据 AlphaMoat 统计,截至 2026-09,Gemini Web Search 累计下载 4,185 次、获 5 个星标,在全部 5,078 个 AI 技能中排名第 2,397 位,在「知识管理」分类(442 个)中排名第 225 位。
| 平台 | 累计安装 | 累计下载 | 星标 | 评论 |
|---|---|---|---|---|
| ClawHub ↗ | 138 | 4,093 | 5 | 3 |
| SkillHub ↗ | 258 | 4,185 | 5 | — |
各平台的计数口径不同,统计时间不一致。
必须在 TTY 中运行 Gemini CLI,并设置较长超时;命令入口为 ~/.npm-global/bin/gemini -p。构造查询时包含实体、代码/名称、时间范围和所需信息。结果要提供关键数字事实、催化剂要点和来源链接,并优先使用公司 IR/SEC 文件及可靠媒体;至少用 2 个独立可靠来源交叉验证。来源冲突或说法可疑时要指出并向用户核实,或用更严格提示重跑。
资料发布于 2026-10-27
以下是根据技能文档生成的示例,不代表实际运行结果。
2026-09 起统计方法调整:同名技能按作者分别统计,并覆盖全部技能。图中虚线为调整前的月份,与之后的数据不直接比较,也不计算跨越调整的增长。
| 月份 | 累计下载 | 环比 | 星标 |
|---|---|---|---|
| 2026-09 | 4,185 | — | 5 |
| 2026-08 | 4,003 | +2.5% | 5 |
| 2026-07 | 3,905 | +6.3% | 5 |
| 2026-06 | 3,673 | +4.1% | 5 |
| 2026-05 | 3,529 | — | 5 |
| 2026-03 | 2,897 | — | 5 |
以下是作者发布的原始文件,按纯文本显示,本站未做修改或审核;其中的链接不可点击,命令请核实后再运行。抓取于 2026-10-23。
--- name: gemini-web-search description: Use Gemini CLI (@google/gemini-cli) to do web search / fact-finding and return a sourced summary. Use when the user asks “why did X happen today”, “what’s the latest news”, “search the web”, “find sources/links”, or any task requiring up-to-date info. Prefer this over other search tools when Gemini is available but slow; run it with a TTY, wait longer, and verify source quality. --- # Gemini Web Search Use Gemini CLI to search the web and produce a concise, sourced answer. ## Quick workflow
1) **Formulate a tight query** - Include: entity + ticker/name + date/time window + what you need (%, $, cause, quotes, links) - Example: `PayPal (PYPL) fell Feb 4 2026: % change, $ change, main catalyst(s), 3 sources` 2) **Run Gemini CLI with a TTY and long timeout** Gemini CLI can hang or be slow without a pseudo-TTY. Preferred (OpenClaw tool call): - Use `functions.exec` with `pty: true` - Use `timeout` 300–600s (longer for heavy searches) - Use `yieldMs` ~10000 then `process.poll` until completion Command template: - `~/.npm-global/bin/gemini -p "<prompt>"` If `pty:true` still behaves poorly, use a pseudo-tty wrapper: - `script -q -c "~/.npm-global/bin/gemini -p \"<prompt>\"" /dev/null` 3) **Extract the answer in a structured way** Return: - The key numeric facts (e.g., % move, $ move, close/intraday) - 2–4 bullets of the main catalyst(s) - **Links** (always) 4) **Quality control (mandatory)** - Prefer: company IR/SEC filing, Reuters, Bloomberg, WSJ/FT, CNBC, reputable outlets. - Avoid relying on low-quality finance blogs/SEO sites. - If sources conflict or look unreliable: say so and ask user for a screenshot/link, or re-run with a stricter prompt. ## Prompts that work well - **Fast triage**: `Search the web: <topic>. Give 3 bullets + 2 reputable links.` - **Market move**: `Search the web: Why did <TICKER> move today (<date>)? Provide exact % and $ move (close + intraday if available) and the main catalyst(s). Cite sources with links.` - **Force better sources**: `Search the web and prioritize Reuters/company IR/SEC filing. If you cannot find them, say so. Topic: <...>. Provide links.` ## Failure modes & fixes - **Gemini prints “I will search…” then stalls** - Wait longer (it can be slow). - Ensure TTY: run with `pty:true` or `script -q -c ... /dev/null`. - **Output has suspicious claims (e.g., odd CEO news)** - Re-run with: “use Reuters/company IR/SEC filing only; otherwise say unknown”. - Cross-check with at least 2 independent reputable sources. - **Need numbers but sources don’t show them** - Ask user for the quote/screenshot from their market data app and reconcile. ## Local setup notes - Gemini CLI binary: `~/.npm-global/bin/gemini` - Auth: already completed by Jiajie (should work without re-login)
把长文本、文档与网页内容压缩成要点和关键词的摘要工具。
通过 IMA OpenAPI 管理笔记与知识库内容。
规定如何为网页请求选择合适工具的必读指引。
调用百度 AI 搜索接口做网页检索的技能。
用 uvx 直接调用 markitdown,把各类文件转成 Markdown。
面向 OpenClaw 的默认网页搜索,实时检索多个引擎。
用 DuckDuckGo 接口做网页、新闻、图片与视频检索的技能。
检索并发现可用 OpenClaw 技能的技能。
数据月份:2026-09 · 下载/星标/安装数聚合自公开技能注册库(ClawHub、SkillHub),按月更新。口径说明见数据方法。