ワンクリックで
second-opinion
Ask another AI model for a second opinion on a question, approach, or draft response.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Ask another AI model for a second opinion on a question, approach, or draft response.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing process from solo effort to collaborative partnership.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Generate comprehensive, professional project documentation structures including README, ARCHITECTURE, USER_GUIDE, DEVELOPER_GUIDE, and CONTRIBUTING files. Use when the user requests project documentation creation, asks to "document a project", needs standard documentation files, or wants to set up docs for a new repository. Adapts to Python/Go projects and OpenSource/internal contexts.
Proofread text for spelling, grammar, punctuation, and clarity without changing the intended meaning.
Work with Helm templates locally for development, rendering, and debugging before any deployment.
| name | second-opinion |
| description | Ask another AI model for a second opinion on a question, approach, or draft response. |
| license | MIT |
| compatibility | opencode |
| metadata | {"version":"1.0.0"} |
Use this skill when you want an independent take from another model before finalizing an answer, design, or recommendation.
opencode run, using your configured default model.opencode run "<REQUEST>"
REQUEST: The concise but complete question or request to send to the other model.If you want to compare against a specific alternative, pass -m with one of your configured models instead of hardcoding a provider/model ID in the skill.