fix(i18n): repair verified translation errors across 7 premium dictionaries#199
Merged
Conversation
…naries Full-depth LLM audit of all 11 premium dictionaries (one reviewer per locale, every finding re-verified against the files before fixing; 89 replacements, each applied with an exact expected-count assertion): it (— #1 install market; most damage was residue of the retired es→regex v1): - Brand/file names restored: Slack was "Lento", Notion was "Nozione", SKILL.md was "ABILITÀ.md" - "Tip" was "Mancia" (a monetary tip) → "Consiglio" - "responsskill" ×2 — the old habilidad→skill regex had fired INSIDE "responsabilità" → restored - "ingegneria rapida" ×4 / "Caching rapido" / "Suggerimenti nel mondo reale" → prompt-engineering terms (the exact "Prompt→신속한" mistranslation class this product exists to prevent) - "Percorsi/Corsi Antropici", "modelli antropici" → "… di Anthropic" de: "Discernment" was rendered three ways incl. "Diskriminierungsfähigkeiten" (= discrimination skills) — unified to "Urteilsvermögen"; "KI-Flüssigkeit" (= AI liquid) ×27 → "KI-Fluency"; "Weitere Lesen" → "Mehr lesen"; one broken imperative sentence rewritten. fr: "AI Fluency" was split three ways (Fluence/Fluidité/Maîtrise) → unified to "Maîtrise de l'IA" ×24; prompt terms "invites"/"techniques d'invitation" → prompts/prompting ×5; "efficacement, efficacement" ×2 → "efficacement, de manière efficiente". es: "Competencia en AI" ×3 → "Fluidez en IA" (30 existing uses); MCP primitives "indicaciones" → "prompts"; "Aumentación" → "Aumento". ko: "AI 활용 능력" ×5 → "AI 활용 역량" (34 existing uses). vi: "kỹ thuật kỹ thuật prompt" ×2 → "kỹ thuật prompt". Rejected after verification (not changed): ja/zh keep the feature word "skill" in English consistently (32:0 — deliberate keep-English policy; the ja reviewer's claimed counter-examples did not exist), and all _protected "violations" flagged by reviewers (those are wrong-form lists BY DESIGN). Plugin terms data regenerated. Gates: 527 unit tests, full E2E 19/19, validate, glossary, check:plugin/i18n/dict-coverage/locales/dicts — green. Store zips NOT rebuilt (owner builds on instruction).
heznpc
added a commit
that referenced
this pull request
Jun 10, 2026
… + machine-readable) (#203) Makes the moat visible and the QA state machine-readable instead of claimed: - _meta gains two QA fields in all 11 dictionaries: lastAudited (stamped by the pre-release LLM audit; 2026-06-10 for the audit that shipped in #197/#199) and nativeReview ("recruiting" -> "reviewed" after a native pass). - generate-docs.js gains a LOCALE_QA marker: the README per-locale QA table (entries / last curated / last audit / native-review status) is generated from _meta by `npm run docs`, so the public table cannot drift from reality. - README "Terminology QA" section: the standing pipeline (drift watcher -> same-day dictionary wiring -> CI gates -> real-dictionary regression suite) with the verifiable same-day proof (2026-06-10: #196 detected morning, #201 wired all 11 locales same day) + the generated table + native-reviewer call. - docs/TRANSLATION_QA.md: the three-layer assurance model, honest about what each layer does NOT catch and why no paid API can sit in CI (free-forever). - RELEASE_CHECKLIST step 0: the pre-release LLM dictionary audit is now a release convention, with the _meta.lastAudited stamping step. - CONTRIBUTING "Native language reviewers" section; recruitment umbrella issue #202 (help wanted / good first issue / i18n) with per-locale checklist. Gates: validate, glossary, check:i18n/dict-coverage/locales/dicts/plugin, 527 unit tests, lint, prettier — green.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Full-depth audit of the premium dictionaries (one LLM reviewer per locale over all ~1,100 entries each; every finding re-verified against the actual files before fixing — several reviewer claims were refuted and NOT applied). 89 replacements, each with an exact expected-count assertion.
Highlights (it — #1 install market; residue of the retired es→regex v1)
Other locales
Refuted (no change)
ja/zh "skill" stays English consistently (32:0 — deliberate keep-English; the reviewer's counter-examples didn't exist); all
_protected"brand violations" (wrong-form lists are BY DESIGN).Plugin terms regenerated. Gates: 527 unit · E2E 19/19 · validate/glossary/check:* — green. Store zips deliberately not rebuilt.
🤖 Generated with Claude Code