deep-researchDeep research skill — broad parallel web searches, multi-source validation, confidence tracking, cited Markdown report. Supports 11 research types: market (TAM/SAM, segments, pricing, trends), domain (industry structure, ecosystem, regulatory landscape), technical (architecture, tools, benchmarks), competitive (competitor teardown, positioning, win/loss), product (feature analysis, reviews, roadmap signals), academic (literature survey, citation networks, key authors), person/org (due diligence on a company or public figure), financial (funding rounds, valuation multiples, revenue signals), legal (IP, patents, litigation, compliance), trend (emerging signals, foresight, scenario mapping), community (ecosystem health, key voices, governance, fragmentation). Use when asked to: 'research <topic>', 'deep dive on X', 'analyze the landscape', 'competitive analysis', 'compare these options', 'who are the players in Z', 'literature review', 'background on Y', 'what papers exist on X', 'product teardown', 'technology evaluation', 'regulatory overview', 'funding landscape', 'what trends are emerging in X', 'patent landscape', 'community health', or any request requiring scanning many sources and producing a cited written analysis. Apply whenever the deliverable is a thorough, sourced report rather than a quick answer. Trigger even when phrased casually: 'look into X', 'what's the deal with Y', 'dig into Z', 'I need to understand the space', 'catch me up on X'.
Install via ClawdBot CLI:
clawdbot install 9438190/deep-researchGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://cdn.tailwindcss.comAudited Aug 20, 2026 · audit v1.0
Generated Oct 25, 2026
An internal strategy team uses the seven-stage pipeline to turn a vague executive question such as 'Should we enter the Southeast Asia EV charging market?' into a structured 6,000-10,000 word report with confirmed outline, evidence-backed findings, and comparison tables. The output is rendered as HTML for board circulation.
A policy researcher investigates new AI regulation frameworks by running the pipeline across official documents, industry statistics, and academic sources, ensuring 80% coverage of standard policy categories. The final report includes critical perspectives, implementation conditions, and a clear decision recommendation.
An analyst evaluates three competing battery-recycling startups, using the entity-based outline mode with per-company dimension breakdowns and a summary comparison table. Quantitative questions like market share and funding are answered with estimated ranges and cited sources.
A graduate student requests a deep research report on transformer efficiency techniques, triggering academic source priorities (arXiv, IEEE, CNKI) and methodology-focused synthesis. The pipeline yields a sourced long-form review with cross-source patterns and research gaps identified.
A product manager asks for a comprehensive overview of the AI code assistant market; the pipeline uses synthesis-type outlines with trend judgments supported by 2-3 typical cases each. The resulting markdown report feeds into roadmap planning and is optionally rendered to HTML for stakeholder review.
Offer a monthly subscription where clients submit research questions and receive deep-research reports produced by the agent pipeline with expert oversight. Positions the seven-stage methodology as a premium, auditable alternative to ad-hoc AI search.
License the skill package as an internal copilot that consultants use during engagements, with customized templates, domain category lists, and brand-styled HTML output. Reduces junior analyst hours while maintaining outline-confirmation checkpoints.
Expose the pipeline through an API or consumer marketplace where anyone can commission a sourced long-form report on demand, with add-ons for HTML rendering and expedited delivery. Monetizes the standardized stage gating and citation guarantees.
💬 Integration Tip
Wire the ask_user outline-confirmation and options-question steps to your chat or approval UI so users can skip defaults, and enforce the ≤5 task and 400-600 word per-task output limits to keep token usage predictable.
Scored Aug 20, 2026
Use this skill when users need to search academic papers, download research documents, extract citations, or gather scholarly information. Triggers include: requests to "find papers on", "search research about", "download academic articles", "get citations for", or any request involving academic databases like arXiv, PubMed, Semantic Scholar, or Google Scholar. Also use for literature reviews, bibliography generation, and research discovery. Requires OpenClawCLI installation from clawhub.ai.
Get institutional-grade CEO performance analytics for S&P 500 companies. Proprietary scores: CEORaterScore (composite), AlphaScore (market outperformance), R...
Creates formal academic research papers following IEEE/ACM formatting standards with proper structure, citations, and scholarly writing style. Use when the user asks to write a research paper, academic paper, or conference paper on any topic.
Search, download, and summarize academic papers from arXiv. Built for AI/ML researchers.
Suggest optimal academic venues for paper submission based on paper content, novelty level, and author's goals. Activated when Chopin asks 'which journal sho...
Baidu Scholar Search - Search Chinese and English academic literature (journals, conferences, papers, etc.)