From copilot-al-configs
Guides the AL translation phase — when to translate, how to handle XLF files, and quality expectations for localized texts.
How this skill is triggered — by the user, by Claude, or both
Slash command
/copilot-al-configs:al-translation-phaseThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this skill after implementation and core review are complete and the app builds successfully.
Use this skill after implementation and core review are complete and the app builds successfully.
al-translator agent or perform translation manually.g.xlf fileal-develop-orchestrator or user explicitly triggers the translation phaseal_build or buildAlPackage) to generate the current .g.xlf.Translations/:
a. Synchronize with refreshXlf.
b. Load glossary (glossary.tsv + getGlossaryTerms).
c. Load existing translations as style reference (getTranslatedTextsMap).
d. Fetch untranslated texts in batches of up to 100 (getTextsToTranslate).
e. Translate, validate, and save each batch (saveTranslatedTexts).
f. Repeat until no untranslated texts remain.
g. Final refreshXlf to confirm completion.%1, %2) in position and formatmaxLength constraints — measure and shorten before savingrefreshXlf — sync XLF with generated .g.xlfgetTextsToTranslate — fetch untranslated textssaveTranslatedTexts — save translations with stategetTranslatedTextsMap / getTranslatedTextsByState — existing translationsgetGlossaryTerms — glossary for target languagegetTextsByKeyword — search texts by keywordbuildAlPackage — compile and generate .g.xlfFall back to direct XLF file editing:
<trans-unit> elements without <target> or with state="needs-translation"<target> elements with the translationstate="needs-review-translation" on new translationsal-translator — the dedicated translation worker that executes this workflowal-develop-orchestrator — triggers the translation phase after successful buildnpx claudepluginhub hyzadan/copilot-al-configsProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.