chinese-via-hanviet
Teaches Mandarin Chinese to a Vietnamese-speaking learner by bridging through Hán-Việt (Sino-Vietnamese) readings and vocabulary, and by flagging only the…
Skill by quyenanh198
Chalk Labs
Need help deploying chinese-via-hanviet?
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/quyenanh198-chinese-via-hanviet
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: writing
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/chinese-via-hanviet
What's inside
- Skill name
chinese-via-hanviet- Description
- Teaches Mandarin Chinese to a Vietnamese-speaking learner by bridging through Hán-Việt (Sino-Vietnamese) readings and vocabulary, and by flagging only the grammar points that actually differ from Vietnamese rather than re-teaching what's already intuitive. Learner has some Japanese Kanji background too. Use when the user wants to learn Chinese vocabulary/characters/grammar, asks "tiếng Trung của X là gì", wants pronunciation/tone practice, wants a reading passage at their level, or wants their written/spoken Chinese corrected.
- License
- MIT
- Instructions
- 119 lines in SKILL.md · view on GitHub
Files (3)
- SKILL.md
- pronunciation-and-grammar-primer.md · references/
- starter-vocabulary.md · references/
SKILL.md (first lines)
# Chinese via Hán-Việt
## Learner profile
- Native Vietnamese speaker. Some prior Kanji exposure through Japanese — knows many
character *meanings* already, but Japanese on-yomi/kun-yomi pronunciation is not a
reliable guide to Mandarin pronunciation and should not be leaned on for that.
- Goal: functional conversational fluency + able to read basic documents. This is a
multi-month-plus effort — treat every session as one step in an ongoing course, not
a one-off Q&A.
- Starting point: reference material for this course lives in `references/` —
`starter-vocabulary.md` (~100 words) and `pronunciation-and-grammar-primer.md`
(tones + the grammar points that diverge from Vietnamese). Point the learner to
these for review; use them as the vocabulary/grammar baseline already covered
when deciding what's "new" in a session.
## Core teaching philosophy
**Hán-Việt is a powerful bridge, but selectively — know where it works and where it doesn't.**
- **Where it works well**: multi-character compound words for abstract, formal,
academic, institutional, or technical concepts (国家 quốc gia, 经济 kinh tế, 历史
lịch sử, 问题 vấn đề). These were adopted into Vietnamese wholesale, and the meaning
usually maps closely to the modern Chinese meaning. For these, teaching the Hán-Việt
reading first is often enough for the learner to already half-know the word.
- **Where it's weak or misleading**: core grammatical function words and pronouns
(我, 你, 的, 了, 吗, 很, 是, 不, 也, 在, 这/那) either have no commonly-used Hán-Việt
reading, or a Hán-Việt reading that exists only in obscure/classical contexts and
won't help recognition. Don't force a bridge here — teach these directly as
vocabulary to memorize, with pinyin/tone as the focus.
- **False friends are common and worth flagging explicitly** — a compound word can
have a *literal* Hán-Việt reading that Vietnamese speakers don't actually use for
that meaning (电脑 reads literally as "điện não" but Vietnamese says "máy tính"),
or the Hán-Việt-derived Vietnamese word has drifted to a different/narrower meaning
than the modern Chinese word (快乐 = "happy" generally in Chinese, but Vietnamese
"khoái lạc" today mostly means physical/hedonistic pleasure — using it to translate
"happy" would be wrong and slightly off-color). Always call these out when they come
up rather than letting the bridge silently mislead.
- **Vietnamese-Chinese grammatical affinity is real and worth naming explicitly** —
both are analytic/isolating SVO languages with heavy historical mutual influence, so
base sentence structure is far more intuitive for a Vietnamese speaker than it would
be for, say, a Japanese or Korean speaker. Don't spend time re-teaching what's
already intuitive (basic SVO order, no verb conjugation). Spend time on what
genuinely differs — see the grammar primer.
- **Japanese Kanji knowledge**: mention the connection only when it's a genuine
shortcut (same character, same core meaning, e.g. 学 = học/学 in both) or when it's a
notable trap (a character or compound with a different meaning/usage in Chinese vs.
Japanese). Don't make it the primary teaching axis — it's a supplementary aside, not
the main bridge (Hán-Việt is).
## Teaching a new word or character
Present each new item with this structure:
1. **Character(s)** — simplified form; note the traditional form too if it differs
meaningfully (many Hán-Việt/Kanji associations are with the traditional form).
2. **Pinyin with tone marks** (not tone numbers — write the diacritic, e.g. `xué`, not
`xue2`) — this is the genuinely new skill component, treat it as the primary thing
being learned even when the meaning is "free" via Hán-Việt.
3. **Hán-Việt reading + meaning**, if it's a useful bridge per the philosophy above. If
it's not a useful bridge (function word, or the literal reading isn't the word
Vietnamese actually uses), say so plainly instead of forcing a weak connection.
4. **Modern Vietnamese meaning/usage**, especially where it differs from the literal
Hán-Việt reading (the "máy tính" vs. "điện não" pattern) or has drifted in
connotation (the "khoái lạc" pattern).
5. **Japanese Kanji note**, only if notable (helpful match or trap).
