Exa Web Toolkit
技能 已验证 活跃Web toolkit powered by Exa, tuned for scientific and technical content. Use this skill when the user needs to search the web or fetch/extract URL content. Covers: web search (semantic lookups, research, current info — with optional research-paper category and academic domain filtering) and URL extraction (fetching pages, articles, academic PDFs in batch). Use this skill for web-related tasks when the user wants high-quality search or scholarly filtering via category=research paper. Triggers on requests to search, look up, fetch a page, or extract an article.
To enable AI agents to perform high-quality web searches and extract content from URLs, with a focus on scientific and technical information.
功能
- Web search with semantic lookups
- URL content extraction (batch)
- Filtering for research papers and academic domains
- Configurable search types (auto, fast, deep)
- Output content to JSON file
使用场景
- Performing topic lookups, research, or finding current information.
- Fetching content from a specific URL, including articles and academic PDFs.
- Conducting research with a bias toward scholarly sources via category and domain filtering.
- Batch extracting content from multiple URLs in a single operation.
非目标
- General-purpose web browsing or navigation.
- Executing arbitrary code found on web pages.
- Replacing direct interaction with specific scientific databases (though it can search for information *about* them).
工作流
- User provides a query or URL and specifies desired capabilities (e.g., search, extract, academic focus).
- The skill determines the appropriate Exa API endpoint (search or extract) and constructs the command with relevant arguments.
- The `EXA_API_KEY` is read from the environment.
- The Exa SDK is invoked to perform the search or extraction.
- Results are processed and formatted into JSON.
- The structured results are returned to the user, optionally saved to a file.
先决条件
- exa-py Python SDK
- EXA_API_KEY environment variable
- Internet access
安装
npx skills add K-Dense-AI/claude-scientific-skills通过 npx 运行 Vercel skills CLI(skills.sh)— 需要本地安装 Node.js,以及至少一个兼容 skills 的智能体(Claude Code、Cursor、Codex 等)。前提是仓库遵循 agentskills.io 格式。
质量评分
已验证类似扩展
Exa Research Orchestrator
99Exa 赋能的深度研究。用于潜在客户开发、文献综述、深度分析、竞争对手分析，或任何单个搜索不足以满足需求的查询，包括诸如“研究这个”、“查找关于……的所有信息”、“找我所有的”或“深入研究……”之类的短语。
Cli Anything Exa
95Agent-native CLI for Exa web search and content retrieval workflows.
External Context
100Invoke parallel document-specialist agents for external web searches and documentation lookup
ARA Research Manager
100Records research provenance as a post-task epilogue, scanning conversation history at the end of a coding or research session to extract decisions, experiments, dead ends, claims, heuristics, and pivots, and writing them into the ara/ directory with user-vs-AI provenance tags. Use as a session epilogue — never during execution — to maintain a faithful, auditable trace of how a research project actually evolved.
Journey Mapping
100Build customer journey maps and service blueprints that visualize the end-to-end user experience including touchpoints, emotions, friction, and underlying systems. Use this skill whenever the user wants to map a customer journey, build a service blueprint, identify friction across an experience, align teams on the user experience, or visualize touchpoints and pain points. Triggers on customer journey, journey map, service blueprint, user journey, experience map, touchpoint analysis, friction map, journey audit, end-to-end experience, customer experience map. Also triggers when the team has departmental views of users but no shared map of what the experience actually feels like.
Manus
100Delegate complex, long-running tasks to Manus AI agent for autonomous execution. Use when user says 'use manus', 'delegate to manus', 'send to manus', 'have manus do', 'ask manus', 'check manus sessions', or when tasks require deep web research, market analysis, product comparisons, stock analysis, competitive research, document generation, data analysis, or multi-step workflows that benefit from autonomous agent execution with parallel processing.