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

Dify Docs Translation Test

by langgenius in langgenius/dify-docs

Judge a zh or ja page as the owner of that edition would: a fresh agent reads it beside its English source against the language's formatting guide and the glossary, marks the sentences that fall…

CC-BY-4.0Auto-check passedWriting & Content

Install Dify Docs Translation Test

skills CLI
$ npx skills add langgenius/dify-docs --skill dify-docs-translation-test -a claude-code

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

GitHub CLI
$ gh skill install langgenius/dify-docs dify-docs-translation-test --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/langgenius/dify-docs.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/dify-docs-translation-test .claude/skills/dify-docs-translation-test && 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
dify-docs-translation-test
GitHub stars
178
Token cost
~1.2k tokens
SKILL.md length
282 words
Files
1
Skills in repo
11
Repo updated
First seen
Licence
CC-BY-4.0

At a glance

Judge a zh or ja page as the owner of that edition would: a fresh agent reads it beside its English source against the language's formatting guide and the glossary, marks the sentences that fall…

  • Works in 3 steps: Agree the dispatch with the owner before… → Dispatch the fresh sub-agent(s)… → Relay the report unedited. Then act on…
  • Tasks that involve Translation
  • SKILL.md covers Procedure and Dispatch prompt
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Dify Docs Translation Test is an agent skill from langgenius/dify-docs. Judge a zh or ja page as the owner of that edition would: a fresh agent reads it beside its English source against the language's formatting guide and the glossary, marks the sentences that fall short, and returns a ship verdict on the work of this round. Runs in the pipeline's Check stage after the editor test.

Its SKILL.md is about 1.2k 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 Dify. The licence is CC-BY-4.0.

When your agent uses it

  • Tasks that involve Translation

Example prompts

  • “/dify-docs-translation-test”

Workflow steps

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

  1. Agree the dispatch with the owner before sending anything: one judge per language per round is the usual shape, reading every page that…
  2. Dispatch the fresh sub-agent(s) (subagent_type: general-purpose) with the template below, filling {LANG} (Chinese or Japanese), {GUIDE}…
  3. Relay the report unedited. Then act on it as the editor test does: the verdict judges this round's work; "Ship with light edits" means fix…

What it can do on your machine

Read from SKILL.md and the folder at commit 01f1cb6. 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

    No scripts in the folder and no shell commands in SKILL.md.

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

  • Network

    No URLs in SKILL.md.

    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

Dify Docs Translation Test loads about 1.2k tokens when it runs. Until then it costs about 85 tokens; SKILL.md has 282 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~85
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

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 langgenius/dify-docs at commit 01f1cb6, republished under its CC-BY-4.0 licence (© langgenius). 282 words, ~1,179 tokens.

Download SKILL.mdSave it as .claude/skills/dify-docs-translation-test/SKILL.md (or your agent's skills folder).
name
dify-docs-translation-test
description
Judge a zh or ja page as the owner of that edition would: a fresh agent reads it beside its English source against the language's formatting guide and the glossary, marks the sentences that fall short, and returns a ship verdict on the work of this round. Runs in the pipeline's Check stage after the editor test.

Translation Test

The CJK linter measures mechanics. This test measures the translation: whether it says what the English says, in the language a native reader would write. It only measures anything if the judge has not seen the translating: a fresh sub-agent gets the translated page, its English source, the language's guide, and the glossary, and nothing else.

Procedure

  1. Agree the dispatch with the owner before sending anything: one judge per language per round is the usual shape, reading every page that round touched in that language; a page translated whole can have its own judge when the round is large. When no reviewer is in the session, state the dispatch in the report or PR description and proceed.
  2. Dispatch the fresh sub-agent(s) (subagent_type: general-purpose) with the template below, filling {LANG} (Chinese or Japanese), {GUIDE} (tools/translate/formatting-zh.md or tools/translate/formatting-ja.md), {GLOSSARY} (writing-guides/glossary.md), {SOURCE} (the English page, absolute path), {DRAFT} (the translated page, absolute path), and {CHANGED} ("the whole page", or the sections and paragraphs this round changed). When one judge reads several pages, the page block (files 3 and 4 and the changed line) and the reply repeat per page, under the page's path. Put nothing else in the prompt.
  3. Relay the report unedited. Then act on it as the editor test does: the verdict judges this round's work; "Ship with light edits" means fix the marked sentences, "Needs heavy edits" means retranslate the marked units whole from the English, "Needs retranslation" means a fresh translator takes the page from the English file on disk. A revised page goes to a new judge. Marks outside the change go to the owner as a list with a proposal for each.

