Hns Oss Docs I18n Rules logo

Hns Oss Docs I18n Rules

OrganizationPopular
modu-ai
hns-oss-docs-i18n-rules

HARD i18n rules digest for the oss-docs harness specialists working on moai-adk-go README 4-locale set and the docs-site (adk.mo.ai.kr). Covers the canonical-locale chains, the 4-locale same-PR obligation, Mermaid TD-only, the no-emoji + icon-shortcode rule, emphasis-marker spacing, the URL blacklist, version SSOT, vercel.json redirect pattern, and the immutable Vercel binding. Loaded FIRST by every oss-docs specialist before any edit.

Overview

Publishermodu-ai
Repositorymoai-adk
Skill namehns-oss-docs-i18n-rules
Stars
1.2K
Forks
226
Bundled files
Instructions only
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by modu-ai on GitHub. Read the source before you install it.

Installation

Install the Hns Oss Docs I18n Rules AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/modu-ai/moai-adk/tree/main/.claude/skills/hns-oss-docs-i18n-rules
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/modu-ai/moai-adk.git /tmp/moai-adk
mkdir -p .claude/skills
cp -r /tmp/moai-adk/.claude/skills/hns-oss-docs-i18n-rules .claude/skills/hns-oss-docs-i18n-rules
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Hns Oss Docs I18n Rules in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Hns Oss Docs I18n Rules on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Hns Oss Docs I18n Rules is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

oss-docs HARD i18n Rules

SSOT: .moai/docs/docs-site-i18n-rules.md (+ CLAUDE.local.md §17.1 for the design/icon regime). This skill is the working digest; on conflict, the SSOT wins — EXCEPT the two stale items in § Known-Stale below, where reality wins.

1. Canonical-locale chains [HARD]

SurfaceCanonicalDerivation chainDerived files
docs-sitekoko → en → ja/zh, same PRdocs-site/content/{en,ja,zh}/
READMEko (README.ko.md)ko → en/ja/zh, same PRREADME.md, README.ja.md, README.zh.md

README canonical flipped en → ko by card t47 (operator decision 2026-08-17): the ko new-skeleton (12-section feature-oriented structure) was promoted to canonical, and en/ja/zh are re-derived from it. Both surfaces are now ko-canonical — the surface chains agree.

  • Author in the canonical locale only; derive the rest. Never "fix" canonical content inside a translation — report the discrepancy back instead.

2. 4-locale simultaneous-update obligation [HARD]

Every canonical content change MUST land in all 4 locales in the same PR. A canonical edit without its 3 derived counterparts is a locale-parity FAIL (sprint contract locale-parity threshold 1.0, must_pass).

3. Mermaid TD-only [HARD]

  • Allowed: flowchart TD, graph TB.
  • Forbidden: LR / RL directions (flowchart LR, graph LR, flowchart RL, graph RL).
  • Translation preserves diagram direction verbatim.

4. No emoji in body text [HARD]

  • Use the icon shortcode instead: {{</* icon <name> [variant] */>}} (defined in docs-site/layouts/shortcodes/icon.html; variants: ok|warn|danger|primary|muted).
  • Preserved (NOT emoji — do not strip): typographic symbols → ← ↓ ✓ ✗, and branding emoji inside MoAI orchestrator-banner example code blocks.

5. Emphasis-marker spacing [HARD]

  • Correct: **바이브코딩** (Vibe Coding) — parenthetical OUTSIDE the markers.
  • Wrong: **바이브코딩(Vibe Coding)**.

6. URL blacklist [HARD]

Only adk.mo.ai.kr is a valid docs-site domain. Forbidden (all occurrences, including link labels and translated prose):

  • docs.moai-ai.dev
  • adk.moai.com
  • adk.moai.kr

7. Version SSOT [HARD]

docs-site/hugo.toml params.version / params.releaseDate is the single version surface. Never hardcode divergent version/date strings into pages, menus, or READMEs beyond what the release process syncs.

Release-sync obligation (operator decision 2026-08-18): every release updates ALL version DISPLAYS to the release number in the same PR — hugo.toml version + releaseDate together (the file's own two-line contract), the README release badges (all 4 locales), and in-page example outputs that show the product version (statusline examples 🗿 vX.Y.Z, update-prompt examples X ⬆️ Y, version-column example values). Historical citations ("introduced in vX.Y.Z", "retired in v3.0.0", "default-on since v3.0.0") are NOT displays and stay untouched. The verify recipe's version-string check (Skill "hns-oss-docs-verify" §6) enforces this at the exit gate.

8. Moved pages need redirects [HARD]

Every docs-site page move/rename adds to docs-site/vercel.json:

  1. Locale-aware: /:locale(ko|en|ja|zh)/old-path → /:locale/new-path
  2. Non-locale fallback: /old-path → /ko/new-path

9. Vercel binding immutable [HARD]

The Vercel project binding and deployment config are never changed by this harness (redirects array excepted). Push = production deploy at adk.mo.ai.kr, which is why specialists NEVER commit/push — publishing is human-gated.

Known-Stale items in the SSOT doc

The SSOT .moai/docs/docs-site-i18n-rules.md predates the current site and carries 2 stale facts — reality wins:

  1. It says the theme is Hextra → reality: hugo-geekdoc.
  2. It says config is hugo.yaml → reality: docs-site/hugo.toml (defaultContentLanguage=ko).

Also: the scripts docs-i18n-check.sh and gen_menu.py referenced there DO NOT exist. Never shell out to them — run the inlined checks in Skill("hns-oss-docs-verify") instead.

Frequently asked questions

What does the Hns Oss Docs I18n Rules AI skill do?

HARD i18n rules digest for the oss-docs harness specialists working on moai-adk-go README 4-locale set and the docs-site (adk.mo.ai.kr). Covers the canonical-locale chains, the 4-locale same-PR obligation, Mermaid TD-only, the no-emoji + icon-shortcode rule, emphasis-marker spacing, the URL blacklist, version SSOT, vercel.json redirect pattern, and the immutable Vercel binding. Loaded FIRST by every oss-docs specialist before any edit.

Why use Hns Oss Docs I18n Rules on TypingMind?

Because you install it once and use it with any model. Hns Oss Docs I18n Rules is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Hns Oss Docs I18n Rules in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/modu-ai/moai-adk/tree/main/.claude/skills/hns-oss-docs-i18n-rules. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Hns Oss Docs I18n Rules?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Hns Oss Docs I18n Rules?

As many as you like. As long as a model supports skills, you can use Hns Oss Docs I18n Rules with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Hns Oss Docs I18n Rules AI skill free?

Yes. It is published on GitHub by modu-ai under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