Home / peter-tu-zynkr / zynkr-skill-builder · GitHub

content-translator SKILL.md skillA

content-translator from peter-tu-zynkr/zynkr-skill-builder is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add peter-tu-zynkr/zynkr-skill-builder/content-translator@git:20260918.2429d96

Pins git:20260918.2429d96 in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: peter-tu-zynkr/zynkr-skill-builder
Path: skills/1-brand-marketing/content-translator/SKILL.md
Versions recorded: 2
Latest version: git:20260918.2429d96, committed Sep 18, 2026
First version recorded: Jun 9, 2026
Size: 7,865 bytes
Repository stars: 22
License: none declared

Translate English (or any source language) into natural, conversational Traditional Chinese using Taiwanese expressions and tone. Removes the 'translation smell' that comes from word-for-word renderings. Also supports a reverse zh-TW → English mode for producing English 'flagship' versions of SEO articles (used by seo-article-pipeline for AEO reach in English-dominant AI engines).

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# zh-TW Translator (翻譯蒟蒻)

```bash
npx skills add https://github.com/peter-tu-zynkr/zynkr-skill-builder --skill content-translator
```

Translate text into natural Traditional Chinese (Taiwan) — the kind a Taiwanese writer would actually publish. Use this skill when source content is in English, simplified Chinese, or any other language, and you need it to read like it was originally written for a Taiwanese audience, not translated. Particularly suited for articles, newsletters, social posts, documentation, and mixed code+prose content.

---

## Step 1 — Identify the source and surface

Detect:
1. **Source language** — usually English, but may be zh-CN, Japanese, etc.
2. **Surface type** — prose, social post, technical doc, code-comment-heavy text, mixed
3. **Tone target** — formal (article, doc), conversational (newsletter, social), or unspecified (default to conversational)
4. **Code blocks** — if any ```fenced``` blocks exist, mark them off-limits

If the user didn't specify tone, infer from surface type. Ask only if genuinely ambiguous.

---

## Step 2 — Translate with Taiwanese voice

Apply these rules while translating:

### Vocabulary
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add peter-tu-zynkr/zynkr-skill-builder/content-translator@sha256:5a715937a0f57d16

The line at the top of this page pins the label git:20260918.2429d96, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

[![mdr](https://markdownregistry.com/badge/art_lp3mdmc5rpke2ti3.svg)](https://markdownregistry.com/a/art_lp3mdmc5rpke2ti3)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Jun 9, 2026 and Sep 18, 2026, about one every 101 days.

version	committed	commit	size	audit
git:20260918.2429d96 latest	2026-09-18	2429d96	7,865 B	A	view · diff
git:20260609.fb3d951	2026-06-09	fb3d951	7,157 B	A	view

Audit of the latest version

A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (7865 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag

Source

GitHub

peter-tu-zynkr/zynkr-skill-builder · 22 stars · license none declared · pushed 2026-10-01 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_lp3mdmc5rpke2ti3
GET https://markdownregistry.com/api/v1/resolve?ref=peter-tu-zynkr/zynkr-skill-builder/content-translator
GET https://markdownregistry.com/api/v1/blob/5a715937a0f57d16d3c0fe7ae8998a8ff8df93990ec6ed0dc29a9dc9d8c488c7

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from peter-tu-zynkr/zynkr-skill-builder

CLAUDE.md CLAUDE.md file

peter-tu-zynkr/zynkr-skill-builder · CLAUDE.md

git:20260701.37418c4 · audit A · 22 stars

planning-1on1-annual-digest SKILL.md skill

peter-tu-zynkr/zynkr-skill-builder · skills/0-strategy/planning-1on1-annual-digest/SKILL.md · Turn ONE teammate's shared 1:1 Doc (weekly WB entries), their LOB plan Doc and the tracker rows they own into a zh-TW…