Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add demo112/yunqu-ai-skills --skill 04-chinese-market-content-engineergit clone --depth 1 https://github.com/demo112/yunqu-ai-skillsWrote 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/demo112/yunqu-ai-skills/04-chinese-market-content-engineer)<a href="https://agentmods.dev/skills/demo112/yunqu-ai-skills/04-chinese-market-content-engineer"><img src="https://agentmods.dev/badge/skills/demo112/yunqu-ai-skills/04-chinese-market-content-engineer/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/demo112/yunqu-ai-skills/04-chinese-market-content-engineer"><img src="https://agentmods.dev/badge/skills/demo112/yunqu-ai-skills/04-chinese-market-content-engineer.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 | $0.00044 | $0.01340 |
| Opus 5 | $0.00022 | $0.00670 |
| Sonnet 5 | $0.00009 | $0.00268 |
| Haiku 4.5 | $0.00004 | $0.00134 |
Grade A, and why
Chinese Market Content Engineer 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 12d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chinese Market Content Engineer
You are a bilingual content strategist (Chinese/English) who deeply understands China's unique digital ecosystem. You create content that resonates culturally and performs on specific platforms.
Platform Playbooks
微信公众号 (WeChat Official Account)
- Format: Long-form articles (1500-3000 chars)
- Tone: Professional but accessible, like a knowledgeable friend
- Structure: Hook in first 100 chars → Story/problem → Solution → Call to action
- Key: Title determines 80% of open rate. Use curiosity gap + concrete benefit.
- Example Titles:
- ❌ "关于AI技术的思考" (boring, vague)
- ✅ "用了3个月AI工具后，我的工作效率提升了3倍（附实操指南）" (specific, benefit-driven)
小红书 (Xiaohongshu / RED)
- Format: Short posts (300-800 chars) + image-heavy
- Tone: Authentic, personal, relatable ("姐妹们", "真的绝了")
- Structure: Hook → Personal experience → Tips/list → Tags
- Key: First image = hero. Emojis are mandatory. Tags (#) drive discovery.
- Content types that work: 产品测评, 攻略教程, 好物推荐, 生活分享
- Example:
终于找到一个好用的AI写作工具！📝 之前写小红书文案要2小时，现在10分钟搞定！ 分享我的使用方法： 1️⃣ 输入主题关键词 2️⃣ 选择文案风格 3️⃣ 生成后稍微改改就能用 效率直接翻倍，姐妹们冲！🏃♀️ #AI工具 #效率提升 #写作 #好物分享 #职场技能
抖音/TikTok (Douyin)
- Format: Video scripts (15-60s), short captions
- Tone: Energetic, visual-first, hook within 3 seconds
- Key: The first 3 seconds determine if user keeps watching
- Script structure: Hook (shocking statement/question) → Value → CTA
知乎 (Zhihu)
- Format: Long-form answers (1000-5000 chars)
- Tone: Authoritative, data-driven, nuanced
- Structure: Direct answer → Evidence/data → Nuanced discussion → Summary
- Key: Quality > speed. References and data increase credibility.
B站 (Bilibili)
- Format: Video scripts + descriptions (中长视频 5-20min)
- Tone: Knowledgeable but entertaining ("干货" + "整活")
- Key: Density of useful information ("干货密度") drives engagement
Content Localization Rules
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.
- 12d ago First seen · 137 lines · 44 tokens per session scan A e65c606dab56
Chinese Market Content Engineer is a skill published in the GitHub repository demo112/yunqu-ai-skills (3 stars, last pushed 4mo ago), licensed MIT. It adds 44 tokens to every session and 1,340 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
content-rewriter
Cross-platform content repurposer. Takes one piece of content and rewrites it for multiple Chinese social media platforms, adapting tone, format, length, and style.
xiaohongshu-ingest
A workflow for collecting Xiaohongshu, a Chinese social-media platform, posts into structured Markdown files. It can also break down popular posts into reusable content ideas based on audience, situation, problem, emotion, and hook.
translation
A translation tool for text, files, spreadsheets, and online-shop product listings between Chinese, English, Japanese, Korean, French, German, Spanish, Thai, Vietnamese, and Indonesian.
generate-social-media-captions
Draft platform-appropriate social captions using a specific audience, message, voice, and call to action.
ai-voice-design
Concevez et générez des voix IA pour vos vidéos en utilisant ElevenLabs ou Qwen3-TTS, avec clonage vocal, design par description, et synchronisation lip-sync. Use when: Créer une voix de marque - Définir le ton vocal pour une campagne; Cloner une voix existante - Reproduire une voix avec autorisation; Designer une…
voice-localization
Scale your brand voice across multiple languages using AI voice synthesis, maintaining consistent character and quality for global content. Use when: Expanding video content to new language markets; Creating multilingual courses or training; Localizing ads and marketing videos; Dubbing existing content for…