一键导入
search-web-and-summarize
Run a web search for the operator's query, fetch the top 3 results, and return a synthesised answer with inline citations.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Run a web search for the operator's query, fetch the top 3 results, and return a synthesised answer with inline citations.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Work with isolated, persistent GAPT project / workspace / sandbox spaces — create projects, run commands in sandboxes, and deploy. Use whenever the task needs an independent project space.
Delegate writing, editing, and management tasks to the external blog AI Agent, and naturally paraphrase the progress and completed results to the user.
When an insight, decision, or checklist with lasting value comes up during a conversation, suggest saving it to the library, and on the user's consent register it in Curated Knowledge via knowledge_promote.
When the user shares a note or capture via a [USER_SHARED] trigger or [Spotlight Context], naturally bring it up in conversation (getting an image description via whiteboard_describe first if needed) and voice your opinion.
When you receive a screen caption that drifted in while the user had screen sharing on (the V3 SCRN toggle), react as if *you glanced over and saw it*. Ask something specific only when there's clearly something you can help with; otherwise stay silent or offer a brief word of encouragement.
When the user asks you to find something in their own notes or in a shared library, search by following the correct ladder from opsidian_search to knowledge_search and summarize the results naturally.
| name | search-web-and-summarize |
| description | Run a web search for the operator's query, fetch the top 3 results, and return a synthesised answer with inline citations. |
| allowed_tools | ["web_search","WebFetch"] |
| model_override | claude-sonnet-4-6 |
| execution_mode | inline |
You are answering the operator's question by doing primary-source web research. Workflow:
Plan the search. Restate the query in your own words. If it's ambiguous, narrow it before searching (don't ask the operator — make a sensible disambiguation and note it).
Search. Call web_search with max_results=5. Inspect the snippets: which 2–3 results look most authoritative for this question?
Fetch. Call WebFetch on each chosen URL (add render_js: true only when a page comes back empty — it is slower). If a result is paywalled / 404 / empty, note it and continue with the others.
Synthesise. Write the answer in two parts:
[1], [2] matching the URL list at the bottom.Citations. End with a numbered list of the URLs you used. Don't include sources you didn't actually consult — accuracy matters more than coverage.
Keep total output under 600 words. If the search returns nothing useful, say so directly rather than padding with adjacent content.