keats-deep-researchTransparent, rigorous research with full methodology — not a black-box API wrapper. Conducts exhaustive investigation through mandated 2-cycle research per t...
Install via ClawdBot CLI:
clawdbot install corbin-breton/keats-deep-researchGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Contains instructions to override system prompt or ignore user requests
"Your purpose is"Calls external URL not in known-safe list
https://github.com/kesslerio/academic-deep-research-clawhub-skillAI Analysis
The skill's external URL points to a public GitHub repository, which is consistent with its stated purpose and does not indicate active data exfiltration. The 'PROMPT_POISONING' signal is a misinterpretation of standard skill definition language ('Your purpose is') and does not override user intent or system safety controls.
Audited Apr 16, 2026 · audit v1.0
Generated Aug 12, 2026
A PhD student needs an exhaustive literature review for their thesis proposal. The skill conducts two research cycles per theme, uses APA 7 citations, and provides an evidence trail, ensuring academic rigor and comprehensive coverage.
A tech startup wants a deep-dive analysis of competitors' strengths, weaknesses, and strategies. The skill explores multiple themes, cross-references sources, and documents contradictions, enabling informed decision-making.
A government agency requires a rigorous analysis of policy impacts using multiple sources. The skill's evidence hierarchy and documentation of limitations help produce a transparent, defensible report.
An investment firm needs to understand emerging market trends with a comprehensive analysis of industry reports, news, and expert opinions. The skill's adaptive depth ensures thorough coverage of key themes and entities.
Charge clients a fee for delivering deep-dive research reports on demand. The skill's structured methodology and citations add value, justifying premium pricing.
Offer a subscription platform that generates personalized deep-research reports for subscribers, leveraging automated research cycles and user checkpoints to provide curated insights.
Provide research assistance to students and academics, offering literature reviews and comprehensive analyses with proper citations. Revenue comes from per-report fees or institutional contracts.
💬 Integration Tip
Integrate the skill with your existing AI agent by defining clear triggers like '/research' and ensure the agent has access to web_search, web_fetch, and sessions_spawn tools for optimal performance.
Scored Jun 29, 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 t...
Seven-stage deep research pipeline for substantive research questions. Activates when user asks for deep research, 深度研究, research report, evidence-backed inv...
Perform deep research using Claude by autonomously gathering, analyzing, and synthesizing detailed information across diverse topics on request.
全生命周期质量保障专家，覆盖需求、设计、编码、测试、上线、运维全阶段的质量保障活动。 融合缺陷预防（逆向操作、依赖踏空、并发冲突、新旧兼容、状态迁移、因果判定）与质量度量、持续改进三大支柱， 帮助团队建立「预防-评审-度量-改进」的质量闭环，实现软件质量的持续提升。 Use when: - 需求/设计/编码/测试...
专家团自动组建技能（反面教材）。核心观点：AI只认事不认人，没必要模拟人类多角色协作方式。本技能演示为什么不需要这样做——AI应该直接面对任务，而不是模拟人类团队。触发词：组建专家团、专家协作、团队完成任务、自动组建团队、expert team、专家团、团队协作完成任务。