Localization Review
This is a Hermes-native localization-review workflow skill.
Why This Exists
localization-review makes terminology, context, cultural fit, and locale QA reviewable without treating a drafted translation as a published or visually validated release.
Do Not Use When
- The request is a short sentence or word translation or rewrite with no product or locale QA context; answer directly or use
content-operator.
- The user needs fresh rendered UI evidence, clipping checks, or a visual PASS/REVISE/BLOCK verdict; use
visual-qa.
- The user asks to edit locale files, push a translation-management-system job, publish strings, or configure localization settings; use
workspace-file-operator or connector-operator with explicit target and authority.
- The request asks for a regulatory or contractual conclusion about translated legal text; use
legal-compliance-review.
Examples
Good example:
- Prompt: Review our Korean checkout strings for terminology consistency, cultural fit, and context gaps before launch.
- Expected behavior: Prepare the locale and source-version brief, glossary choices, issue matrix, and locale QA criteria.
- Why: The product-release context needs localization review beyond a one-off translation.
Bad example:
- Prompt: Translate 'Your trial ends tomorrow' into Korean.
- Expected behavior: Answer directly or route to
content-operator, not localization-review.
- Why: A one-off sentence has no product locale QA or release-review objective.
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: Materials and visual summaries (
design-orchestration, apple-design, design-quality-gate, award-bar-score, frontend, accessibility-audit, visual-qa, content-operator, +6 more) - web, accessibility, visual QA, files, and packages.
- 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 when multiple strings, a product surface, a market release, or a locale-sensitive document needs terminology, context, consistency, cultural-fit, and QA guidance beyond one-off translation.
Strong routing signals: `localization review`, `translation QA`, `locale glossary`, `현지화 검토`, `번역 QA`, `용어집`
Catalog Metadata
Category: review
Phase: localization-review
Hermes role: reviewer
Quality tier: review-gated
Reasoning demand: standard
Quality bar:
- Ground terminology and cultural-fit choices in locale, audience, context, and source version.
- Make string severity, review ownership, and rendered QA gaps explicit.
Handoff policy:
Keep domain framing, clarification, source/evidence synthesis, draft outputs, and next-work routing in Hermes. A prepared brief, review, reply, or plan is not an external action, approval, filing, send, publish, data mutation, implementation, review, CI, or merge claim. Prepare a connector, file, coding, or human-review handoff only when the user explicitly accepts that next step; report it only from observed evidence. Hermes may draft and review language guidance; it does not alter locale files, upload strings, publish translations, validate a rendered build, or claim market approval.
Required inputs:
- locale
- audience
- source version
- product or content context
Expert clarification questions:
locale
- English: Which target locale should this localization review cover?
- Korean: 이 현지화 검토의 대상 로캘은 무엇인가요?
Expected outputs:
- locale/audience/context and source-version brief
- approved-term glossary and transcreation/localization choices
- string/content issue matrix with context, severity, and review owner
- locale QA acceptance criteria and handoff/observed-evidence gaps
Artifact expectations:
- prepared localization review when a wrapper captures it
Safety rules:
- Separate language guidance from rendered UI evidence and market approval.
- Do not claim locale-file changes, translation upload, publication, or rendered validation.
Runtime Evidence
Preferred harness for this skill: critic.
omh runtime record --skill localization-review --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.
- Treat wrapper memory/context summaries as advisory local context, not proof of opaque Hermes memory reads or changes.
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-localization-review"
3description: "[omh] Make a product or content release locale-ready with terminology, cultural-fit, and quality-review guidance. Use when the user says: localization review, translation QA, locale glossary, 현지화 검토, 번역 QA, 용어집."
4metadata:
5 hermes:
6 tags: [workflow, oh-my-hermes, review]
7 category: review
8 phase: localization-review
9 role: reviewer
10 quality_tier: review-gated
11---
12
13# Localization Review
14
15This is a Hermes-native `localization-review` workflow skill.
16
17## Why This Exists
18
19`localization-review` makes terminology, context, cultural fit, and locale QA reviewable without treating a drafted translation as a published or visually validated release.
20
21## Do Not Use When
22
23- The request is a short sentence or word translation or rewrite with no product or locale QA context; answer directly or use `content-operator`.
24- The user needs fresh rendered UI evidence, clipping checks, or a visual PASS/REVISE/BLOCK verdict; use `visual-qa`.
25- The user asks to edit locale files, push a translation-management-system job, publish strings, or configure localization settings; use `workspace-file-operator` or `connector-operator` with explicit target and authority.
