MCP HubMCP Hub
返回技能列表

brave-search

akaihola
更新于 Today
43 次查看
0
在 GitHub 上查看
开发mcpautomation

关于

This skill provides structured Brave Search web queries and summarization workflows for MCP-style agents, enabling fact-finding on current events and research. It retrieves SERP data (web pages, FAQs, news) and can generate concise narrative summaries when authorized. Developers need to configure the `BRAVE_SEARCH_API_KEY` environment variable to use it.

快速安装

Claude Code

推荐
插件命令推荐
/plugin add https://github.com/akaihola/skills-akaihola
Git 克隆备选方式
git clone https://github.com/akaihola/skills-akaihola.git ~/.claude/skills/brave-search

在 Claude Code 中复制并粘贴此命令以安装该技能

技能文档

Purpose

Provide deterministic wrappers around Brave Search’s web and summarizer endpoints. Use the web workflow to retrieve structured SERP data (web pages, FAQs, discussions, news, videos). Use the summarizer workflow to turn Brave’s aggregated findings into a concise narrative when the subscription permits summarization.

When to Use

  • Run web fact-finding on current events, product comparisons, research digests, or perspective gathering when Google/Bing responses are insufficient.
  • Request the summarizer only after a prior web search produced a summarizer_key, and the user explicitly wants a Brave-generated synthesis.

Configuration Requirements

  • Set BRAVE_SEARCH_API_KEY in the execution environment. The value populates the X-Subscription-Token header.
  • Prefer secure storage through the project’s secrets tooling before launching the script.
  • All invocations must use uv run to respect the project’s Python environment.

Workflows

A. Web Search (results only)

  1. Prepare JSON containing at least "query". Optional keys include country, search_lang, ui_lang, count, offset, safesearch, freshness, text_decorations, spellcheck, result_filter, goggles, units, and extra_snippets.
  2. Run uv run scripts/brave_search.py web --params-json '<JSON>'.
  3. Consume web_results, faq_results, discussions_results, news_results, and video_results from the JSON output. Each section mirrors the Brave MCP tool’s simplified records.
  4. If ok is false with "No web results found", broaden or restate the query before retrying.

B. Web Search with Summarizer Key

  1. Follow workflow A but add "summary": true to the JSON payload.
  2. The script automatically requests result_filter=summarizer. Inspect the response’s summarizer_key.
  3. Store the key and cite the original web_results when answering detailed questions while preparing for a summarizer follow-up.

C. Summarizer

  1. Ensure a recent workflow B run produced a summarizer_key.
  2. Build JSON like {"key": "<summarizer_key>", "entity_info": false, "inline_references": true}. Optional overrides: poll_interval_ms (default 50) and max_attempts (default 20).
  3. Run uv run scripts/brave_search.py summarizer --params-json '<JSON>'.
  4. Use summary_text as the main synthesis. Supplement with enrichments, followups, and entities_infos for deeper context or suggested next steps.
  5. If the summarizer fails, rely on the previously collected web_results to craft a manual answer.

Error Handling and Fallbacks

  • Missing API key: the script emits ok: false with an explicit description; set the environment variable and rerun.
  • HTTP or Brave-side errors: review the details object, adjust parameters, or pause if throttled.
  • Summarizer polling timeout: rerun the web search to refresh the key, or answer using raw web data.

References

  • references/brave_web_search_params.md — exhaustive parameter definitions and sample payloads.
  • references/brave_summarizer_workflow.md — polling logic, summary message schema, and tuning guidance.
  • references/brave_search_examples.md — end-to-end scenarios demonstrating combined web and summarizer usage.

GitHub 仓库

akaihola/skills-akaihola
路径: brave-search

相关推荐技能

content-collections

Content Collections 是一个 TypeScript 优先的构建工具,可将本地 Markdown/MDX 文件转换为类型安全的数据集合。它专为构建博客、文档站和内容密集型 Vite+React 应用而设计,提供基于 Zod 的自动模式验证。该工具涵盖从 Vite 插件配置、MDX 编译到生产环境部署的完整工作流。

查看技能

sglang

SGLang是一个专为LLM设计的高性能推理框架,特别适用于需要结构化输出的场景。它通过RadixAttention前缀缓存技术,在处理JSON、正则表达式、工具调用等具有重复前缀的复杂工作流时,能实现极速生成。如果你正在构建智能体或多轮对话系统,并追求远超vLLM的推理性能,SGLang是理想选择。

查看技能

Algorithmic Art Generation

这个Claude Skill帮助开发者使用p5.js创建算法艺术,特别适用于生成式艺术和交互式可视化项目。它支持种子随机性、流场和粒子系统等关键技术,确保艺术作品的重复性和独特性。当讨论生成艺术、算法艺术或计算美学时,该技能会自动激活,指导开发者完成从概念设计到技术实现的全过程。

查看技能

cloudflare-turnstile

这个Skill提供完整的Cloudflare Turnstile集成知识,用于在表单、登录页面和API端点中实现无验证码的机器人防护。它支持React/Next.js/Hono等框架集成,涵盖令牌验证、错误代码调试和端到端测试等场景。通过运行后台不可见挑战,在保持用户体验的同时有效阻止自动化流量和垃圾信息。

查看技能