Ask
This is a Hermes-native ask workflow skill.
Why This Exists
ask exists to keep review 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: ask: ask Claude as an external advisor to critique this plugin bridge plan before implementation.
- Expected behavior: Prepare an advisor prompt, capture the response boundary, and summarize reusable critique.
- Why: The user wants outside review before committing to a direction.
Bad example:
- Prompt: ask: 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
ask.
- Why: The request lacks the required inputs or would overclaim work that Hermes did not observe.
Completion Checklist
- Findings or no-issue results are grounded in concrete file, artifact, command, or source evidence.
- Open questions, residual risk, and missing verification are named.
- Fixes or follow-up work are separate handoffs unless the user explicitly asked to implement them.
Recovery Notes
- If the reviewed target is missing, inspect the requested artifact or ask one target question.
- If independent verification is unavailable, report the gap and avoid an approval-style claim.
Workflow Lane
- Current lane: Automation and status (
achievements, workspace-audit, production-audit, automation-blueprint, github-event-ops, github-issue-intake, buzz, agent-board, +35 more) - schedules, status, health, and ops review.
- If intent belongs to another lane, hand back to
oh-my-hermes or name the adjacent workflow.
- Shared product, routing, compatibility, and evidence rules:
omh-routing/references/skill-common-rail.md.
Use When
Use only when an external advisor is configured and would materially improve the answer.
Strong routing signals: `ask`, `$ask`, `external advisor`, `ask claude`, `ask gemini`, `consult claude`, `consult gemini`, `opinion from claude`, `opinion from gemini`, `second opinion`, `claude 의견`, `gemini 의견`
Catalog Metadata
Category: review
Phase: external-advice
Hermes role: reviewer
Quality tier: evidence-gated
Reasoning demand: standard
Quality bar:
- Name the workflow target, constraints, validation evidence, and stop condition.
- Separate Hermes guidance from executor or wrapper behavior unless evidence proves the step happened.
Handoff policy:
Use as optional advice gathering; evaluate the advice in Hermes and delegate coding changes separately.
Required inputs:
- question
- context summary
- why external advice helps
Expected outputs:
- advisor summary
- accepted/rejected advice
- decision note
Artifact expectations:
- advisor transcript reference only when explicitly captured
Safety rules:
- Use only when configured and materially useful.
- Treat advisor output as evidence to evaluate, not authority.
- Do not send secrets or private prompts without explicit opt-in.
Runtime Evidence
Preferred harness for this skill: critic.
omh runtime record --skill ask --harness critic --status started
Record observed delegation results; otherwise return not_available or not_observed.
Prepared OMH routing is not execution, review, CI, merge-readiness, or merge evidence.
- When wrapper metadata includes
memory_review_card/v1 or handoff_context_pack/v1, treat it as reviewed OMH-local or wrapper-supplied context only. Use conflict-free context summaries to shape plans and handoffs, but do not claim Hermes internal memory was read or changed.
Preserve workflow intent and stop conditions; verify before claiming completion.
Use Hermes-native subagent/delegation features when available: native subagents -> Hermes delegation when available, otherwise sequential lanes.
Shared product, compatibility, topology, memory, harness, and execution rules: omh-routing/references/skill-common-rail.md. Load it when applicable; otherwise name an unavailable capability.
1---2name: omh-ask3description: [omh] Hermes adaptation for consulting an external advisor when configured. Use when the user says: ask, external advisor, ask claude, ask gemini, consult claude, consult gemini, opinion from claude, opinion from gemini.4---5
6# Ask
7
8This is a Hermes-native `ask` workflow skill.
9
10## Why This Exists
11
12`ask` exists to keep `review` work explicit, evidence-backed, and inside the Hermes/executor boundary instead of relying on ad hoc chat narration.
13
14## Do Not Use When
15
16- The request is casual chat, a status-only acknowledgement, or another workflow has stronger routing evidence.
17- The user needs implementation, review, CI, merge, or external publishing evidence that has not been delegated or observed.
18
19## Examples
20
21Good example:
22
23- Prompt: ask: ask Claude as an external advisor to critique this plugin bridge plan before implementation.
24- Expected behavior: Prepare an advisor prompt, capture the response boundary, and summarize reusable critique.
25- Why: The user wants outside review before committing to a direction.
26
27Bad example:
28
29- Prompt: ask: treat casual chat or unaccepted work as if this workflow already produced verified results.
30- Expected behavior: Ask a clarification question or route to a narrower workflow instead of forcing `ask`.
31- Why: The request lacks the required inputs or would overclaim work that Hermes did not observe.
32
33## Completion Checklist
34
35- Findings or no-issue results are grounded in concrete file, artifact, command, or source evidence.
36- Open questions, residual risk, and missing verification are named.
37- Fixes or follow-up work are separate handoffs unless the user explicitly asked to implement them.
38
39## Recovery Notes
40
41- If the reviewed target is missing, inspect the requested artifact or ask one target question.
42- If independent verification is unavailable, report the gap and avoid an approval-style claim.
43
44## Workflow Lane
45
46- Current lane: **Automation and status** (`achievements`, `workspace-audit`, `production-audit`, `automation-blueprint`, `github-event-ops`, `github-issue-intake`, `buzz`, `agent-board`, `+35 more`) - schedules, status, health, and ops review.
47- If intent belongs to another lane, hand back to `oh-my-hermes` or name the adjacent workflow.
48- Shared product, routing, compatibility, and evidence rules: `omh-routing/references/skill-common-rail.md`.
49
50## Use When
51
52Use only when an external advisor is configured and would materially improve the answer.
53
54 Strong routing signals: `ask`, `$ask`, `external advisor`, `ask claude`, `ask gemini`, `consult claude`, `consult gemini`, `opinion from claude`, `opinion from gemini`, `second opinion`, `claude 의견`, `gemini 의견`
55
56## Catalog Metadata
57
58Category: `review`
59Phase: `external-advice`
60Hermes role: `reviewer`
61Quality tier: `evidence-gated`
62Reasoning demand: `standard`
63
64Quality 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
69Handoff policy:
70
71Use as optional advice gathering; evaluate the advice in Hermes and delegate coding changes separately.
72
73Required inputs:
74
75- question
76- context summary
77- why external advice helps
78
79Expected outputs:
80
81- advisor summary
82- accepted/rejected advice
83- decision note
84
85Artifact expectations:
86
87- advisor transcript reference only when explicitly captured
88
89Safety 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## Runtime Evidence
96
97Preferred harness for this skill: `critic`.
98
99```sh
100omh runtime record --skill ask --harness critic --status started
101```
102
103Record observed delegation results; otherwise return `not_available` or `not_observed`.
104Prepared OMH routing is not execution, review, CI, merge-readiness, or merge evidence.
105- When wrapper metadata includes `memory_review_card/v1` or `handoff_context_pack/v1`, treat it as reviewed OMH-local or wrapper-supplied context only. Use conflict-free context summaries to shape plans and handoffs, but do not claim Hermes internal memory was read or changed.
106Preserve workflow intent and stop conditions; verify before claiming completion.
107
108Use Hermes-native subagent/delegation features when available: native subagents -> Hermes delegation when available, otherwise sequential lanes.
109
110Shared product, compatibility, topology, memory, harness, and execution rules: `omh-routing/references/skill-common-rail.md`. Load it when applicable; otherwise name an unavailable capability.