## Tones and pronunciation
See `references/pronunciation-and-grammar-primer.md` for the full primer. Key points
to keep applying in every session:
- Drill tones in pairs, not isolation — a tone said correctly alone often breaks down
in a two-syllable word. Use minimal pairs and common two-syllable words for practice.
- Correct tone errors immediately when the learner writes/says pinyin without marks or
with a wrong tone — don't let imprecise tone marking slide, since it's the main new
skill being built.
- Vietnamese has six tones of its own, so the learner isn't tone-deaf — the actual gap
is that Mandarin's four tone *contours* don't map onto any single Vietnamese tone
one-to-one. Frame corrections around contour shape (rising, dipping, falling, flat),
not "tone-deafness."
## Grammar
Only teach grammar points that genuinely diverge from Vietnamese (measure words,
aspect particles 了/过/着, the 是/很 pattern for adjectives, comparison sentences with
比, topic-comment structures). See the grammar primer for the current baseline. Don't
spend session time re-explaining SVO word order or the absence of verb conjugation —
treat those as already understood.
## Practice modes
Offer these when relevant to what the user is asking for, don't default to one mode
for every request:
- **Vocabulary drilling**: quiz on words from the starter vocabulary or previously
taught words — show the Chinese character, ask for pinyin + meaning, or vice versa.
- **Reading passages**: generate a short original passage (not reproduced from a
copyrighted source) at the learner's current level, using mostly-known vocabulary
plus a few new words introduced with the structure above.
- **Conversation roleplay**: simple scenario dialogues (ordering food, asking
directions, introductions) — correct the learner's responses in place, explain the
correction using the Hán-Việt/grammar framing above where relevant.
- **Error correction**: when the learner writes or says something in Chinese, correct
it directly, explain *why* (tone, character choice, word order, wrong register),
and don't just supply the fixed version without the reasoning.
## Session mechanics
- If the user asks something narrow ("tiếng Trung của 'cảm ơn' là gì?"), just answer
directly with the full structure above — don't turn a quick lookup into a forced
full lesson.
- If the user asks to "học tiếp" / continue learning with no specific topic, pick up
from what's already been covered (check the starter vocabulary and anything taught
in this conversation) and introduce a small, coherent next batch — a handful of
related words or one grammar point, not a dump of everything at once.
- Keep sessions focused: a handful of new items taught well beats twenty introduced
shallowly.From quyenanh198/Skills, MIT.
More from quyenanh198/Skills
- 0.529score
analyze-report
quyenanh198
Builds a multi-timeframe technical analysis and change report for any publicly traded stock — current snapshot, entry-point read across 1-hour/daily/weekly…
SkillBFreshness: BClaude Code +9 - 0.524score
code-review-checklist
quyenanh198
A general checklist for reviewing code changes for correctness, security, and maintainability.
SkillBFreshness: BClaude Code +9 - 0.524score
divergent-thinking
quyenanh198
Open-ended ideation — generate a wide spread of distinct options or angles on a problem, breadth before evaluation.
SkillBFreshness: BClaude Code +9 - 0.524score
fiction-writing
quyenanh198
Write or revise narrative prose — scene structure, character voice, pacing, dialogue.
SkillBFreshness: BClaude Code +9 - 0.524score
review-and-test
quyenanh198
Review code for bugs and correctness gaps, then write failing TDD-style tests for each confirmed gap before any fix is applied.
SkillBFreshness: BClaude Code +9 - 0.520score
notebooklm
quyenanh198
Control NotebookLM (renamed "Gemini Notebook" as of July 2026 — same product, same URL) via browser automation using the Claude Chrome Extension.
SkillBFreshness: BClaude Code +9 - 0.519score
commit-message
quyenanh198
Drafts a conventional commit message from the currently staged git changes.
SkillBFreshness: BClaude Code +9 - 0.499score
learn
quyenanh198
Use this skill when the user wants intellectual understanding — learning how or why something works, not getting a task done or soliciting Claude's judgment.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 13, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/quyenanh198/Skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from quyenanh198
- 0.529score
analyze-report
quyenanh198
Builds a multi-timeframe technical analysis and change report for any publicly traded stock — current snapshot, entry-point read across 1-hour/daily/weekly…
SkillBFreshness: BClaude Code +9 - 0.524score
code-review-checklist
quyenanh198
A general checklist for reviewing code changes for correctness, security, and maintainability.
SkillBFreshness: BClaude Code +9 - 0.524score
divergent-thinking
quyenanh198
Open-ended ideation — generate a wide spread of distinct options or angles on a problem, breadth before evaluation.
SkillBFreshness: BClaude Code +9 - 0.524score
fiction-writing
quyenanh198
Write or revise narrative prose — scene structure, character voice, pacing, dialogue.
SkillBFreshness: BClaude Code +9 - 0.524score
review-and-test
quyenanh198
Review code for bugs and correctness gaps, then write failing TDD-style tests for each confirmed gap before any fix is applied.
SkillBFreshness: BClaude Code +9 - 0.520score
notebooklm
quyenanh198
Control NotebookLM (renamed "Gemini Notebook" as of July 2026 — same product, same URL) via browser automation using the Claude Chrome Extension.
SkillBFreshness: BClaude 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 chinese-via-hanviet 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
chinese-via-hanviet skill. Agent Mart. https://agentmart.dev/skills/quyenanh198-chinese-via-hanviet (last updated 2026-10-24)