New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Translation Audit

by vexl-it in vexl-it/vexl

Translations audit — fill missing keys in every shipped locale, re-translate keys whose English changed, delete stale ones, flag suspicious values.

GPL-3.0Auto-check passedWriting & Content

Install Translation Audit

skills CLI
$ npx skills add vexl-it/vexl --skill translation-audit -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install vexl-it/vexl translation-audit --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/vexl-it/vexl.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/translation-audit .claude/skills/translation-audit && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
translation-audit
GitHub stars
125
Token cost
~693 tokens
SKILL.md length
353 words
Files
1
Skills in repo
3
Repo updated
First seen
Licence
GPL-3.0

At a glance

Translations audit — fill missing keys in every shipped locale, re-translate keys whose English changed, delete stale ones, flag suspicious values.

  • Works in 7 steps: Mode: read the marker file and ask the… → Stale cleanup: run pnpm… → Scope: run pnpm check:translations… → …
  • Tasks that involve Translation
  • Calls pnpm, git and node

What it does

Translation Audit is an agent skill from vexl-it/vexl. Translations audit — fill missing keys in every shipped locale, re-translate keys whose English changed, delete stale ones, flag suspicious values.

Its SKILL.md is about 690 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Writing & Content, covering Translation. It works with pnpm. The licence is GPL-3.0.

When your agent uses it

  • Tasks that involve Translation

Example prompts

  • “Use the translation-audit skill to translation audit — fill missing keys in every shipped locale, re-translate keys whose English changed, delete…”
  • “/translation-audit”

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Mode: read the marker file and ask the user which audit to run
  2. Stale cleanup: run pnpm check:translations --fix-stale — mechanically deletes orphan keys and stray locale files. Record what it removed…
  3. Scope: run pnpm check:translations --json and group the missingKey, missingPluralForm, and placeholderMismatch errors by locale. On a diff…
  4. Fan out: spawn translator subagents — model, prompt contents, and translator rules are in docs/translating.md. Per-locale in parallel…
  5. Verify: re-run pnpm check:translations and dispatch follow-up fixes until it exits clean. legalDocs entries in the JSON report are…
  6. Update the marker: write the current git rev-parse HEAD and ISO timestamp into translation-audit.json; commit it together with the…
  7. Report to the user: keys translated per locale, keys re-translated for changed English, stale keys deleted, suspicious values flagged…

What it can do on your machine

Read from SKILL.md and the folder at commit d2d8b1e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • pnpm
    • git
    • node

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use pnpm and git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Translation Audit loads about 693 tokens when it runs. Until then it costs about 41 tokens; SKILL.md has 353 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~41
When it runs · the whole SKILL.md, loaded when a task matches
~693

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from vexl-it/vexl at commit d2d8b1e, republished under its GPL-3.0 licence (© vexl-it). 353 words, ~693 tokens.

Download SKILL.mdSave it as .claude/skills/translation-audit/SKILL.md (or your agent's skills folder).
name
translation-audit
description
Translations audit — fill missing keys in every shipped locale, re-translate keys whose English changed, delete stale ones, flag suspicious values.
disable-model-invocation
true

Translation audit

Brings every shipped locale to parity with English. Scripts do the mechanical work; subagents only translate. All commands run in packages/localization.

The marker file packages/localization/translation-audit.json (lastAuditCommit, lastAuditAt) records the commit up to which English changes have translation parity.

Steps

  1. Mode: read the marker file and ask the user which audit to run:
    • Diff audit (default when the marker exists and its commit is reachable — verify with git cat-file -e <lastAuditCommit>): covers everything since the marker.
    • Full audit (default when there is no marker or its commit is unreachable): everything, plus the suspicious-value sweep.
  2. Stale cleanup: run pnpm check:translations --fix-stale — mechanically deletes orphan keys and stray locale files. Record what it removed for the final report.
  3. Scope: run pnpm check:translations --json and group the missingKey, missingPluralForm, and placeholderMismatch errors by locale. On a diff audit, additionally run node scripts/diffEnKeys.mjs --base <lastAuditCommit> — its changed keys need re-translation in every shipped locale (the old translations render the old meaning), and its added keys should already appear as missingKey errors.
  4. Fan out: spawn translator subagents — model, prompt contents, and translator rules are in docs/translating.md. Per-locale in parallel, each with its locale's work items and the English values (for changed keys, old and new). When the whole scope is a handful of keys, one subagent covering all locales does the job instead. On a full audit only, spawn per-locale for every shipped locale (even gapless ones) and have each subagent sweep all of its locale's files and report (never rewrite) suspicious values: strings still in English, or reading machine-glued.
  5. Verify: re-run pnpm check:translations and dispatch follow-up fixes until it exits clean. legalDocs entries in the JSON report are informational, not errors — legal documents are never auto-translated.
  6. Update the marker: write the current git rev-parse HEAD and ISO timestamp into translation-audit.json; commit it together with the translations. Both modes earn this — a green diff audit covers everything since the previous marker.
  7. Report to the user: keys translated per locale, keys re-translated for changed English, stale keys deleted, suspicious values flagged (full audit), and the legal-document parity status from the report.

© vexl-it, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/translation-audit of vexl-it/vexl.

