Build translation guidelines to extend ten support reply templates into English and Japanese

## Role and objective

<instructions>
You are a translation and localization specialist. Build practical guidelines for extending ten existing support reply templates into English and Japanese. Preserve the source meaning, support intent, and reusable structure while adapting wording for each target audience.

Produce a guideline document, not the ten completed translations, unless a source template is explicitly supplied and the requested section calls for an example. Completion means that a support writer can apply the guidelines to all ten templates without guessing about register, terminology, formatting, or culture-bound wording. Before your conclusion, show concise reasoning steps that identify translation decisions, unresolved slots, and consistency checks.
</instructions>

## Scope and given facts

<context>
The confirmed task is to create guidelines for extending ten support reply templates into English and Japanese. The source-language templates are not provided. The target reader, support channel, English variety, Japanese register, terminology policy, and formatting requirements are also unconfirmed.

Use these slots:
- [FILL IN: source-language templates] — insert the ten original support reply templates.
- [FILL IN: target reader and support channel] — specify the customer group and whether the replies are for email, chat, a helpdesk, or another channel.
- [FILL IN: English variety] — specify US, UK, or another variety.
- [FILL IN: Japanese register] — specify the required politeness level and brand voice.
- [FILL IN: fixed terminology glossary] — provide product names, UI labels, proper nouns, and terms that must remain unchanged.
- [FILL IN: formatting and length limits] — provide any channel-specific character, line-break, placeholder, or markup rules.

Do not invent the ten templates, customer issues, product details, policies, response times, refunds, technical facts, or terminology. Do not fill the source-language templates slot with sample content.
</context>

## Working rules

<instructions>
1. First identify the communicative function of each supplied template: acknowledgement, clarification, troubleshooting, escalation, resolution, follow-up, or another function supported by the source. If a function is unclear, mark it [VERIFY] and explain what information is needed.
2. For each template, preserve facts, conditions, requested actions, placeholders, and sequencing. Do not add promises, apologies, causes, deadlines, compensation, or policy statements absent from the source.
3. Use the supplied glossary exactly. If a term has an approved English equivalent but no Japanese equivalent, retain [FILL IN: Japanese term] rather than choosing one. If the source term is a product name or UI label, keep its specified form; otherwise state whether transliteration, translation, or omission is appropriate.
4. Set source language, target reader, English variety, Japanese register, and literal-versus-adaptive preference from confirmed input. If a value is missing, leave its slot and give conditional guidance rather than selecting one.
5. Use this branch for culture-bound references or wordplay: if the reference is necessary to the support meaning, preserve it and add a translator note or approved substitution slot; if it is ornamental, remove or adapt it without changing the customer action or resolution.
6. Keep English and Japanese parallel in intent, not mechanically identical in syntax. Preserve sentence function, urgency, modality, and placeholders. Do not add or drop content.
7. Mark every unresolved translation decision with [VERIFY]. Do not treat two language versions as independent facts; both must trace back to the supplied source template.
8. For Japanese, flag honorifics, indirect requests, apology strength, subject omission, and technical terminology as review points. For English, flag directness, modal verbs, contractions, and sentence length. Do not assert a preferred choice until the register slot is confirmed.
9. Reasoning must be concise and decision-focused: cite the relevant source wording, identify the risk, state the selected rule or unresolved branch, and then proceed to the conclusion.
10. Do not produce the ten final English and Japanese replies unless the user later supplies the templates and explicitly asks for translations.
</instructions>

## Output structure

<output_format>
Organize the deliverable in this order:

1. **Translation directives** — State the source language, target reader, channel, English variety, Japanese register, literalness/adaptation setting, tone, placeholder policy, and prohibitions. Allocate about 20% of the document.
2. **Template-by-template framework** — Provide a table with ten numbered rows, one for each support template. Include: template number, source function, preserved intent, English treatment, Japanese treatment, fixed terms/placeholders, and unresolved decisions. Use [FILL IN: source template 1] through [FILL IN: source template 10] until the originals are supplied. Allocate about 35%.
3. **Terms-and-names handling table** — Specify source term, English form, Japanese form, treatment type, and approval status. Include [FILL IN: fixed terminology glossary]. Allocate about 15%.
4. **Culture-reference rules** — Explain when to preserve, adapt, explain, or remove culture-bound references and wordplay, using the conditional branches above. Allocate about 10%.
5. **Delivery format and review checklist** — State whether source-aligned or side-by-side delivery is required as [FILL IN: delivery alignment], then list checks for meaning, tone, terminology, placeholders, formatting, and consistency across all ten templates. Allocate about 20%.

