deep-research-skill深度调研的多Agent编排工作流:把一个调研目标拆成可并行子目标,用 Claude Code 非交互模式(`claude -p`)运行子进程;联网与采集优先使用已安装的 skills,其次使用 MCP 工具;用脚本聚合子结果并分章精修,最终交付"成品报告文件路径 + 关键结论/建议摘要"。用于:系统性网页/资料调...
Install via ClawdBot CLI:
clawdbot install feiskyer/deep-research-skillGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://example.comAudited Apr 17, 2026 · audit v1.0
Generated Mar 22, 2026
Conducts comprehensive online investigations by breaking down research goals into parallel sub-tasks, such as analyzing multiple websites or datasets. Ideal for gathering detailed information from diverse sources efficiently.
Performs in-depth comparisons of competitors by distributing analysis of different companies or product features across sub-processes. Useful for identifying strengths, weaknesses, and market opportunities.
Handles large-scale retrieval and processing of links or data slices by splitting them into manageable chunks for parallel execution. Suitable for aggregating content from numerous sources quickly.
Supports the creation of detailed reports by researching and integrating evidence from multiple sub-tasks, ensuring thorough documentation and structured output. Helps in producing well-supported documents.
Analyzes industry trends by researching various dimensions like time slices or thematic clusters in parallel, delivering insights into evolving patterns and key developments.
Offers ongoing access to deep research workflows for clients needing regular insights, such as market updates or competitor tracking. Generates revenue through monthly or annual subscriptions.
Provides tailored research projects for specific client needs, like one-time reports or analysis, with pricing based on scope and complexity. Ideal for businesses requiring in-depth, ad-hoc investigations.
Licenses the skill as part of a software platform that automates research and report generation for users in sectors like finance or academia. Revenue comes from platform usage fees and enterprise licenses.
💬 Integration Tip
Ensure proper setup of MCP tools like firecrawl and exa for optimal web fetching, and configure sub-process permissions carefully to maintain security and efficiency.
Scored Apr 19, 2026
Multi-source deep research agent. Searches the web, synthesizes findings, and delivers cited reports. No API keys required.
Transparent, rigorous research with full methodology — not a black-box API wrapper. Conducts exhaustive investigation through mandated 2-cycle research per theme, APA 7th citations, evidence hierarchy, and 3 user checkpoints. Self-contained using native OpenClaw tools (web_search, web_fetch, sessions_spawn). Use for literature reviews, competitive intelligence, or any research requiring academic rigor and reproducibility.
Transparent, rigorous research with full methodology — not a black-box API wrapper. Conducts exhaustive investigation through mandated 2-cycle research per t...
Score startup idea through S.E.E.D. niche check + STREAM 6-layer analysis + Devil's Advocate inversion, auto-pick stack, and generate PRD with acceptance cri...
Apply Bayesian thinking to update beliefs systematically based on new evidence. Use when the user needs to assess probabilities, weigh competing hypotheses,...
生成完整产业图谱。支持深度调研(30+搜索)、自动发现一级分类、5-7层层级深度。 触发场景:用户请求生成产业图谱、产业链分析、行业分类图谱、产业结构梳理等。