Translate

Activation Boundary

This is a tag-only worker skill. Use it only after execute or execute-one selects an exact <@translate...> annotation in a target document. Never activate it from ordinary chat, semantic similarity, or another non-router skill. Without that handoff, change nothing.

Translate the surrounding block into the requested language, then consume the tag.

Tag

<@translate: target language>

Example: <@translate: German>.

Input

• File path — the document being processed.
• Surrounding block — the maximal run of non-blank lines containing the tag; blank lines bound it.
• Prompt — the target language, optionally with style notes.

Workflow

1. Read the surrounding block; read the full file if terminology context helps.
2. Translate the authored prose into the target language. Leave citation keys, code spans, and LaTeX commands untranslated.
3. Write the result back: replace the surrounding block (including the <@translate: ...> tag) with the translation.

Scope Modifiers

• Protect << >> — content stays in the original language, untouched; remove the delimiters in the output.
• Field (( )) — translate only inside the field; remove the delimiters in the output.

Context References

Double-backtick references in the prompt (for example a glossary file) are inputs; resolve paths relative to the document's directory unless absolute.

Rules

• Consume this tag and its consumed modifier delimiters. Preserve every unrelated tag, <@comment: ...> tag, <@chat-model> block, and contextual literal/example byte-for-byte.
• If no target language is given or a referenced file is unreadable, fail cleanly: leave the tag, change nothing, report the error.