ask

Name: ask
Author: rlaope

61stars2forks

How to install ask?

rlaope/oh-my-hermes/ask

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

Installs into the current project.

Summary

[omh] Hermes adaptation for consulting an external advisor when configured.

Files · 1

View on GitHub

SKILL.md

1	# Ask
2
3	This is a Hermes-native `ask` workflow skill.
4
5	## Why This Exists
6
7	`ask` exists to keep `review` 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: ask: ask Claude as an external advisor to critique this plugin bridge plan before implementation.
19	- Expected behavior: Prepare an advisor prompt, capture the response boundary, and summarize reusable critique.
20	- Why: The user wants outside review before committing to a direction.
21
22	Bad example:
23
24	- Prompt: ask: 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 `ask`.
26	- Why: The request lacks the required inputs or would overclaim work that Hermes did not observe.
27
28	## Completion Checklist
29
30	- Findings or no-issue results are grounded in concrete file, artifact, command, or source evidence.
31	- Open questions, residual risk, and missing verification are named.
32	- Fixes or follow-up work are separate handoffs unless the user explicitly asked to implement them.
33
34	## Recovery Notes
35
36	- If the reviewed target is missing, inspect the requested artifact or ask one target question.
37	- If independent verification is unavailable, report the gap and avoid an approval-style claim.
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: Automation and status (`achievements`, `workspace-audit`, `production-audit`, `automation-blueprint`, `github-event-ops`, `agent-board`, `gateway-intent-card`, `voice-operator`, `+26 more`) - schedules, status, health, and ops review.
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 only when an external advisor is configured and would materially improve the answer.
54
55	Strong routing signals: `ask`, `$ask`, `external advisor`, `claude`, `gemini`
56
57	## Catalog Metadata
58
59	Category: `review`
60	Phase: `external-advice`
61	Hermes role: `reviewer`
62	Quality tier: `evidence-gated`
63
64	Quality bar:
65
66	- Name the workflow target, constraints, validation evidence, and stop condition.
67	- Separate Hermes guidance from executor or wrapper behavior unless evidence proves the step happened.
68
69	Handoff policy:
70
71	Use as optional advice gathering; evaluate the advice in Hermes and delegate coding changes separately.
72
73	Required inputs:
74
75	- question
76	- context summary
77	- why external advice helps
78
79	Expected outputs:
80
81	- advisor summary
82	- accepted/rejected advice
83	- decision note
84
85	Artifact expectations:
86
87	- advisor transcript reference only when explicitly captured
88
89	Safety rules:
90
91	- Use only when configured and materially useful.
92	- Treat advisor output as evidence to evaluate, not authority.
93	- Do not send secrets or private prompts without explicit opt-in.
94
95	## Harness Discipline
96
97	- 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.
98	- Prefer richer evidence and clearer stop conditions over adding more workflow names.
99	- Use specialist lanes only when they change the quality of the answer or verification.
100
101	## Runtime Evidence
102
103	Preferred harness for this skill: `critic`.
104
105	When local shell access or a bot wrapper is available, record metadata-only evidence:
106
107	```sh
108	omh runtime record --skill ask --harness critic --status started
109	omh runtime delegate --run <

People who liked this also viewed

6 picks

Type

ask

61stars2forks

View on GitHub

How to install ask?

rlaope/oh-my-hermes/ask

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

Installs into the current project.

Summary

[omh] Hermes adaptation for consulting an external advisor when configured.

Files · 1

View on GitHub

SKILL.md

1	# Ask
2
3	This is a Hermes-native `ask` workflow skill.
4
5	## Why This Exists
6
7	`ask` exists to keep `review` 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: ask: ask Claude as an external advisor to critique this plugin bridge plan before implementation.
19	- Expected behavior: Prepare an advisor prompt, capture the response boundary, and summarize reusable critique.
20	- Why: The user wants outside review before committing to a direction.
21
22	Bad example:
23
24	- Prompt: ask: 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 `ask`.
26	- Why: The request lacks the required inputs or would overclaim work that Hermes did not observe.
27
28	## Completion Checklist
29
30	- Findings or no-issue results are grounded in concrete file, artifact, command, or source evidence.
31	- Open questions, residual risk, and missing verification are named.
32	- Fixes or follow-up work are separate handoffs unless the user explicitly asked to implement them.
33
34	## Recovery Notes
35
36	- If the reviewed target is missing, inspect the requested artifact or ask one target question.
37	- If independent verification is unavailable, report the gap and avoid an approval-style claim.
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: Automation and status (`achievements`, `workspace-audit`, `production-audit`, `automation-blueprint`, `github-event-ops`, `agent-board`, `gateway-intent-card`, `voice-operator`, `+26 more`) - schedules, status, health, and ops review.
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 only when an external advisor is configured and would materially improve the answer.
54
55	Strong routing signals: `ask`, `$ask`, `external advisor`, `claude`, `gemini`
56
57	## Catalog Metadata
58
59	Category: `review`
60	Phase: `external-advice`
61	Hermes role: `reviewer`
62	Quality tier: `evidence-gated`
63
64	Quality bar:
65
66	- Name the workflow target, constraints, validation evidence, and stop condition.
67	- Separate Hermes guidance from executor or wrapper behavior unless evidence proves the step happened.
68
69	Handoff policy:
70
71	Use as optional advice gathering; evaluate the advice in Hermes and delegate coding changes separately.
72
73	Required inputs:
74
75	- question
76	- context summary
77	- why external advice helps
78
79	Expected outputs:
80
81	- advisor summary
82	- accepted/rejected advice
83	- decision note
84
85	Artifact expectations:
86
87	- advisor transcript reference only when explicitly captured
88
89	Safety rules:
90
91	- Use only when configured and materially useful.
92	- Treat advisor output as evidence to evaluate, not authority.
93	- Do not send secrets or private prompts without explicit opt-in.
94
95	## Harness Discipline
96
97	- 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.
98	- Prefer richer evidence and clearer stop conditions over adding more workflow names.
99	- Use specialist lanes only when they change the quality of the answer or verification.
100
101	## Runtime Evidence
102
103	Preferred harness for this skill: `critic`.
104
105	When local shell access or a bot wrapper is available, record metadata-only evidence:
106
107	```sh
108	omh runtime record --skill ask --harness critic --status started
109	omh runtime delegate --run <

People who liked this also viewed

6 picks

Type