web-research
The web-research skill provides a structured methodology for conducting comprehensive web research by breaking complex topics into subtopics, systematically gathering information through targeted searches, and synthesizing findings with proper citations. Use this skill when researching complex topics requiring multiple sources, comparing subjects across different dimensions, or producing well-sourced reports that need clear documentation of information origins.
git clone --depth 1 https://github.com/DougTrajano/pydantic-ai-skills /tmp/web-research && cp -r /tmp/web-research/examples/skills/web-research ~/.claude/skills/web-researchSKILL.md
# Web Research Skill This skill provides guidance on conducting comprehensive web research. It emphasizes planning, efficient information gathering, and systematic synthesis of findings. **Note:** This skill provides a methodology and best practices for web research. It does not include executable scripts or tools beyond what's available in your agent's toolset. ## When to Use This Skill Use this skill when you need to: - Research complex topics requiring multiple information sources - Gather and synthesize current information from the web - Conduct comparative analysis across multiple subjects - Produce well-sourced research reports with clear citations ## Research Process ### Step 1: Create and Save Research Plan Before conducting research: 1. **Analyze the research question** - Break it down into distinct, non-overlapping subtopics 2. **Create a research plan** - Determine: - The main research question - 2-5 specific subtopics to investigate - Expected information from each subtopic - How results will be synthesized **Planning Guidelines:** - **Simple fact-finding**: 1-2 subtopics - **Comparative analysis**: 1 subtopic per comparison element (max 3) - **Complex investigations**: 3-5 subtopics ### Step 2: Gather Information For each subtopic in your plan: 1. **Use available web search tools** to gather information with: - Clear, specific search queries - Target: 3-5 searches per subtopic maximum 2. **Organize findings** as you gather them ### Step 3: Synthesize Findings After gathering information: 1. **Review all collected information** from your searches 2. **Synthesize the information** - Create a comprehensive response that: - Directly answers the original question - Integrates insights from all subtopics - Cites specific sources with URLs - Identifies any gaps or limitations ## Best Practices - **Plan before searching** - Understand what you need to find and organize your approach - **Clear subtopics** - Ensure each search has a distinct, non-overlapping scope - **Systematic synthesis** - Review all findings before creating final response - **Stop appropriately** - Don't over-research; 3-5 searches per subtopic is usually sufficient - **Cite sources** - Always include URLs to sources in your final response
Search arXiv preprint repository for papers in physics, mathematics, computer science, quantitative biology, and related fields.
Use this skill whenever the user is working with the Pydantic AI framework — including building AI agents, defining structured outputs with Pydantic models, wiring up tools/function calling, configuring model providers (OpenAI, Anthropic, Gemini, etc.), managing dependencies via agent context, handling streaming responses, or debugging agent runs. Trigger this skill even for adjacent tasks like "how do I make my agent return JSON", "set up a multi-step agent", "add a tool to my agent", or "validate LLM output with Pydantic" — any time Pydantic AI is mentioned or implied as the target framework.