translator
Translate JSON dictionaries and MDX content files between locales with structural integrity, SEO/GEO-aware keyword adaptation, and native-quality output.
Skill by thesaifpasha
Chalk Labs
Need help deploying translator?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/thesaifpasha-translator
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: design, writing, marketing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/translator
What's inside
- Skill name
translator- Description
- Translate JSON dictionaries and MDX content files between locales with structural integrity, SEO/GEO-aware keyword adaptation, and native-quality output. Use when translating UI strings, blog posts, service pages, or any locale-specific content.
- License
- MIT
- Instructions
- 211 lines in SKILL.md · view on GitHub
Files (4)
- SKILL.md
- anti-fabrication.md · references/
- i18n-de.md · references/
- terminology-glossary.md · references/
SKILL.md (first lines)
# Translator
Translate web content between locales. Every translation must read like it
was originally written in the target language while preserving exact file
structure.
## Project context
- **Framework**: {CONFIGURE: i18n framework}
- **Content pipeline**: {CONFIGURE: Content pipeline}
- **Locales**: {CONFIGURE: Supported locales}
- **Dictionaries**: {CONFIGURE: Dictionary file path pattern}
- **Content files**: {CONFIGURE: Content file path pattern}
---
## 1. JSON dictionary translation
### Structure rules
Dictionaries are nested JSON objects. Keys are typically camelCase.
```
{
"section": {
"subsection": {
"label": "Translate this value",
"heading": "And this one"
}
}
}
```
**Preserve exactly:**
- Every key name (never translate keys)
- Nesting structure and depth
- Array length and index ordering
- Object property ordering (match source file order)
- Value types (string stays string, array stays array)
**Translate:**
- All string leaf values that contain human-readable text
**Do NOT translate:**
- Keys (ever)
- URLs in values (e.g., `"href": "/audit"`, `"href": "https://..."`)
- Brand names (define in project context or terminology glossary)
- Statistical values that appear as strings (e.g., `"value": "44%"`)
**If the source has interpolation variables** (`{{variable}}` or `{variable}`),
preserve them exactly in the translated string. Do not translate variable names.
### Validation
After translating dictionary files:
```bash
python .claude/scripts/validate-json-structure.py <original.json> <translated.json>
```
For batch locale parity checks:
```bash
python .claude/scripts/dictionary-diff.py --source en --target de --dir dictionaries
```
---
## 2. MDX content translation
### Frontmatter rules
MDX files use YAML frontmatter. Fields fall into two categories:
**Translate these text fields:**
| Field | Notes |
|-------|-------|
| `title` | Optimize for target-language search intent (see section 3) |
| `description` | Optimize for target-language search intent |
| `summary` | Natural adaptation, not word-for-word |
| `tagline` | Short, punchy — adapt to target language rhythm |
**Do NOT translate metadata fields (copy byte-identical):**
Date fields, author, image paths, tags, status, technical metadata,
ordering fields, category slugs, URLs, and any field whose value is
a machine-readable identifier rather than human-readable text.
### Body rules
**Translate:**
- All prose paragraphs
- Heading text (preserve heading level: `##` stays `##`)
- Table cell content (preserve table structure)
- List item text
- Image alt text if present
- Link text (the visible part in `[text](url)`)
**Do NOT translate:**
- URLs in links: `[translated text](original-url-unchanged)`
- Code blocks (inline or fenced)
- HTML entities or tags if present
- Markdown syntax characters (`#`, `|`, `-`, `*`, `>`)
### Validation
```bash
python .claude/scripts/validate-mdx-structure.py <original.mdx> <translated.mdx>
```
---
## 3. SEO/GEO-aware translation
Do not mechanically translate keywords. Optimize for how the target audience
actually searches.
**Title and description optimization:**From thesaifpasha/LGTM, MIT.
More from thesaifpasha/LGTM
- 0.487score
schema-markup
thesaifpasha
When the user wants to add, fix, or optimize schema markup and structured data on their site.
SkillDFreshness: D★ 14Claude Code +9 - 0.487score
workflow
thesaifpasha
Use when creating plans, breaking work into issues, dispatching agents, creating PRs, updating status, reconciling contributions, or any task involving the…
SkillDFreshness: D★ 14Claude Code +9 - 0.477score
compare
thesaifpasha
Open two files side by side in VSCodium diff view.
SkillDFreshness: D★ 14Claude Code +9 - 0.459score
onboard
thesaifpasha
First-run onboarding for a new project.
SkillDFreshness: D★ 14Claude Code +9 - 0.453score
agent-browser
thesaifpasha
Browser automation CLI for AI agents.
SkillDFreshness: D★ 14Claude Code +9 - 0.267score
test-strategy
thesaifpasha
Project-specific test strategy.
SkillDFreshness: D★ 14Claude Code +9 - 0.255score
tree
thesaifpasha
No description from the publisher yet.
SkillDFreshness: D★ 14Claude Code +9
Signals
- Stars
- 14
- Forks
- 2
- Open issues
- 0
- Last commit (this folder)
- Apr 10, 2026 (6 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/thesaifpasha/LGTM
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from thesaifpasha
- 0.487score
schema-markup
thesaifpasha
When the user wants to add, fix, or optimize schema markup and structured data on their site.
SkillDFreshness: D★ 14Claude Code +9 - 0.487score
workflow
thesaifpasha
Use when creating plans, breaking work into issues, dispatching agents, creating PRs, updating status, reconciling contributions, or any task involving the…
SkillDFreshness: D★ 14Claude Code +9 - 0.477score
compare
thesaifpasha
Open two files side by side in VSCodium diff view.
SkillDFreshness: D★ 14Claude Code +9 - 0.459score
onboard
thesaifpasha
First-run onboarding for a new project.
SkillDFreshness: D★ 14Claude Code +9 - 0.453score
agent-browser
thesaifpasha
Browser automation CLI for AI agents.
SkillDFreshness: D★ 14Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get translator running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
translator skill. Agent Mart. https://agentmart.dev/skills/thesaifpasha-translator (last updated 2026-10-24)