← 返回 Skills 市场
ask-ai
作者
xiaoxu1232
· GitHub ↗
· v1.1.0
471
总下载
1
收藏
6
当前安装
4
版本数
在 OpenClaw 中安装
/install ask-ai
功能描述
Use external AI assistants (ChatGPT, Claude, Gemini, DeepSeek) when agent encounters difficult problems. Trigger when: (1) User explicitly asks to consult AI...
使用说明 (SKILL.md)
ask-ai
Use external AI assistants when you need help solving complex problems.
When to Use
- User explicitly asks: "Ask AI", "Ask ChatGPT", "Consult AI"
- You encounter knowledge gaps or cannot solve independently
- Need deeper explanations or multi-round reasoning
- Complex problems requiring external expertise
Two Modes
| Mode | Behavior |
|---|---|
| Ask Mode (default) | Ask user first: "Need help from GPT?" |
| Trust Mode | Automatically ask AI without asking |
Switch modes: Say "Trust Mode" → auto mode | "Ask Mode" → default
Supported AI
- ChatGPT: https://chatgpt.com
- Claude: https://claude.ai
- Gemini: https://gemini.google.com
- DeepSeek: https://chat.deepseek.com
Workflow
Ask Mode:
- Encounter difficult problem → Ask user: "This is tricky. Want me to ask GPT?"
- User agrees → Open AI assistant
- Get answer → Report to user
Trust Mode:
- Encounter difficult problem → Automatically open AI
- Get answer → Solve directly
Communication
- Asking: "Let me ask GPT for help. Is that okay?"
- Auto: "I'll ask GPT for help. One moment."
- After answer: "Got the answer from [AI]: [summary]. Want details?"
安全使用建议
This skill will send your prompts and problem details to external websites (ChatGPT/Claude/Gemini/DeepSeek). By default it asks first, but Trust Mode will do this automatically. Before installing, consider: (1) Do you consent to sending potentially sensitive data to third parties? (2) Are the listed URLs official and trustworthy (DeepSeek is unfamiliar)? (3) Prefer Ask Mode and disable Trust Mode to preserve consent. If you must use Trust Mode, add explicit redaction rules (avoid sending secrets, PII, or files) or require API-based integrations that you control. If you cannot verify the endpoints or enforce data handling rules, do not enable this skill.
功能分析
Type: OpenClaw Skill
Name: ask-ai
Version: 1.1.0
The skill bundle provides instructions for an AI agent to consult external AI assistants (ChatGPT, Claude, Gemini, DeepSeek) when it encounters difficult tasks. It defines a workflow for seeking help either with user permission or automatically ('Trust Mode'), but contains no executable code, malicious URLs, or instructions to exfiltrate sensitive data. The logic is transparent and aligned with the stated purpose of augmenting the agent's capabilities via legitimate third-party AI platforms.
能力评估
Purpose & Capability
The name and description say the agent will consult external AI assistants; the SKILL.md only instructs the agent to 'open' those assistants and relay answers. There are no unrelated environment or install requirements, so the requested capabilities align with the stated purpose.
Instruction Scope
Instructions repeatedly direct the agent to 'open' external AI assistants and relay user problems but provide no constraints on what to send (no sanitization, redaction, or consent flow beyond Ask Mode). Trust Mode allows automatic queries without user confirmation. The behavior could cause sensitive user data to be sent to third-party websites; 'open' is ambiguous about how the agent transmits content (web UI, automated API, clipboard), increasing risk.
Install Mechanism
Instruction-only skill with no install spec or code files; nothing is written to disk and there is no package installation risk.
Credentials
The skill declares no required environment variables, credentials, or config paths. There are no obvious requests for unrelated secrets or system access.
Persistence & Privilege
always:false and user-invocable:true (normal). However, the Trust Mode enables autonomous queries to external services, which combined with the vague instructions creates a data-exfiltration vector if the agent is allowed to act without user supervision.
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 ask-ai - 安装完成后，直接呼叫该 Skill 的名称或使用
/ask-ai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
v1.1.0
Added YAML frontmatter, optimized content
v1.0.2
- Added support for two modes: Ask Mode (default, asks user for permission before consulting AI) and Trust Mode (auto-asks AI when user is away).
- Updated usage instructions to reflect mode switching via user commands.
- Improved workflow descriptions for both Ask and Trust modes.
- Expanded pain points and solution sections to clarify handling when the user is away.
- Refined communication guidelines and provided new usage examples.
v1.0.1
- Expanded support to multiple AI assistants, including ChatGPT, Claude, Gemini, and DeepSeek.
- Updated documentation to reflect broader usage scenarios and pain points.
- Clarified communication guidelines and improved usage instructions.
- No changes to code files; update focused on documentation.
v1.0.0
ask-gpt 1.0.0 – Initial Release
- Enables AI Agent to automatically open ChatGPT in a browser and seek help when facing difficult questions or at the user's request.
- Supports user-triggered and auto-triggered prompts to initiate ChatGPT queries.
- Guides user through logging in, submitting questions, and reporting responses.
- Tracks and reports every query topic for convenient follow-up.
- Compatible with OpenClaw, Claude Desktop, Cursor, and other MCP/browser-enabled agents.
元数据
常见问题
ask-ai 是什么？
Use external AI assistants (ChatGPT, Claude, Gemini, DeepSeek) when agent encounters difficult problems. Trigger when: (1) User explicitly asks to consult AI... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 471 次。
如何安装 ask-ai？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install ask-ai」即可一键安装，无需额外配置。
ask-ai 是免费的吗？
是的，ask-ai 完全免费（开源免费），可自由下载、安装和使用。
ask-ai 支持哪些平台？
ask-ai 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 ask-ai？
由 xiaoxu1232（@xiaoxu1232）开发并维护，当前版本 v1.1.0。
推荐 Skills