Dispatch prompt

text
You are the editor of the {LANG} edition of a documentation set, reading a
translated page the way its owner would before deciding whether it can ship.

Read exactly these files, in this order:
1. {GUIDE}: the whole guide. Its translation-quality sections describe
   the failures you are looking for; the rest of the guide is context for
   them, and its formatting rules are checked elsewhere.
2. {GLOSSARY}: the terms and UI labels, with their {LANG} forms.

Then, for each page under review:
3. {SOURCE}: the English page. It is what the translation has to say.
4. {DRAFT}: the {LANG} page under review.
   This round changed: {CHANGED}. Read the whole page regardless; a
   sentence is judged in the context the page gives it.

Read nothing else and run no other command.

Mark every sentence that falls short, quoting it, with one tag each. A
sentence, block (a list, table, code block, callout, or image), or section
of the English page with no counterpart in the translation is marked too,
quoting the English:
- meaning: says something the English does not, or drops something it
  does (a condition, a restriction, a qualifier such as "only", a whole
  sentence, block, or section)
- structure: carries the English clause structure or sentence order where
  a native writer would not
- register: a word in the wrong register for its context
- term: a general term whose {LANG} form is not the glossary's, or a UI
  label that does not correspond to the label the English page names
- tell: a translationese pattern the guide lists
- rule: breaks a translation rule the guide states and the tags above do
  not name (a standard phrase, a katakana convention, an app-type name);
  name the section

Then give one verdict on this round's work: Ship with light edits / Needs
heavy edits / Needs retranslation, with one sentence on what decided it.
Marks outside the change do not move the verdict; list them separately.

Do not check formatting, links, or facts beyond what the English page
says. Do not rewrite. Judge only whether a native reader would take this
page for one written in {LANG}.

Reply with exactly this, once per page, under the page's path:
- **Marked, in this change**: [quoted sentence, or the missing English unit — tag — five words on why; for rule, the section], one per line, or "none"
- **Marked, elsewhere on the page**: same form, or "none"
- **Best passage**: [the section that reads as written, in a phrase]
- **Verdict**: [one of the three, and the deciding sentence]

© langgenius, CC-BY-4.0. 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 .claude/skills/dify-docs-translation-test of langgenius/dify-docs.

Open the folder on GitHubat commit 01f1cb6

Compare with similar skills

Dify Docs Translation Test 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.

Dify Docs Translation Test compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Dify Docs Translation Test this skilllanggenius/dify-docs178—~1.2kAutomated safety check: PassCC-BY-4.0
Translation Diff ExportDevolutions/UniGetUI26k—~1.1kAutomated safety check: PassMIT
Sync Translationssymfony/symfony31k—~1.9kAutomated safety check: PassMIT
Translation Diff ImportDevolutions/UniGetUI26k—~750Automated safety check: PassMIT
Translation Diff TranslateDevolutions/UniGetUI26k—~934Automated safety check: PassMIT
Generate Translationspayloadcms/payload45k—~1.1kAutomated safety check: PassMIT

Similar skills

  • 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 today
    Writing & ContentAuto-check passed

  • Sync Translations

    symfony/symfony

    Synchronize translation catalogs across maintained Symfony branches: find messages that newer branches added to the English catalogs but that are still missing from the oldest maintained branch…

    31k GitHub stars~1.9k tokensUpdated today
    Writing & ContentAuto-check passed

  • Translation Diff Import

    Devolutions/UniGetUI

    Merges translated key-value pairs from a UniGetUI JSON localization patch back into the full language file and validates the merged result.

