BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.coscup.org//coscup-2026//talk//SAMSGH
BEGIN:VTIMEZONE
TZID:CST
BEGIN:STANDARD
DTSTART:20000101T000000
RRULE:FREQ=YEARLY;BYMONTH=1
TZNAME:CST
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-coscup-2026-SAMSGH@pretalx.coscup.org
DTSTART;TZID=CST:20260809T134000
DTEND;TZID=CST:20260809T141000
DESCRIPTION:Open source educational materials often come with their own “
 dialects” of Markdown. For example\, [The Carpentries Workbench](https:/
 /carpentries.github.io/workbench/) extends Markdown with special directive
 s\, metadata blocks\, and conventions that are essential for building less
 ons. These are not just formatting details—they are part of the executab
 le structure of the content.\n\nToday\, AI tools make it easy to translate
  documentation quickly. You can generate a full draft in seconds. But if y
 ou’ve tried this on structured teaching materials\, you may have seen wh
 at happens next: broken builds\, modified syntax\, or translations that ig
 nore the intent of the lesson design. AI is powerful\, but it doesn’t au
 tomatically understand which parts of a document must never be touched.\n\
 nIn this talk\, I’ll share a practical approach to solving this problem 
 using “[agent skills](https://agentskills.io/home)” designed specifica
 lly for translating structured technical content. These skills act as guar
 drails: they protect non-translatable syntax while allowing AI to focus on
  natural language parts. The goal is not just speed\, but safe and maintai
 nable translation workflows.\n\nI’ll present a real-world example from t
 he [Bioconductor](https://www.bioconductor.org/) community\, where we appl
 ied this approach to translate Carpentries-style training materials. With 
 these agent skills\, we were able to significantly accelerate translation 
 while keeping lessons fully buildable and consistent.\n\nMore importantly\
 , this is not just a tooling story—it’s a community story. These trans
 lated materials are now being used in workshops across different regions\,
  enabling participants to learn in their own languages. Translation become
 s more than a task\; it becomes an entry point for contributing to open so
 urce. You don’t need to start with code—you can start by helping your 
 local community access knowledge.\n\nAt COSCUP\, where community and openn
 ess are at the center\, this talk aims to share both practical techniques 
 and a perspective: AI can amplify community efforts\, but only if we desig
 n workflows that respect how open source projects actually work.\n\nIf you
  care about documentation\, localization\, or making open source more incl
 usive\, this talk is for you.
DTSTAMP:20260713T142757Z
LOCATION:TR410
SUMMARY:Translating Open Source Lessons with AI (Without Breaking Them) - K
 ozo Nishida
URL:https://pretalx.coscup.org/coscup-2026/talk/SAMSGH/
END:VEVENT
END:VCALENDAR