Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/chen3feng/agent-skillsnpx agentmods add skills/chen3feng/agent-skills/chinese-markdown-styleWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/chen3feng/agent-skills/chinese-markdown-style)<a href="https://agentmods.dev/skills/chen3feng/agent-skills/chinese-markdown-style"><img src="https://agentmods.dev/badge/skills/chen3feng/agent-skills/chinese-markdown-style/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/chen3feng/agent-skills/chinese-markdown-style"><img src="https://agentmods.dev/badge/skills/chen3feng/agent-skills/chinese-markdown-style.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00031 | $0.00893 |
| Opus 5 | $0.00015 | $0.00447 |
| Sonnet 5 | $0.00006 | $0.00179 |
| Haiku 4.5 | $0.00003 | $0.00089 |
Grade A, and why
chinese-markdown-style scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chinese Markdown style
When to use
Any time you edit, review, or generate Chinese documentation — READMEs, design docs, tutorials. Especially relevant when the repo has mixed Chinese + English + code.
Problem
Chinese Markdown drifts in predictable ways:
- No space between CJK characters and adjacent ASCII letters / digits
(
使用Python3instead of使用 Python 3). - Half-width punctuation after a Han character (
你好,世界instead of你好，世界). - English proper nouns lowercased or re-cased (
github,Macos,scons). - Unnecessary full-width or double spaces around inline code and links.
These accumulate quietly and make diffs noisy later.
Solution
Follow chen3feng/cn-doc-style-guide
and lean on its tooling. The checker / previewer / formatter now ship as a
stdlib-only Python package cndocstyle (src-layout under src/), so invoke
them with python3 -m cndocstyle.<module>:
# 1. Clone the guide as a sibling of your doc repo
git clone https://github.com/chen3feng/cn-doc-style-guide.git
# 2. Make the package importable (src-layout). Pick ONE:
export PYTHONPATH=../cn-doc-style-guide/src # for this shell, or
cd ../cn-doc-style-guide && pip install -e . # editable install
# 3. Check — reports every violation, exits non-zero if any
python3 -m cndocstyle.check path/to/docs
# 4. Preview what an auto-fix would change (dry-run diff)
python3 -m cndocstyle.preview path/to/docs
# 5. Dry-run the formatter (default) — lists files that would change
python3 -m cndocstyle.formatter path/to/docs
# 6. Apply the safe subset of fixes
python3 -m cndocstyle.formatter --apply path/to/docs
The old
tools/check.py/tools/preview.py/tools/format.pyscripts have been removed — use the module form above.
Core rules you should apply even without the tool:
- One half-width space between CJK and ASCII (letters, digits), except around Chinese punctuation.
- Use full-width punctuation in Chinese prose:
，。：；？！、""'' （）《》and……for ellipsis. - Keep English proper nouns in their canonical casing: GitHub, macOS, Python, JSON, Scons.
- Units follow English convention with a space:
10 MB,3.6+. - Code, filenames, commands, paths go in backticks and are not translated.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 96 lines · 31 tokens per session scan A 6df65921d89e
chinese-markdown-style is a skill published in the GitHub repository chen3feng/agent-skills (5 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 31 tokens to every session and 893 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
documentation-style
NVCF public docs style: short, plain, ASCII Markdown with no bold, emojis, em-dash, or en-dash. Use when editing public docs, READMEs, AGENTS.md, agent skills, plans, GitHub issues, or GitHub Pull Request descriptions.
mr-li-writer
A Chinese-language editing and writing workflow for turning ideas, source material, or rough topics into publishable content. It adapts the structure and wording to formats such as WeChat articles, Zhihu answers, Xiaohongshu posts, websites, and blogs.
note-organizer
Use this skill whenever the user wants to organize course materials, lecture notes, PPT/PDF/DOCX files, textbooks, personal notes, senior-student notes, historical exams, review questions, standards, manuals, or scattered study resources into a structured Markdown note library. Use it even when the user only says…
ikevss-zh-friendly
A Chinese-language helper that scans installed AI tools and translates or fills in their skill descriptions so developers can understand what each capability does. It can also produce a list of available skills, agents, and command-line tools.
seedance-vocab-zh
Look up 550+ Chinese cinematic, photography, and production terms with English equivalents and prompt-ready phrases for Seedance 2.0 across 22 categories, including filter-safe vocabulary for action, weapons, and combat. Use when writing prompts in Mandarin, translating a production concept into Chinese Seedance…
seedance-examples-zh
Browse 16+ battle-tested, production-ready Chinese prompt examples for Seedance 2.0 across 8 genres: drama, action, advertising, animation, product, one-take, VFX, and music sync. Use to learn advanced prompt structure, copy-paste working examples, or find inspiration for new scenes.