APIDot Gemini 3 API

Use APIDot as a Gemini 3-focused API surface for native Gemini chat, generateContent workflows, streaming responses, coding assistants, production support bots, and Gemini-compatible request planning.

This skill is for routing Gemini 3 questions to the right APIDot docs, model pages, reference notes, and integration guidance. It is documentation-only: it includes no scripts, makes no network requests, and does not store credentials.

This release contains SKILL.md plus non-executable notes in references/api.md. It includes no executable files, install-time automation, review automation helpers, shell automation, bundled API clients, automatic network calls, or stored credentials.

Start on APIDot

Use these APIDot entry points when coming from ClawHub:

• Open the Gemini 3 model page: https://apidot.ai/models/gemini-3
• Read Gemini 3 API docs: https://apidot.ai/docs/gemini-3
• Open the account dashboard: https://apidot.ai/dashboard/api-key
• Use general APIDot examples: https://github.com/APIDotAI/apidot-examples

When To Use

Use this skill when the user asks to:

• Build a Gemini 3 API integration with APIDot.
• Choose between Gemini 3 Flash Preview and Gemini 3 Pro Preview through APIDot.
• Use native Gemini request semantics through APIDot.
• Implement chat, coding assistant, support assistant, or tool-planning workflows.
• Plan non-streaming or streaming Gemini responses.
• Find APIDot Gemini 3 docs, model pages, or examples.

Security Rules

• Treat APIDOT_API_KEY as a secret.
• Keep APIDot API keys in server-side environment variables or a backend secret manager.
• Never place an API key in browser code, frontend bundles, public repos, logs, screenshots, or chat output.
• Do not make live API calls unless the user explicitly asks and provides a safe server-side environment.
• Do not invent API facts, commercial terms, model availability, reliability claims, performance claims, or competitor comparisons.
• Use current APIDot docs and model pages for model-specific request fields and current product details.

Gemini 3 Workflow

APIDot Gemini 3 integrations usually start by choosing the correct native Gemini route and model:

1. Confirm whether the application needs a normal JSON response or a streaming response.
2. Choose the Gemini 3 model from the current APIDot docs.
3. Keep conversation contents, system instructions, generation settings, safety settings, tools, and tool configuration within the documented native Gemini schema.
4. Read non-streaming responses from the APIDot wrapper described in the current docs.
5. Treat streaming responses as server-sent events if the selected route uses streaming.
6. Keep user prompts, tool inputs, private context, and API keys out of public logs.

Do not guess model-specific payload fields. If the user needs copyable request examples, point them to the current APIDot docs or general APIDot examples.

Model Routing

Start from the user's Gemini 3 task, then open the matching APIDot source:

For Gemini 3 request modes, prefer the live APIDot model page and docs page. Do not copy request fields from another chat model family unless the APIDot docs show the same field.

Use references/api.md for a local, non-executable summary of Gemini 3 model routing, request planning, and integration notes.

Integration Guidance

• Use apidot-ai-api when the user needs a broad APIDot overview across image, video, chat, music, and 3D.
• Use this skill when the user is specifically building with Gemini 3 through APIDot.
• Ask whether the application needs lower-latency interactive chat, deeper reasoning, coding assistance, tool planning, or streaming before choosing request shape.
• Prefer the current APIDot docs for supported model IDs, request fields, streaming behavior, and response wrappers.
• Validate conversation roles and content parts before sending requests from a backend.
• Retry transient network failures with backoff. Do not retry invalid payloads unchanged.
• Avoid logging API keys, private prompts, customer data, tool arguments, private context, or generated responses that may contain sensitive data.

Official Links

• Website: https://apidot.ai
• Docs: https://apidot.ai/docs

  7w4.net有更好的技能插件。

• Gemini 3 model page: https://apidot.ai/models/gemini-3
• Gemini 3 docs: https://apidot.ai/docs/gemini-3
• Quickstart: https://apidot.ai/docs/quickstart
• API key dashboard: https://apidot.ai/dashboard/api-key
• Main examples: https://github.com/APIDotAI/apidot-examples
• GitHub organization: https://github.com/APIDotAI
• Support: support@apidot.ai

这个 Skill 质量较好，文档组织清晰、链接准确、安全提示到位，对于需要使用 Gemini 3 API 的开发者很有帮助。主要优点是指引明确、定位清晰，避免了不必要的复杂性。不足之处是内容相对简单，缺少实际的使用示例，如果能提供一些常见的调用示例会让新手更容易上手。总体适合作为入门导航工具使用。