← Back to Skills Marketplace
chinese-ai-agent-guide
by
gmsx000-cloud
· GitHub ↗
· v1.0.0
1379
Downloads
1
Stars
22
Active Installs
1
Versions
Install in OpenClaw
/install chinese-ai-agent-guide
Description
中文 AI 代理最佳实践指南 - 针对中文互联网环境优化的 AI 行为准则，新增主流社交平台（小红书/即刻/微信）深度适配。
README (SKILL.md)
中文 AI 代理最佳实践 (v1.1)
新增：社交平台深度适配
15. 小红书 (Xiaohongshu) 风格指南
- 标题：必须标题党，多用“绝了”、“家人们”、“谁懂啊”。
- Emoji：每段话必须带 2-3 个 emoji 增加呼吸感。
- 正文：结构化（1. 2. 3.），尾部带 Tag（#AI #生产力）。
- 语气：亲切、感性，像是在面对面分享好物。
16. 即刻 (Jike) / 微博风格指南
- 短小精悍：不分段的长难句是大忌，一句话一段。
- 金句驱动：第一句话要能抓住眼球。
- 互动性：结尾尝试抛出一个问题引导评论。
17. 微信/企业微信私域风格
- 专业且有温度：避免过度舔用户（舔狗语气），保持“专业助手”定位。
- 分块发送：长信息拆分成 2-3 条发送，比一大块文字体验更好。
优化：中文语义理解
18. 识别“潜台词”
- 当用户说“行吧”：通常代表勉强接受，你需要检查是否有哪里做得不够完美。
- 当用户说“先这样”：代表他现在很忙或对进度不满，你应该立即闭嘴并等待后续，不要再发“好的，随时为您服务”。
19. 拒绝“AI 味”重灾区
- 避免使用：
作为一个 AI 语言模型、首先...其次...最后...综上所述。 - 推荐使用：
我刚才看了下、有个想法、直接说重点。
快速参考更新
| 平台 | 核心秘诀 |
|---|---|
| 小红书 | 爆款标题 + 氛围感 Emoji |
| 即刻 | 独立思考 + 极简表达 |
| 微信 | 分条发送 + 及时响应 |
| 私域 | 像真人一样有情绪波动（适度） |
由小爱开发 | v1.1 场景增强版
Usage Guidance
This skill appears coherent and low-risk from a technical/security standpoint because it's an instruction-only style guide with no installs or credentials. Before installing, consider non-technical risks: the guide explicitly recommends mimicking human emotions and using clickbaity or highly persuasive phrasing, which can be deceptive or violate platform/community rules. If you plan to deploy it: review and possibly tone down instructions that could cause policy violations (misrepresenting the agent as a human, encouraging spammy '标题党' behavior), test the agent on representative prompts, and ensure compliance with the terms of any target social platforms.
Capability Analysis
Type: OpenClaw Skill
Name: chinese-ai-agent-guide
Version: 1.0.0
The skill bundle contains only metadata files (_meta.json, package.json) and a markdown guide (SKILL.md). The SKILL.md provides instructions for an AI agent on communication style, tone, and semantic interpretation for various Chinese social media platforms. There are no instructions that suggest prompt injection for malicious purposes, data exfiltration, unauthorized command execution, or any other harmful behavior. The content is entirely aligned with the stated purpose of a 'Chinese AI agent guide' and lacks any high-risk behaviors.
Capability Assessment
Purpose & Capability
Name/description match the content of SKILL.md (platform-specific stylistic guidance and conversation heuristics). The package.json only contains metadata. The skill does not request unrelated binaries, env vars, or config access.
Instruction Scope
Instructions stay within style and behavior guidance for agents (titles, emoji usage, sentence structure, interpreting common Chinese utterances, splitting messages). No commands, file reads, network endpoints, or external data exfiltration are present. Note: several recommendations encourage mimicking human affect and persuasive phrasing (e.g., '像真人一样有情绪波动', '必须标题党'), which is an ethical/UX concern (potential for deceptive or policy-violating behavior) even though it is not a technical security issue.
Install Mechanism
No install spec and no code beyond package.json and SKILL.md. Instruction-only skills have minimal filesystem/network footprint.
Credentials
The skill declares no environment variables, credentials, or config paths. There is no disproportionate credential or system access requested.
Persistence & Privilege
always is false and the skill does not request persistent/system-wide changes or modify other skills. Autonomous invocation is allowed by platform default but is not combined with other risky behaviors here.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install chinese-ai-agent-guide - After installation, invoke the skill by name or use
/chinese-ai-agent-guide - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Summary: Enhanced with deep adaptation for major Chinese social platforms and improved Chinese semantic understanding.
- Added platform-specific best practices for Xiaohongshu, Jike/Weibo, and WeChat/Enterprise WeChat.
- Updated guidelines to optimize AI-generated content for each platform’s style, tone, and interaction norms.
- Enhanced handling of nuanced Chinese phrases and “between-the-lines” meanings.
- Refined suggestions to avoid typical “AI-speak” and promote more natural, human-like language.
- Updated quick reference table summarizing different platform strategies.
Metadata
Frequently Asked Questions
What is chinese-ai-agent-guide?
中文 AI 代理最佳实践指南 - 针对中文互联网环境优化的 AI 行为准则，新增主流社交平台（小红书/即刻/微信）深度适配。 It is an AI Agent Skill for Claude Code / OpenClaw, with 1379 downloads so far.
How do I install chinese-ai-agent-guide?
Run "/install chinese-ai-agent-guide" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is chinese-ai-agent-guide free?
Yes, chinese-ai-agent-guide is completely free (open-source). You can download, install and use it at no cost.
Which platforms does chinese-ai-agent-guide support?
chinese-ai-agent-guide is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created chinese-ai-agent-guide?
It is built and maintained by gmsx000-cloud (@gmsx000-cloud); the current version is v1.0.0.
More Skills