits are required.
68	- Report deltas only from observed benchmark evidence.
69
70	Handoff policy:
71
72	Hermes can own baselines, benchmark plans, and status; optimization code changes should be selected executor/runtime handoffs.
73
74	Required inputs:
75
76	- metric
77	- baseline
78	- budget
79	- benchmark command
80
81	Expected outputs:
82
83	- measurement delta
84	- implementation summary
85	- benchmark evidence
86
87	Artifact expectations:
88
89	- baseline and final benchmark evidence
90
91	Safety rules:
92
93	- Do not imply hidden Hermes runtime behavior.
94	- Use the smallest verification that can prove the claim.
95
96	## Harness Discipline
97
98	- Start from the representative harness registry in `oh-my-hermes` when the workflow needs coding, research, planning, goal execution, architecture, critique, QA, or documentation lanes.
99	- Prefer richer evidence and clearer stop conditions over adding more workflow names.
100	- Use specialist lanes only when they change the quality of the answer or verification.
101
102	## Runtime Evidence
103
104	Preferred harness for this skill: `goal-execution`.
105
106	When local shell access or a bot wrapper is available, record metadata-only evidence:
107
108	```sh
109	omh runtime record --skill performance-g

People who liked this also viewed

6 picks

Type

performance-goal

61stars2forks

View on GitHub

How to install performance-goal?

rlaope/oh-my-hermes/performance-goal

$npx -y skills add rlaope/oh-my-hermes --skill performance-goal

Installs into the current project.

Summary

[omh] Hermes adaptation for measurable performance-goal execution.

Files · 1

View on GitHub

SKILL.md

1	# Performance Goal
2
3	This is a Hermes-native `performance-goal` workflow skill.
4
5	## Why This Exists
6
7	`performance-goal` exists to keep `optimization` work explicit, evidence-backed, and inside the Hermes/executor boundary instead of relying on ad hoc chat narration.
8
9	## Do Not Use When
10
11	- The request is casual chat, a status-only acknowledgement, or another workflow has stronger routing evidence.
12	- The user needs implementation, review, CI, merge, or external publishing evidence that has not been delegated or observed.
13
14	## Examples
15
16	Good example:
17
18	- Prompt: performance-goal: benchmark recommendation latency, optimize hot paths safely, and prove no regressions.
19	- Expected behavior: Create a measurement-led optimization loop with baseline, change, verification, and regression evidence.
20	- Why: The request is performance optimization and needs measured before/after proof.
21
22	Bad example:
23
24	- Prompt: performance-goal: treat casual chat or unaccepted work as if this workflow already produced verified results.
25	- Expected behavior: Ask a clarification question or route to a narrower workflow instead of forcing `performance-goal`.
26	- Why: The request lacks the required inputs or would overclaim work that Hermes did not observe.
27
28	## Completion Checklist
29
30	- Confirm the workflow target, evidence boundary, and stop condition are named.
31	- Report which outputs are prepared, observed, blocked, or missing.
32	- Name the smallest next verification or handoff instead of claiming completion from narration.
33
34	## Recovery Notes
35
36	- If required context is missing, ask one blocking question or route back to the narrower workflow.
37	- If runtime or wrapper evidence is unavailable, keep the status as not_observed and expose the next observable action.
38
39	## OMH Context Rail
40
41	- This skill is part of OMH's Hermes workflow layer, not a standalone executor.
42	- Product context: OMH is a Hermes-native workflow pack: choose skills, shape work, prepare artifacts, show status, and hand off with evidence boundaries.
43	- Current lane: Intent -> plan (`oh-my-hermes`, `deep-interview`, `plan`, `ralplan`, `codebase-onboarding`, `codegraph-refresh`, `ultragoal`, `ultraprocess`, `+3 more`) - clarify, plan, ship, or loop goals.
44	- If the user intent belongs to another OMH lane, hand back to `oh-my-hermes` or name the adjacent workflow instead of force-fitting this skill.
45	- Cross-skill context: every OMH skill: match lane; generic tool can render or execute.
46	- Generic-tool checkpoint: image->img-summary; frontend->frontend/a11y/visual-qa; paper->paper-learning; content->content-operator; media->media-input-operator; file->materials-package; search->web-research; live->live-info-operator; audit->workspace/production/security; failures->build-failure; verify->verification-gate; code->codegraph/onboarding/ultraprocess.
47	- Coverage: Every generated workflow skill carries this rail.
48	- Normal users talk to Hermes; OMH CLI is infra.
49	- Boundary: Prepared OMH routing, cards, handoffs, or artifacts are not observed execution, image generation, delivery, review, CI, merge-readiness, or merge evidence.
50
51	## Use When
52
53	Use when the goal is measurable performance improvement with evaluator evidence.
54
55	Strong routing signals: `performance-goal`, `performance goal`, `latency`, `throughput`, `benchmark`
56
57	## Catalog Metadata
58
59	Category: `optimization`
60	Phase: `measurement`
61	Hermes role: `tracker`
62	Quality tier: `measurement-gated`
63
64	Quality bar:
65
66	- Name the metric, baseline, budget, and benchmark command before optimizing.
67	- Treat code-level optimization as executor work when edits are required.
68	- Report deltas only from observed benchmark evidence.
69
70	Handoff policy:
71
72	Hermes can own baselines, benchmark plans, and status; optimization code changes should be selected executor/runtime handoffs.
73
74	Required inputs:
75
76	- metric
77	- baseline
78	- budget
79	- benchmark command
80
81	Expected outputs:
82
83	- measurement delta
84	- implementation summary
85	- benchmark evidence
86
87	Artifact expectations:
88
89	- baseline and final benchmark evidence
90
91	Safety rules:
92
93	- Do not imply hidden Hermes runtime behavior.
94	- Use the smallest verification that can prove the claim.
95
96	## Harness Discipline
97
98	- Start from the representative harness registry in `oh-my-hermes` when the workflow needs coding, research, planning, goal execution, architecture, critique, QA, or documentation lanes.
99	- Prefer richer evidence and clearer stop conditions over adding more workflow names.
100	- Use specialist lanes only when they change the quality of the answer or verification.
101
102	## Runtime Evidence
103
104	Preferred harness for this skill: `goal-execution`.
105
106	When local shell access or a bot wrapper is available, record metadata-only evidence:
107
108	```sh
109	omh runtime record --skill performance-g

People who liked this also viewed

6 picks

Type