菜单
Online web search and page-content extraction for current external information.
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
Use when bringing the harness method to a NEW or non-sentropic repo — maps the repo's conventions into a harness profile so the same scope/branch/verify kernel applies anywhere.
Use before any creative/design work (a feature, a package, an evolution) — explores intent and design via the spec-ladder with multi-peer adversarial review BEFORE implementation.
Use on any bug, test failure, or unexpected behaviour BEFORE proposing a fix — runs the generic evidence-first root-cause loop.
Use when you have a spec/decisions and need an executable plan — writes a lot-based BRANCH.md from the template and completes with track for realization state.
Use when completing a feature, a design step, or before merging — runs a ≥2-peer consensus review and reconciles the findings, instead of a single rubber-stamp pass.
Use when adding or evolving tests for a feature/bugfix — applies the sentropic test-pyramid, scoped-test loop, environment isolation, and AI-flaky policy.
| name | web |
| description | Online web search and page-content extraction for current external information. |
| version | 0.1.0 |
| category | web |
| contextFilter | {"requiresOnline":true} |
| tools | [{"name":"web_search","description":"Tavily Search API for real-time web search. Use this tool to search for current information on the web.","inputSchema":{"type":"object","properties":{"query":{"type":"string","description":"The search query to find relevant information."}},"required":["query"]}},{"name":"web_extract","description":"Extract and retrieve the full content of one or more existing web page URLs. Use this tool when the user asks for details about references or when you need to analyze specific URLs. Pass all URLs in one call using the urls array.","inputSchema":{"type":"object","properties":{"urls":{"type":"array","items":{"type":"string"},"description":"Array of URLs to extract content from. Must contain all URLs you need to extract in a single call."}},"required":["urls"]}}] |
Use web_search for current external information and web_extract for known
URLs already available in context.
For extraction, pass every URL needed for the task in one urls array. Never
call web_extract with an empty array.