    26k GitHub stars~750 tokensUpdated today
    Writing & ContentAuto-check passed

  • Translation Diff Translate

    Devolutions/UniGetUI

    Translates a sparse UniGetUI JSON language patch, writes completed entries into the working copy, preserves placeholders and terminology, and prepares the patch for merge-back.

    26k GitHub stars~934 tokensUpdated today
    Writing & ContentAuto-check passed

  • 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 today
    Writing & ContentAuto-check passed

  • InkOS Creative Harness

    Narcooo/inkos

    Drives long-form fiction, scripts, storyboards, interactive films and long-document translation through InkOS, with every change made by a typed action.

    10k GitHub starsUsed in 1 repo~1.1k tokens
    Writing & ContentAuto-check passed

More from langgenius/dify-docs

All 11 skills in this repo

  • Dify Docs Feature Research

    langgenius/dify-docs

    Research a Dify feature before writing or optimizing documentation.

    178 GitHub stars~2.6k tokensUpdated today
    Auto-check passed

  • Dify Docs Format Check

    langgenius/dify-docs

    Check formatting compliance in changed documentation against writing-guides/formatting-guide.md and tools/translate/formatting-{zh,ja}.md.

    178 GitHub stars~2.7k tokensUpdated today
    Auto-check passed

  • Dify Docs Terminology Check

    langgenius/dify-docs

    Audit terminology consistency across documentation against the codebase UI labels and the glossary — in prose and in the UI strings shown in screenshots.

    178 GitHub stars~2.3k tokensUpdated today
    Auto-check passed

  • Dify Docs API Reference

    langgenius/dify-docs

    Rule pack for the Service API specs ({en,zh,ja}/api-reference/openapiservice.json): spec conventions, app-type scoping, code-verification rules, and the audit machinery.

    178 GitHub stars~2.5k tokensUpdated today
    Auto-check passed

  • Dify Docs Env Vars

    langgenius/dify-docs

    Rule pack for the environment variable reference — en/self-host/deploy/configuration/environments.mdx.

    178 GitHub stars~2.5k tokensUpdated today
    Auto-check passed

  • Dify Docs Write

    langgenius/dify-docs

    The entry point for writing or revising any documentation in this repo: user guides, deployment pages, plugin-dev pages, API specs, the env-var reference, CLI pages.

    178 GitHub stars~3.2k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Dify Docs Translation Test

What does Dify Docs Translation Test do?

Judge a zh or ja page as the owner of that edition would: a fresh agent reads it beside its English source against the language's formatting guide and the glossary, marks the sentences that fall…. Dify Docs Translation Test is an agent skill from langgenius/dify-docs. Judge a zh or ja page as the owner of that edition would: a fresh agent reads it beside its English source against the language's formatting guide and the glossary, marks the sentences that fall short, and returns a ship verdict on the work of this round.

When should I use Dify Docs Translation Test?

Dify Docs Translation Test fits situations like: tasks that involve Translation.

How do I install Dify Docs Translation Test in Claude Code?

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

How do I install Dify Docs Translation Test in Codex?

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

Can I use Dify Docs Translation Test 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 langgenius/dify-docs --skill dify-docs-translation-test -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/dify-docs-translation-test, .gemini/skills/dify-docs-translation-test, .github/skills/dify-docs-translation-test and .opencode/skills/dify-docs-translation-test in your project.

What does Dify Docs Translation Test need to run?

SKILL.md names no scripts, command-line tools or credentials: Dify Docs Translation Test is instructions for the agent only.

Does Dify Docs Translation Test access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Dify Docs Translation Test 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 Dify Docs Translation Test use?

Dify Docs Translation Test is published under the CC-BY-4.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Dify Docs Translation Test use?

About 1.2k tokens (SKILL.md is roughly 4.7k 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 Dify Docs Translation Test?

Skills that share tags, products or a category with Dify Docs Translation Test: Translation Diff Export (Devolutions/UniGetUI, 26k stars), Sync Translations (symfony/symfony, 31k stars), Translation Diff Import (Devolutions/UniGetUI, 26k stars) and Translation Diff Translate (Devolutions/UniGetUI, 26k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Dify Docs Translation Test?

langgenius (a GitHub organization) maintains it in langgenius/dify-docs, which has 178 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 8, 2026.

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