← 返回 Skills 市场
Chinese LLM Models (Kimi 2.5, MiniMax 2.5, Qwen, DeepSeek) with One Key
作者
0xjordansg-yolo
· GitHub ↗
· v1.0.1
812
总下载
0
收藏
4
当前安装
2
版本数
在 OpenClaw 中安装
/install openclaw-aisa-chinese-llm-models
功能描述
Configure AIsa as a first-class model provider for OpenClaw, enabling production access to major Chinese AI models (Qwen, DeepSeek, Kimi K2.5, Doubao) throug...
安全使用建议
This skill is coherent for configuring AIsa, but it routes your prompts/requests to a third-party endpoint (api.aisa.one). Before installing or using: 1) verify AIsa's website and reputation (https://marketplace.aisa.one) and any contractual Zero Data Retention (ZDR) claims — enterprise ZDR promises may not apply to consumer accounts; 2) treat AISA_API_KEY like any secret (do not paste it into untrusted places); 3) test with non-sensitive data first to confirm privacy/behavior and pricing; and 4) if you need provable ZDR for regulated data, request the contract details from AIsa/Moonshot and confirm the coverage for your account. If you are uncomfortable trusting a third-party gateway, prefer direct vendor integrations you control.
功能分析
Type: OpenClaw Skill
Name: openclaw-aisa-chinese-llm-models
Version: 1.0.1
The skill bundle provides documentation and configuration examples for integrating the AIsa API provider with OpenClaw. All files, including SKILL.md, guide-zh-CN.md, pricing.md, and config-examples.md, contain instructions for setting environment variables, modifying OpenClaw configuration files, and using OpenClaw CLI commands to manage AI models. The `curl` commands present in SKILL.md and guide-zh-CN.md are used to query the `https://api.aisa.one/v1/models` endpoint to list available models, which is a legitimate informational action for an API integration. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, prompt injection with harmful intent, or obfuscation. The content is consistently aligned with the stated purpose of configuring a third-party AI model provider.
能力评估
Purpose & Capability
The skill's name/description match its runtime instructions: it explains how to configure AIsa as a provider, shows example OpenClaw config, CLI onboarding commands, and a curl example to list models. The single required env var (AISA_API_KEY) is exactly what an API gateway integration would need. No unrelated credentials or binaries are requested.
Instruction Scope
SKILL.md confines runtime behavior to configuration steps (exporting AISA_API_KEY, openclaw onboarding commands, editing ~/.openclaw/openclaw.json) and examples of calling the AIsa API (curl to https://api.aisa.one). There are no instructions to read unrelated system files or exfiltrate arbitrary data. Note: using the skill will cause prompts/data to be sent to the external AIsa endpoint, which is expected for this provider integration.
Install Mechanism
This is an instruction-only skill with no install spec and no code files. That minimizes on-disk execution risk; nothing is downloaded or written by the skill itself.
Credentials
Only AISA_API_KEY is required and is declared as the primary credential. Requiring a single provider API key is proportionate for this purpose. Treat the key as a secret (it grants API access and potentially billing).
Persistence & Privilege
The skill does not request always:true or any elevated platform privileges. It does reference the user's OpenClaw config file path (~/.openclaw/openclaw.json) in examples, which is reasonable for configuring a provider but does not attempt to modify other skills or system-wide settings beyond the documented provider config.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install openclaw-aisa-chinese-llm-models - 安装完成后，直接呼叫该 Skill 的名称或使用
/openclaw-aisa-chinese-llm-models触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.1
- Added detailed Chinese-language documentation and guides (`guide-zh-CN.md`, `pricing.md`) to support users in both English and Chinese.
- Moved documentation files into organized subfolders (`AIsa Chinese Models v3/`, `references/`).
- Removed duplicated top-level guide and pricing files in favor of new structured documentation.
- No changes to provider configuration or API usage—this update is documentation and structure only.
v1.0.0
Initial release of AIsa as an OpenClaw model provider, enabling access to leading Chinese LLMs.
- Adds AIsa as a first-class provider for OpenClaw, integrating Chinese AI models including MiniMax, Qwen, DeepSeek, Kimi K2.5, and Doubao.
- Supports rapid onboarding via environment variable, CLI, interactive setup, or manual config.
- Provides pre-configured, API-verified access to major models with sample pricing and feature tables.
- Highlights discounted pricing (e.g., Kimi K2.5 at ~80% of official rates) and enterprise Zero Data Retention for privacy-sensitive workloads.
- Documents temperature constraint for Kimi K2.5 and explains best practices for configuration and model selection.
- Includes instructions for listing and adding additional AIsa-supported models.
元数据
常见问题
Chinese LLM Models (Kimi 2.5, MiniMax 2.5, Qwen, DeepSeek) with One Key 是什么？
Configure AIsa as a first-class model provider for OpenClaw, enabling production access to major Chinese AI models (Qwen, DeepSeek, Kimi K2.5, Doubao) throug... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 812 次。
如何安装 Chinese LLM Models (Kimi 2.5, MiniMax 2.5, Qwen, DeepSeek) with One Key？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install openclaw-aisa-chinese-llm-models」即可一键安装，无需额外配置。
Chinese LLM Models (Kimi 2.5, MiniMax 2.5, Qwen, DeepSeek) with One Key 是免费的吗？
是的，Chinese LLM Models (Kimi 2.5, MiniMax 2.5, Qwen, DeepSeek) with One Key 完全免费（开源免费），可自由下载、安装和使用。
Chinese LLM Models (Kimi 2.5, MiniMax 2.5, Qwen, DeepSeek) with One Key 支持哪些平台？
Chinese LLM Models (Kimi 2.5, MiniMax 2.5, Qwen, DeepSeek) with One Key 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Chinese LLM Models (Kimi 2.5, MiniMax 2.5, Qwen, DeepSeek) with One Key？
由 0xjordansg-yolo（@0xjordansg-yolo）开发并维护，当前版本 v1.0.1。
推荐 Skills