一键导入
web-search
Search the web and fetch content from URLs. Use for real-time information, API documentation, and current events.
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
Search the web and fetch content from URLs. Use for real-time information, API documentation, and current events.
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
A test skill for validating secondary skill deployment.
List and manage user feedback items from the agent inbox. Use when the user asks about feedback, bug reports, feature requests, or inbox items.
Spawn a code review (architect) subagent for deep analysis, planning, and debugging. The architect specializes in strategic guidance rather than implementation. Architect should be called after building major features. Relies on `delegation` skill.
Create and manage Replit's built-in PostgreSQL databases, check status, execute SQL queries with safety checks, and run read-only queries against the production database.
Delegate tasks to specialized subagents. Use subagent for synchronous task execution, startAsyncSubagent for background task execution, messageSubagent for async follow-ups, or messageSubagentAndGetResponse for sync follow-ups.
Configure and publish your project. Use to set deployment settings and suggest publishing when the app is ready.
| name | web-search |
| description | Search the web and fetch content from URLs. Use for real-time information, API documentation, and current events. |
Search the web and retrieve content from URLs for current information.
Use this skill when:
Search the web for current information.
Parameters:
query (str, required): Natural language search query phrased as a complete questionReturns: Dict with searchAnswer and resultPages (list of title/url dicts)
Example:
const results = await webSearch({ query: "OpenAI API rate limits 2026" });
console.log(results.searchAnswer);
for (const page of results.resultPages) {
console.log(`${page.title}: ${page.url}`);
}
Fetch and extract content from a URL as markdown.
Parameters:
url (str, required): Full HTTPS URL to fetchReturns: Dict with markdown key containing page content
Example:
const content = await webFetch({ url: "https://platform.openai.com/docs/guides/rate-limits" });
console.log(content.markdown.slice(0, 1000));
// Find information about a topic
const searchResults = await webSearch({ query: "FastAPI dependency injection tutorial 2026" });
// Get full content from the most relevant result
if (searchResults.resultPages.length > 0) {
const bestUrl = searchResults.resultPages[0].url;
const fullContent = await webFetch({ url: bestUrl });
console.log(fullContent.markdown);
}