26- The request asks for a regulatory or contractual conclusion about translated legal text; use `legal-compliance-review`.
27
28## Examples
29
30Good example:
31
32- Prompt: Review our Korean checkout strings for terminology consistency, cultural fit, and context gaps before launch.
33- Expected behavior: Prepare the locale and source-version brief, glossary choices, issue matrix, and locale QA criteria.
34- Why: The product-release context needs localization review beyond a one-off translation.
35
36Bad example:
37
38- Prompt: Translate 'Your trial ends tomorrow' into Korean.
39- Expected behavior: Answer directly or route to `content-operator`, not `localization-review`.
40- Why: A one-off sentence has no product locale QA or release-review objective.
41
42## Completion Checklist
43
44- Findings or no-issue results are grounded in concrete file, artifact, command, or source evidence.
45- Open questions, residual risk, and missing verification are named.
46- Fixes or follow-up work are separate handoffs unless the user explicitly asked to implement them.
47
48## Recovery Notes
49
50- If the reviewed target is missing, inspect the requested artifact or ask one target question.
51- If independent verification is unavailable, report the gap and avoid an approval-style claim.
52
53## Workflow Lane
54
55- Current lane: **Materials and visual summaries** (`design-orchestration`, `apple-design`, `design-quality-gate`, `award-bar-score`, `frontend`, `accessibility-audit`, `visual-qa`, `content-operator`, `+6 more`) - web, accessibility, visual QA, files, and packages.
56- If intent belongs to another lane, hand back to `oh-my-hermes` or name the adjacent workflow.
57- Shared product, routing, compatibility, and evidence rules: `omh-routing/references/skill-common-rail.md`.
58
59## Use When
60
61Use when multiple strings, a product surface, a market release, or a locale-sensitive document needs terminology, context, consistency, cultural-fit, and QA guidance beyond one-off translation.
62
63 Strong routing signals: `localization review`, `translation QA`, `locale glossary`, `현지화 검토`, `번역 QA`, `용어집`
64
65## Catalog Metadata
66
67Category: `review`
68Phase: `localization-review`
69Hermes role: `reviewer`
70Quality tier: `review-gated`
71Reasoning demand: `standard`
72
73Quality bar:
74
75- Ground terminology and cultural-fit choices in locale, audience, context, and source version.
76- Make string severity, review ownership, and rendered QA gaps explicit.
77
78Handoff policy:
79
80Keep domain framing, clarification, source/evidence synthesis, draft outputs, and next-work routing in Hermes. A prepared brief, review, reply, or plan is not an external action, approval, filing, send, publish, data mutation, implementation, review, CI, or merge claim. Prepare a connector, file, coding, or human-review handoff only when the user explicitly accepts that next step; report it only from observed evidence. Hermes may draft and review language guidance; it does not alter locale files, upload strings, publish translations, validate a rendered build, or claim market approval.
81
82Required inputs:
83
84- locale
85- audience
86- source version
87- product or content context
88
89Expert clarification questions:
90- `locale`
91 - English: Which target locale should this localization review cover?
92 - Korean: 이 현지화 검토의 대상 로캘은 무엇인가요?
93
94Expected outputs:
95
96- locale/audience/context and source-version brief
97- approved-term glossary and transcreation/localization choices
98- string/content issue matrix with context, severity, and review owner
99- locale QA acceptance criteria and handoff/observed-evidence gaps
100
101Artifact expectations:
102
103- prepared localization review when a wrapper captures it
104
105Safety rules:
106
107- Separate language guidance from rendered UI evidence and market approval.
108- Do not claim locale-file changes, translation upload, publication, or rendered validation.
109
110## Runtime Evidence
111
112Preferred harness for this skill: `critic`.
113
114```sh
115omh runtime record --skill localization-review --harness critic --status started
116```
117
118Record observed delegation results; otherwise return `not_available` or `not_observed`.
119Prepared OMH routing is not execution, review, CI, merge-readiness, or merge evidence.
120- Treat wrapper memory/context summaries as advisory local context, not proof of opaque Hermes memory reads or changes.
121Preserve workflow intent and stop conditions; verify before claiming completion.
122
123Use Hermes-native subagent/delegation features when available: native subagents -> Hermes delegation when available, otherwise sequential lanes.
124
125Shared product, compatibility, topology, memory, harness, and execution rules: `omh-routing/references/skill-common-rail.md`. Load it when applicable; otherwise name an unavailable capability.