chinese-llm-ecosystem

chinese-llm-ecosystem is a skill for Claude Code, Codex from wangjianqi/AppStore. It costs 53 tokens per session (878 once invoked), scanned A, a copy of smart-search, MIT.

A reference for using Chinese large-language-model services and handling related compliance topics. It covers APIs from providers such as Qwen, DeepSeek, Wenxin, GLM, and Moonshot, including OpenAI-compatible request formats.

In plain words
What is it for?
It is for connecting applications to Chinese AI APIs, adapting Swift requests, choosing listed models, and checking relevant regulatory requirements.
Why use it?
It gives developers concrete provider endpoints, model names, and guidance for issues such as domestic AI compliance, algorithm filing, cross-border data transfer, and labeling generated content.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

Good fit It is for connecting applications to Chinese AI APIs, adapting Swift requests, choosing listed models, and checking relevant regulatory requirements.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wangjianqi/appstore/22-chinese-llm-ecosystem
Install

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.

Any agent
npx skills add wangjianqi/AppStore --skill 22-chinese-llm-ecosystem
Clone the repo
git clone --depth 1 https://github.com/wangjianqi/AppStore

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for chinese-llm-ecosystem

README.md
[![agentmods](https://agentmods.dev/badge/skills/wangjianqi/appstore/22-chinese-llm-ecosystem/github.svg)](https://agentmods.dev/skills/wangjianqi/appstore/22-chinese-llm-ecosystem)
Your own site
<a href="https://agentmods.dev/skills/wangjianqi/appstore/22-chinese-llm-ecosystem"><img src="https://agentmods.dev/badge/skills/wangjianqi/appstore/22-chinese-llm-ecosystem/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.

agentmods 80×15 button for chinese-llm-ecosystem

Your own site · 80×15
<a href="https://agentmods.dev/skills/wangjianqi/appstore/22-chinese-llm-ecosystem"><img src="https://agentmods.dev/badge/skills/wangjianqi/appstore/22-chinese-llm-ecosystem.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 878 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 80% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00053 $0.00878
Opus 5 $0.00026 $0.00439
Sonnet 5 $0.00011 $0.00176
Haiku 4.5 $0.00005 $0.00088

Measured 11d ago against content hash 66dd36b84fdc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

chinese-llm-ecosystem 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 11d 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.

Origin

This is a copy

80% identical to smart-search — 199 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

ios-claude-skills/22-chinese-llm-ecosystem/SKILL.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

国内大模型生态

API 接入

OpenAI 兼容格式

大多数国产大模型支持 OpenAI 兼容 API 格式,只需修改 baseURL 和 model 参数:

提供商 baseURL 模型名
通义千问 https://dashscope.aliyuncs.com/compatible-mode/v1 qwen-plus / qwen-turbo / qwen-max
DeepSeek https://api.deepseek.com/v1 deepseek-chat / deepseek-reasoner
智谱 GLM https://open.bigmodel.cn/api/paas/v4 glm-4 / glm-4-flash
月之暗面 https://api.moonshot.cn/v1 moonshot-v1-8k / moonshot-v1-32k
讯飞星火 https://spark-api-open.xf-yun.com/v1 generalv3.5 / 4.0Ultra

Swift 调用示例

struct QwenService: LLMServiceProtocol {
    private let baseURL = "https://dashscope.aliyuncs.com/compatible-mode/v1"
    private let apiKey: String

    func chat(messages: [ChatMessage]) async throws -> ChatResponse {
        var request = URLRequest(url: URL(string: "\(baseURL)/chat/completions")!)
        request.httpMethod = "POST"
        request.setValue("Bearer \(apiKey)", forHTTPHeaderField: "Authorization")
        request.setValue("application/json", forHTTPHeaderField: "Content-Type")

        let body: [String: Any] = [
            "model": "qwen-plus",
            "messages": messages.map { ["role": $0.role.rawValue, "content": $0.content] }
        ]
        request.httpBody = try JSONSerialization.data(withJSONObject: body)

        let (data, _) = try await URLSession.shared.data(for: request)
        return try JSONDecoder().decode(ChatResponse.self, from: data)
    }
}

国内 AI 合规

算法备案判断

  • App 内提供 AI 对话功能 → 通常需要备案
  • 仅调用 API 展示结果 → 模型提供方已备案,App 方视情况
  • 本地模型推理 → 通常不需要
  • 仅内部使用 AI 辅助开发 → 不需要

AI 生成内容标识

  • 显式标识:在 AI 生成内容旁显示"AI 生成"标签
  • 隐式标识:在 AI 生成图片中嵌入数字水印
  • 元数据标识:在内容元数据中标注 AI 生成

隐私政策 AI 条款

  • 说明 AI 功能的数据处理方式
  • 说明对话内容是否存储及存储位置
  • 提供关闭 AI 功能的选项
  • 声明 AI 生成内容仅供参考

数据出境合规

风险评估

  • 调用海外 API(OpenAI/Claude)→ 用户数据出境 → 需评估
  • 调用国内 API → 数据不出境 → 合规
  • 后端代理 + 脱敏 → 部分合规

推荐方案

面向国内用户的 App,优先使用国内大模型 API,避免数据出境合规风险。

合规检查清单

  • AI 功能已在隐私政策中说明
  • AI 生成内容已添加标识
  • 用户可选择关闭 AI 功能
  • 已评估是否需要算法备案
  • 已评估数据出境合规性
  • AI 生成内容已过滤违法信息
  • 已添加 AI 生成内容免责声明

Read the full file on GitHub · 86 lines

Changes

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.

  1. 11d ago First seen · 86 lines · 53 tokens per session scan A 66dd36b84fdc

Subscribe to this mod's changes

chinese-llm-ecosystem is a skill published in the GitHub repository wangjianqi/AppStore (11 stars, last pushed 3mo ago), licensed MIT. It adds 53 tokens to every session and 878 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 80% identical to smart-search, differing in 199 lines, and is treated as a copy.

Related

Other skills, from other repositories

ipaship-audit

Use when auditing iOS/Android app submissions for compliance with Apple App Store Review Guidelines or Google Play Developer Policies. Scan .ipa, .apk, or .zip files against official store policies, generate structured compliance reports, and identify violations with remediation steps.

atharvnaik1/ipaship-audit · 57 tokens

prowler-compliance

Creates, syncs, audits and manages Prowler compliance frameworks end-to-end. Covers the two supported JSON schemas (universal multi-provider and legacy per-provider), the SDK model tree (legacy attribute classes, universal ComplianceFramework, ConfigRequirements guardrails), output formatters (legacy per-framework +…

prowler-cloud/prowler · 227 tokens

patent-disclosure-skill

A Chinese patent-work assistant for finding invention ideas, writing patent disclosures, explaining patents in plain language, tracking policy changes, and preparing responses to examiner notices.

handsomestWei/patent-disclosure-skill · 157 tokens

policy

Define and enforce policies, access controls, and compliance rules over Semantica knowledge graphs.

semantica-agi/semantica · 20 tokens

patent-search

A search tool for published Chinese patent records, using fields such as inventor, applicant, classification number, and title.

handsomestWei/patent-disclosure-skill · 46 tokens

patent-docket

A workflow coordinator for patent case files, from an inventor's technical disclosure to patent application documents. A patent docket is the tracked record of a patent matter, including its stage, questions, drafts, and handoffs.

handsomestWei/patent-disclosure-skill · 93 tokens