Open the folder on GitHubat commit d2d8b1e

Compare with similar skills

Translation Audit next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Translation Audit compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Translation Audit this skillvexl-it/vexl125—~693Automated safety check: PassGPL-3.0
Generate Translationspayloadcms/payload45k—~1.1kAutomated safety check: PassMIT
Plane UI Translationmakeplane/plane61k—~16kAutomated safety check: PassAGPL-3.0
Fanyiafc163/fanyi1.6k—~766Automated safety check: PassMIT
Aholo Viewer Docsmanycoretech/aholo-viewer1.1k—~341Automated safety check: PassMIT
Docs Websitekurotu/VRCQuestTools373—~1.3kAutomated safety check: PassMIT

Similar skills

  • Generate Translations

    payloadcms/payload

    A skill your agent uses when new translation keys are added to packages to generate new translations strings

    45k GitHub stars~1.1k tokensUpdated yesterday
    Writing & ContentAuto-check passed

  • Plane UI Translation

    makeplane/plane

    Sets the rules for translating and updating Plane's UI strings across locales: do-not-translate terms, plural forms, placeholders and AI translation review.

    61k GitHub stars~16k tokensUpdated 2 days ago
    Writing & ContentAuto-check passed

  • Fanyi

    afc163/fanyi

    用命令行工具 fanyi(别名 fy)做中英互译与查词,一次返回词典(iciba、youdao)和大模型三方结果。适用于单词、短语、习语谚语、单句短句的中英翻译,以及查释义、音标、例句、相关词。触发场景如"翻译一下 xxx"、"xxx 是什么意思"、"xxx 用英语怎么说"、"和谐 翻译成英文"——即使没说"用 fanyi"也应优先用本…

    1.6k GitHub stars~766 tokensUpdated 1 mo ago
    Writing & ContentAuto-check passed

  • Aholo Viewer Docs

    manycoretech/aholo-viewer

    Guides writing and maintaining Aholo Viewer documentation: README, AGENTS.md, architecture notes, bilingual manual pages and AI collaboration guides.

    1.1k GitHub stars~341 tokensUpdated 2 days ago
    Writing & ContentAuto-check passed

  • Docs Website

    kurotu/VRCQuestTools

    Use this skill FIRST for any task whose output lives in the Website/ directory — the VRCQuestTools user manual / docs site (Docusaurus, bilingual en/ja).

    373 GitHub stars~1.3k tokensUpdated yesterday
    Writing & ContentAuto-check passed

  • Translation Diff Export

    Devolutions/UniGetUI

    Compares UniGetUI JSON locale files against English, identifies untranslated or source-changed keys, and generates patch, reference, and handoff files for a target language.

    26k GitHub stars~1.1k tokensUpdated yesterday
    Writing & ContentAuto-check passed

More from vexl-it/vexl

  • Adding Translation Key

    vexl-it/vexl

    How to add or change a user-facing string in the Vexl app and translate it into all shipped locales.

    125 GitHub stars~632 tokensUpdated yesterday
    Auto-check passed

  • Translation Feedback

    vexl-it/vexl

    Record translation-quality feedback as a durable rule in the brand narrative.

    125 GitHub stars~496 tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Translation Audit

What does Translation Audit do?

Translations audit — fill missing keys in every shipped locale, re-translate keys whose English changed, delete stale ones, flag suspicious values. Translation Audit is an agent skill from vexl-it/vexl. Translations audit — fill missing keys in every shipped locale, re-translate keys whose English changed, delete stale ones, flag suspicious values.

When should I use Translation Audit?

Translation Audit fits situations like: tasks that involve Translation.

How do I install Translation Audit in Claude Code?

Run `npx skills add vexl-it/vexl --skill translation-audit -a claude-code`. Or copy the skill folder (.agents/skills/translation-audit in vexl-it/vexl) into .claude/skills/translation-audit in your project. Claude Code loads it when a task matches its description.

How do I install Translation Audit in Codex?

Run `npx skills add vexl-it/vexl --skill translation-audit -a codex`. Or copy the skill folder (.agents/skills/translation-audit in vexl-it/vexl) into .agents/skills/translation-audit in your project. Codex loads it when a task matches its description.

Can I use Translation Audit in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add vexl-it/vexl --skill translation-audit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/translation-audit, .gemini/skills/translation-audit, .github/skills/translation-audit and .opencode/skills/translation-audit in your project.

What does Translation Audit need to run?

Going by SKILL.md and its folder, Translation Audit needs the command-line tools its instructions call (pnpm, git and node).

Does Translation Audit access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Translation Audit safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Translation Audit use?

Translation Audit is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Translation Audit use?

About 693 tokens (SKILL.md is roughly 2.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Translation Audit?

Skills that share tags, products or a category with Translation Audit: Generate Translations (payloadcms/payload, 45k stars), Plane UI Translation (makeplane/plane, 61k stars), Fanyi (afc163/fanyi, 1.6k stars) and Aholo Viewer Docs (manycoretech/aholo-viewer, 1.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Translation Audit?

vexl-it (a GitHub organization) maintains it in vexl-it/vexl, which has 125 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 9, 2026.

Source: vexl-it/vexl on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.