← 返回 Skills 市场
model-platform-guide
作者
huixiaheyu
· GitHub ↗
· v1.0.0
· MIT-0
113
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install model-platform-guide
功能描述
查询主流大模型开放平台的 API 文档入口与精简调用要点，适用于月之暗面 Kimi、阿里云百炼、硅基流动、DeepSeek、OpenRouter 等平台。用于回答鉴权方式、base URL、OpenAI 兼容调用、聊天补全、模型名、常见差异、多平台对比与文档入口。当用户提到 Kimi、Moonshot、百炼、Da...
安全使用建议
This skill is a local collection of concise references and call examples and appears coherent with its described purpose. Things to consider before installing: (1) The agent may perform live web checks of the official docs when you ask about up-to-date model capabilities — if you care about privacy/networking, be aware of that behavior. (2) The included files show example environment variable names and code snippets; the skill itself does not require or collect keys, but you should never paste actual secret keys into chat or into code examples when using the skill. (3) Validate any official URLs returned by the skill before using them, and prefer copying examples into a secure environment (your own code) rather than executing unreviewed snippets. If you want greater assurance, ask the publisher for provenance of the references or review a few of the referenced URLs manually to confirm they point to the expected official documentation.
功能分析
Type: OpenClaw Skill
Name: model-platform-guide
Version: 1.0.0
The skill bundle is a comprehensive documentation assistant designed to help users integrate various LLM platform APIs (e.g., DeepSeek, Aliyun, Moonshot). It contains structured reference files with official documentation links, API base URLs, and standard code templates for Python, Node.js, and curl. The instructions in SKILL.md and live-check-policy.md emphasize accuracy by directing the agent to verify high-frequency changes against official sources rather than relying solely on static local data, and no malicious behaviors such as data exfiltration or unauthorized execution were found.
能力标签
能力评估
Purpose & Capability
Skill name/description match the shipped artifacts: it contains concise reference files, migration recipes, curl/Python/Node examples and an index of official doc URLs for the listed platforms. There are no unrelated binaries, installs, or environment variables required by the skill itself.
Instruction Scope
The SKILL.md explicitly limits itself to: reading its own references/* files, returning links and short examples, and performing 'dynamic verification' by visiting official docs when needed. Those actions are appropriate for a documentation/navigation skill. The instructions do not tell the agent to read arbitrary system files, secrets, or unrelated config paths. Note: dynamic verification implies the agent may fetch external documentation pages at runtime — this is expected behavior for live checks.
Install Mechanism
No install spec and no code files that would be written/executed. Instruction-only skills are lowest risk from an install perspective.
Credentials
The reference files include example environment variable names (e.g., MOONSHOT_API_KEY, DASHSCOPE_API_KEY) solely as usage examples for calling remote APIs. The skill does not declare any required env vars or request credentials. There is no disproportionate credential access.
Persistence & Privilege
always:false and no special privileges are requested. The skill does not attempt to persist configuration outside its own references or alter other skills. Autonomous invocation is allowed (platform default) but not combined with other red flags here.
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 model-platform-guide - 安装完成后，直接呼叫该 Skill 的名称或使用
/model-platform-guide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
v1.0.0
Initial release of model-platform-guide.
- Supports quick lookup of API docs and usage highlights for major model platforms (Kimi, DashScope, SiliconFlow, DeepSeek, OpenRouter, etc.).
- Provides official doc links, authentication, base URLs, and minimal usage examples for each platform.
- Enables multi-platform comparison and OpenAI API compatibility guidance.
- Offers ready-made code templates (Python, Node.js, curl) and OpenAI migration tips.
- Follows a concise, link-first approach to keep info current and avoid outdated content.
- Includes dynamic verification policy for high-change features and capability checks.
元数据
常见问题
model-platform-guide 是什么？
查询主流大模型开放平台的 API 文档入口与精简调用要点，适用于月之暗面 Kimi、阿里云百炼、硅基流动、DeepSeek、OpenRouter 等平台。用于回答鉴权方式、base URL、OpenAI 兼容调用、聊天补全、模型名、常见差异、多平台对比与文档入口。当用户提到 Kimi、Moonshot、百炼、Da... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 113 次。
如何安装 model-platform-guide？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install model-platform-guide」即可一键安装，无需额外配置。
model-platform-guide 是免费的吗？
是的，model-platform-guide 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
model-platform-guide 支持哪些平台？
model-platform-guide 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 model-platform-guide？
由 huixiaheyu（@huixiaheyu）开发并维护，当前版本 v1.0.0。
推荐 Skills