agentmods.dev

translationReviewer

translationReviewer is a skill for Claude Code from AlirezaSoltaniJazi/Skillnir. It costs 162 tokens per session (2,898 once invoked), scanned A, original, MIT.

A review checklist for translation and localization changes in code projects. It checks language catalogs and translation pull requests for missing text, broken placeholders, plural rules, formatting, and fallback problems across common translation file formats.

In plain words
What is it for?
Use it to review changes from translation services such as Lokalise, Crowdin, or Phrase, compare locales with the base language, and audit numbers, dates, and currencies in translated strings.
Why use it?
It helps catch errors that can make translated screens show the wrong text, lose variable values, or fall back to the wrong language. It also avoids reviewing translations without checking the project's own conventions and tools.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents.

not rated 9repo 12d ago A scan 162 tokens original MIT

Good fit Use it to review changes from translation services such as Lokalise, Crowdin, or Phrase, compare locales with the base language, and audit numbers, dates, and currencies in translated strings.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/alirezasoltanijazi/skillnir/translationreviewer
View source ↗ AlirezaSoltaniJazi/Skillnir
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add AlirezaSoltaniJazi/Skillnir --skill translationreviewer
Clone the repo
git clone --depth 1 https://github.com/AlirezaSoltaniJazi/Skillnir

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for translationReviewer

README.md
[![agentmods](https://agentmods.dev/badge/skills/alirezasoltanijazi/skillnir/translationreviewer/github.svg)](https://agentmods.dev/skills/alirezasoltanijazi/skillnir/translationreviewer)
Your own site
<a href="https://agentmods.dev/skills/alirezasoltanijazi/skillnir/translationreviewer"><img src="https://agentmods.dev/badge/skills/alirezasoltanijazi/skillnir/translationreviewer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for translationReviewer

Your own site · 80×15
<a href="https://agentmods.dev/skills/alirezasoltanijazi/skillnir/translationreviewer"><img src="https://agentmods.dev/badge/skills/alirezasoltanijazi/skillnir/translationreviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 162 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,898 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00162 $0.02898
Opus 5.5 $0.00065 $0.01159
Sonnet 5.5 $0.00032 $0.00580
Haiku 4.5 $0.00016 $0.00290

Measured 11d ago against content hash 5b2c4942bc8e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

translationReviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/check_catalogs.py, scripts/dump_side_by_side.py, scripts/locale_facts.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.data/skills/translationReviewer/SKILL.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Before You Start

  1. Say "Using: translationReviewer skill" at the start of the response.
  2. Read LEARNED.md first — project conventions (paths, served languages, TMS, glossary, do-not-translate terms) and user preferences override defaults here.
  3. Find the project's own tooling: grep for check_translation*, *translation*checklist*, update_translations*, .lokalise.yml, crowdin.yml. Run project checkers in addition to this skill's.

When to Use

  1. A PR that updates catalogs from a TMS or adds translations for a feature
  2. A backport/forward-port of such a PR (parity check)
  3. "This string shows English / the raw key / braces / blank in language X"
  4. Auditing locale formatting (numbers, dates, currency) in strings
  5. Writing the review as PR comments, a ticket, or a shareable artifact

Do NOT Use

  • Implementing i18n in code (extracting strings, wiring Intl) — frontend/backend skill
  • Translating new content from scratch — translate directly; use this skill to review the result
  • Pure copywriting of the English source — content/UX writing

Workflow

  1. Scope — gh pr view <n> --json title,body,state,baseRefName,headRefOid,files,commits,reviews; fetch the head (git fetch origin pull/<n>/head:pr-<n>); note base, merge state, CI, counterpart PRs (gh pr list --state all --search <ticket>), non-catalog files (tooling, tests), commits after the export.
  2. Mechanical pass — <skill>/scripts/validate-catalogs.sh origin/<base> pr-<n> <brand>… (project checker if present + check_catalogs.py + msgfmt -c). For a merged PR use <merge>^1 <merge>. Read ERROR, then WARN, then the TERM SHIFTS summary. Add --all once to list OLD issues.
  3. Regressions and tooling — emptied/removed strings, case regressions, .po without .mo; read any export/import script diff like production code (review-checklist.md §8).
  4. Consumption — for new keys, push/email/PDF texts and not-in-source findings, confirm which loader reads which file and what an empty value renders (consumption-and-fallback.md). Test the loader in one line when possible; do not assume fallback.
  5. Content — scripts/dump_side_by_side.py --base … --head … [--langs] [--rewritten-only] [--grep]. Read German in full and 2–3 more languages; for term shifts, grep the new term with the old gender's markers. Big PRs: spawn language-reviewer per language family in parallel.
  6. Locale formats — any number, date, time, currency, percent or unit inside a string is checked against locale-formats.md (CLDR, generated by scripts/locale_facts.py).
  7. Verify each finding before reporting: re-read the exact string at the head ref, check it is NEW, and drop false positives (inflected brands in fi, localized acronyms, legit spelled-out numbers).
  8. Report with report-template.md: verdict, blocking, fix-in-TMS, minor, OLD context, next steps. Publish an artifact if asked. Draft PR/Jira comments; post only after explicit approval.

Read the full file on GitHub · 164 lines

Files

What ships with it

16 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 164 lines · 162 tokens per session scan A 5b2c4942bc8e

Subscribe to this mod's changes

translationReviewer is a skill published in the GitHub repository AlirezaSoltaniJazi/Skillnir (9 stars, last pushed 12d ago), licensed MIT. It adds 162 tokens to every session and 2,898 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-26.

Localization
Related

translationReviewer compared with skills from other repositories

translationReviewer next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
translationReviewerAlirezaSoltaniJazi/SkillnirSkill912d agoMITA162Claude Code
intl-expansionalirezarezvani/claude-skillsSkill29kyesterdayMITA27Claude Code
azure-ai-translation-text-pymicrosoft/skillsSkill3.2kyesterdayMITA60Claude Code
chinese-documentationjnMetaCode/superpowers-zhSkill8.5k11d agoMITA62Claude Code
hardenfengshao1227/ccg-workflowSkill6.0k5d agoMITA62Claude Code
edit-sitemicrosoft/power-platform-skillsSkill1.1kyesterdayMITA104Claude Code
asc-subscription-localizationrorkai/app-store-connect-cli-skillsSkill1.1kyesterdayMITA60Claude Code