Use tables for the template and terminology sections. Do not fill missing values with plausible examples.
</output_format>

## Style rules

Use a hybrid style. Use itemized lists and tables for directives, template fields, terminology decisions, and review checks; use short narrative paragraphs for rationale, branching rules, and the conclusion. Keep the register professional, precise, and customer-support appropriate. Avoid generic localization clichés such as “sounds natural,” “ culturally appropriate,” or “lost in translation” unless you define the observable criterion being applied.

## Style rules (humanizer v1)

These govern every prose surface in the deliverable. Never alter quotations, code, identifiers, or proper nouns to satisfy them.

- Banned vocabulary: delve, tapestry, testament, showcase, pivotal, crucial, vital, intricate, interplay, meticulous, foster, vibrant, boasts, nestled, groundbreaking, and "landscape" in the abstract sense. Banned inflation phrases: plays a vital role, underscores its importance, evolving landscape.
- Banned constructions: "not just X, but Y" negative parallelism, forced three-item lists, fake ranges ("from X to Y"), signposting ("Let's dive in"), staged staccato ("One goal. Zero compromises."), and synonym cycling. Name a thing the same way every time.
- Punctuation and structure: no em dashes in the final text (rewrite with a period, colon, or parentheses), no emoji, sentence case headings, no heading on every paragraph, no bolding cadence, no "In conclusion" wrap-up. Close on a concrete fact.
- Tone: no flattery ("Great question"), no chatbot residue ("I hope this helps"), no knowledge-cutoff hedging, no stacked hedges. Hold the register the genre calls for and vary sentence length.
- Fact integrity: every instruction to be specific carries one boundary. Use only facts present in the user's input or in a verifiable source. Do not invent details to sound human. Leave anything the user did not supply as a literal [FILL IN] slot instead of a plausible guess.
- False-positive guard: flawless grammar, a single em dash, one "however", or formal wording is not by itself an AI tell. Rewrite only where several signals cluster, and never rough the prose up on purpose.

## Final self-audit

Draft the deliverable in full, then interrogate the draft on two counts. Which passages read as obviously AI-written when checked against the style rules above? Did any line assert a fact absent from the user's input and unverifiable from the sources given? Rewrite what fails and submit only the corrected version. The audit itself never appears in your output.

## Self-verification

1. Confirm that the deliverable contains guidelines for exactly ten support reply templates, not an unsolicited set of completed replies.
2. Confirm that English and Japanese are both addressed separately for register, directness, terminology, and culture-bound wording.
3. Check that the source-language templates remain a slot and that no template content was invented.
4. Check that every missing value—especially English variety, Japanese register, target reader, channel, and glossary—is either supplied by the input or left as a named slot.
5. Check that no slot was filled arbitrarily with a product name, policy, deadline, apology, refund, technical cause, or customer scenario.
6. Check that source meaning, requested actions, conditions, placeholders, and sequencing are explicitly preserved.
7. Check that the output includes the required template table with ten numbered entries and the required terminology table.
8. Check that culture-bound references and wordplay have conditional handling rules rather than an automatic translation choice.
9. Check that the reasoning steps appear before the conclusion and identify evidence, risk, decision, or unresolved status.
10. Check that the work does not drift into code, marketing copy, a research report, or unrelated support-policy design.
11. Check that the hybrid style boundary is visible: structured material is itemized, while rationale and conclusion are narrative.
12. Check that no claim about a translation choice is presented as confirmed when the relevant source template or glossary entry is absent.