SkillFoxx

Turkish Native skill

A skill that teaches an agent to write Turkish without English calques: it fixes sentence structure, collocations and UI copy

  • 91 ★ on the repository
  • Last commit
  • MIT
Skill

Minimal access

Why this level

  • The skill consists of instructions and reference files, runs nothing itself and works only on the text you give it.
All reasons and checks

oguzhankayan/turkish-nativeAuthor:oguzhankayan

Install

In your terminal, with SkillFoxx CLI

npx skillfoxx add skills/turkish-native

Detects the agents on your machine, shows the access level and pins the version.

Other ways to install

Access and checks

How we review

Minimal accessThe tool runs nothing and makes no network calls.

  • The skill consists of instructions and reference files, runs nothing itself and works only on the text you give it.

This is third-party code. Review the repository files before installing.

What it does

Turkish Native is a skill for writing and editing Turkish that reads as native and not translated. It catches grammatically valid but foreign-built sentences: carried-over subordinate clause structure, wrong cases and collocations, SaaS and sales calques, internal product jargon, slogans from model-written copy and page-level repetition. Work starts from meaning. The agent identifies the audience and register, separates facts from wording, fixes structure before vocabulary, rebuilds foreign sentences whole and finally checks natural flow, factual fidelity, domain fit and over-editing. A taxonomy of 57 patterns falls into six groups: sentence architecture, verbs and vocabulary, UI and localization, marketing and model copy, register and fidelity, page integrity. Detailed rules with examples and false-positive guards sit in `references/`. The skill does not replace spell checking, an AI detector or a lawyer, and it leaves natural phrasing alone.

Who it is for. Localizers, marketers and interface developers who prepare Turkish copy and review translations from English and AI-written text.

Good fit when

  • You need to review Turkish website or app copy and remove English calques without changing facts
  • A translated interface sounds artificial and buttons, hints and error messages need rewriting
  • A clinic or SaaS page was built from a neighboring template and keeps foreign fields and calls to action
  • Copy in a file like `src/content/tr/home.ts` has to be rewritten while keys, variables, links and routes stay untouched
  • Legal, security and corporate prose in Turkish has to move toward natural language without losing meaning

Not a fit when

  • You need spelling and punctuation checks: the skill works a layer above and does not replace a proofreader
  • You need a loanword ban: words like link, demo and dashboard stay when they are natural in context
  • The text is legal and needs professional review: the skill does not replace a lawyer

Example request

Use $turkish-native to review this Turkish copy. Flag translationese and unnatural collocations, then rewrite it naturally.

Limitations

The skill targets Turkish only and fixes the sounds-translated problem. The author calls version 0.5.0 pre-1.0, so pattern names and the evaluation schema may change before 1.0. The repository has 105 regression cases including positive controls that should stay unchanged, but that checks the skill itself and does not guarantee results on your text. The skill does not guess industry terms or legal consequences, so names, numbers, dates and commands are kept as they are. The agent can still invent a polished phrase a native speaker finds unnatural, so a person who knows the language should read the result.

How to disable. Remove the plugin through `/plugin` or delete the `turkish-native` skill folder from the agent skills directory. `npx skills remove` also works if you installed through the Skills CLI.

FAQ

How do I install the skill?

Run `npx skills add oguzhankayan/turkish-native --global`. For Claude Code there is a plugin: `/plugin marketplace add oguzhankayan/turkish-native` and `/plugin install turkish-native@turkish-native`. Manually copy `SKILL.md` and the `references/` folder.

How does the skill differ from Humanizer?

Humanizer catches general traits of AI-written text. Turkish Native solves a narrow problem: calques and foreign-built Turkish sentences. It is not a Humanizer fork and has its own taxonomy.

Will the skill break natural phrases?

No, it has a guard against over-editing. Phrases like Sen satışa bak. stay if the context supports them.

What does it do with code and keys?

If asked to rewrite copy in a file, keys, variables, links, code and route names stay unchanged. Facts, numbers and terms are preserved.

How do I check that the skill works?

The repository has `scripts/validate-package.py`, `scripts/validate-benchmark.py` and 105 regression cases. They validate the package itself, while a person judges results on your text.

Discussion

No questions or reviews yet.

Skills

A skill that edits English prose: it strips filler and cliches, keeps facts and voice and marks gaps instead of inventing.

SkillMinimal access56

A skill that translates and polishes English into Chinese by the Ye Zinan method, removes translationese and pairs paragraphs.

SkillMinimal access115
Russian stack

Russian proofreading skill covering typography, bureaucratic style and 17 signs of machine text, with a rule cited for every fix

SkillMinimal access298
Russian stack

A Russian text editing skill: removes bureaucratese, calques and AI mannerisms without touching facts, with a scanner to measure the edit

SkillExtended access562
Editors’ pick

A skill that strips AI writing tells from text using Wikipedia's list, without adding invented facts

SkillMinimal access68.4K

Infostyle

infostyle

Russian stack

A Russian copy-editing skill based on Ilyakhov's information style: cuts filler and cliches, adds facts, shows before and after

SkillMinimal access41

README in short

The README explains the job of the skill, gives artificial and natural examples, scope limits, install options, the meaning-first workflow, the 57-pattern taxonomy and package validation.

README badge

Original SKILL.md

---
name: turkish-native
description: |
  Write and rewrite Turkish so it reads as native Turkish rather than translated English.
  Use for Turkish marketing copy, product and UI text, localization, documentation, support,
  legal or security prose, and reviews of AI-written Turkish. Detect translationese, copied
  clause structure, nominalization, wrong case and collocations, generic helper verbs, SaaS
  and sales calques, jargon leakage, forced slogans, corporate abstraction, cross-sector
  template residue, unsupported operational claims, and page-level repetition.
license: MIT
metadata:
  version: "0.5.0"
---

# Turkish Native

Write Turkish as Turkish. Do not preserve the sentence skeleton of English or another source language and merely replace its words with Turkish ones.

A sentence can be grammatically valid and still sound translated. Work from meaning, not source-language shape.

## Core test

Before keeping a sentence, ask:

> If I had received only this meaning, with no source-language wording, would I naturally build the Turkish sentence this way?

If not, rebuild it from the intended meaning.

## How to work

1. **Identify the job.** Determine audience, medium, register, sector, and intended action. A landing-page hero, button label, legal notice, clinic page, and API document need different Turkish.
2. **Extract the meaning.** Separate facts and required terminology from wording. Preserve names, numbers, claims, dates, links, commands, legal terms, identifiers, and product behavior.
3. **Fix structure before vocabulary.** Check clause structure, word order, case, references, verb choice, and collocations first.
4. **Check domain fit.** Make sure fields, CTAs, process steps, labels, and examples belong to the actual sector and task rather than a neighboring template.
5. **Rebuild instead of patching.** If the sentence is structurally foreign or domain-wrong, rewrite it around its main meaning. Do not repair translationese one word at a time.
6. **Read it as Turkish.** A native reader should not need to reconstruct another language mentally.
7. **Check fidelity.** Do not invent, remove, strengthen, weaken, or generalize factual claims, operational promises, source labels, or regulated-domain outcomes.
8. **Check restraint.** Do not rewrite natural Turkish merely because another phrasing is possible.

## Voice and register

Match a supplied writing sample or existing product voice. Preserve deliberate short sentences, colloquial expressions, terminology, humor, or formality when they fit the audience.

Do not turn natural Turkish into corporate Turkish. `Sen satışa bak.` can be better than a longer formal alternative. Do not force every English loanword into Turkish: `link`, `demo`, `dashboard`, `API`, `MCP`, and `commit` may be natural in technical or product contexts.

Report a problem