translate-docs
Skill0 starsChanged 5 months agoMITView on GitHub
Translate documentation (.md files) into another language. Use when: translating a markdown doc, updating an existing translation after source changes, localizing documentation, creating a french translation of a doc, keeping translations in sync with the source. Default target language is French. Translated files are placed in a folder named after the language (e.g. 'french/') mirroring the source path.
8 other projects use a version of this.
Adopted by
Most recently taken up by
- kanap-hq/KANAPtheir own version, first seen Nov 8, 2026
- X-T-E-R/kikitheir own version, first seen Nov 1, 2026
- CherryHQ/cherry-studiotheir own version, first seen Oct 25, 2026
- reactive/data-clienttheir own version, first seen Oct 17, 2026
- clice-io/clicetheir own version, first seen Oct 8, 2026
- xiaolai/vmarktheir own version, first seen Oct 8, 2026
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- CherryHQ/cherry-studio★ 53ksame name
- MoonshotAI/kimi-code★ 8.2ksame name
- ArcReel/ArcReel★ 6.3ksame name
- reactive/data-client★ 2ksame name
- clice-io/clice★ 1.4ksame name
- xiaolai/vmark★ 908same name
- X-T-E-R/kiki★ 53same name
- kanap-hq/KANAP★ 7same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository7 other files it gives its agents.
- antigravity-migrationSkill
- audio-normalizeSkill
- copilot-migrationSkill
- meeting-syncSkill
- meeting-to-documentationSkill
- meeting-transcribeSkill
- spark-promptSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 5 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 8 edited versions we read keep these.
5
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 38
If the output file does not exist: proceed to Step 3 (full translation).
- Distinctive: line 39
If the output file exists: proceed to Step 4 (incremental update).
- Very specific: line 43
Read the entire source .md file.
- Distinctive: line 51
Create the output file at the computed path (create parent directories if needed).
- Very specific: line 55
Read both the source .md and the existing translation.
- Distinctive: line 57
Use structural landmarks (headings, table rows) to align the two documents.
- Distinctive: line 64
After writing the output file, verify:
“Common” is measured: kept by at least 6 in 10 of the 8 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
translate-docs
Translates .md documentation files into a target language and places them in a language-named folder that mirrors the source path structure.
When to Use
- Translating a new
.mddoc into French (or another language) - Updating a translation when the source
.mdhas changed - Checking whether an existing translation is up to date
Conventions
| Concept | Convention |
| Target language folder | Named after the language in lowercase English (e.g. french/, spanish/, german/) |
| Output path | Insert the language folder under the source folder path (e.g. docs/foo.md → docs/french/foo.md) |
| File name | Same as the source file name |
| Default language | French (use when no language is specified) |
Procedure
Step 1 — Identify source and output paths
- Note the source
.mdpath (e.g.docs/acquisition-node-comparison.md). - Determine the target language (default:
french). - Compute the output path: insert the language folder inside the source file’s parent folder.
- Example:
docs/foo.md→docs/french/foo.md - Example:
readme.md→french/readme.md(root files placefrenchin workspace root)
- Example:
Step 2 — Check for an existing translation
- If the output file does not exist: proceed to Step 3 (full translation).
- If the output file exists: proceed to Step 4 (incremental update).
Step 3 — Full translation (new file)
- Read the entire source
.mdfile. - Translate all prose content into the target language.
- Preserve exactly:
- Markdown structure (headings, lists, tables, code blocks, links, images)
- Code snippets and inline code (do not translate code)
- Technical terms, product names, API names, and proper nouns
- Front-matter YAML/TOML (translate values only if they are human-readable descriptions)
- Link URLs (translate only visible link text if appropriate)
- Create the output file at the computed path (create parent directories if needed).
Step 4 — Incremental update (existing translation)
- Read both the source
.mdand the existing translation. - Identify sections or paragraphs that differ between the current source and what the translation reflects.
- Use structural landmarks (headings, table rows) to align the two documents.
- Translate only the changed or added content.
- Preserve already-correct translated sections unchanged.
- Overwrite the translation file with the updated content.
Step 5 — Quality check
After writing the output file, verify:
- All headings are translated.
- No source-language sentences remain (except inside code blocks).
- Code blocks are untouched.
- Table structure is intact.
- Internal links still resolve (adjust relative paths if the folder depth changed).
- File saved at the correct output path.
Examples
| User prompt | Source | Output |
| "Translate docs/foo.md" | docs/foo.md | docs/french/foo.md |
| "Translate readme.md to spanish" | readme.md | french/readme.md |
| "Update the french translation of docs/bar.md" | docs/bar.md | docs/french/bar.md (updated) |
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

