Web Research Skill
Skill ПровереноSearches multiple web sources, synthesizes findings, and produces cited research reports using delegated subagents. Use when the user asks to research a topic online, search the web, look something up, find current information, compare options, or produce a research report.
This skill automates the process of researching topics online by creating a research plan, delegating tasks to subagents for data collection, and then synthesizing the findings into a comprehensive report. It utilizes tools for file management, web searching, and task delegation, ensuring a structured and organized research workflow.
Documentation
- warning:Configuration & parameter referenceWhile the documentation outlines the process well, it does not explicitly list default values for any parameters or detail the precedence order of configuration files, assuming user familiarity with the underlying tools.
Versioning
- warning:Release ManagementThere is no explicit versioning information (e.g., `version` field in frontmatter, CHANGELOG, or releases) for this example skill, and installation likely relies on the main project's `main` branch.
Code Execution
- warning:ValidationWhile the skill defines a process, it relies on the underlying `deepagents` framework tools for validation. The skill's own instructions do not explicitly detail schema validation for inputs like topic names or file paths.
Practical Utility
- warning:Usage examplesThe SKILL.md describes the process and provides a template for subagent instructions but lacks concrete, end-to-end usage examples demonstrating the input, invocation, and observable outcome for a sample research task.
- warning:Edge casesWhile best practices are mentioned, the skill does not explicitly document failure modes (e.g., malformed input, rate limits) or recovery steps for individual research tasks or subagent failures.
Установка
npx skills add langchain-ai/deepagentsЗапускает Vercel skills CLI (skills.sh) через npx — нужны локальный Node.js и хотя бы один установленный совместимый со skills агент (Claude Code, Cursor, Codex, …). Предполагается, что репозиторий соответствует формату agentskills.io.
Похожие расширения
Fact-Check Skill
98Verify claims in generated output against sources. Use as a separate pass AFTER content generation to catch hallucinations. Critical constraint - cannot be reliably combined with generation in a single pass.
Web Search (Brave Search API)
98Search the web using Brave Search API for fast, privacy-respecting results with localization, freshness filtering, and extra snippets. Use when you need web search results with country/language targeting or time-based filtering. Requires BRAVE_API_KEY. Keywords: brave, web search, localized search, privacy search, freshness filtering.
Web Search (Tavily API)
97Search the web using Tavily API for high-quality, AI-optimized results with advanced filtering options. Use when you need structured search results, domain filtering, relevance scores, or AI-generated answer summaries. Requires TAVILY_API_KEY. Keywords: tavily, advanced search, filtered search, domain filtering, relevance scoring.
Media Meta-Analysis
95Synthesize multiple media analyses into cross-source patterns and insights. Use when you need to cross-reference analyses, find patterns across sources, or perform meta-analysis of media content.
Deep Research
95Conduct comprehensive research on any topic. Synthesize information from multiple angles, provide structured analysis, and generate detailed research reports.
Deep Agents Orchestration
95INVOKE THIS SKILL when using subagents, task planning, or human approval in Deep Agents. Covers SubAgentMiddleware, TodoList for planning, and HITL interrupts.