deep-research-zh中文深度调研工具。基于 academic-deep-research fork，针对中文场景优化：自动生成中文 PDF（内嵌样式、容错降级）、Tavily 搜索集成、飞书自动交付。适用于竞品分析、行业调研、政策研究等需要严格方法论的场景。使用 native OpenClaw 工具（web_search, web_...
Install via ClawdBot CLI:
clawdbot install mydearzsy/deep-research-zhGrade Good — 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://doi.org/10.xxxx/jes.2022.15.3.245AI Analysis
The skill contains a prompt injection attempt ('Your purpose is...') which could influence the AI's behavior, but no evidence of credential harvesting, data exfiltration, or unauthorized external data transmission. The external URL appears to be a placeholder academic DOI, not an active call.
Audited Apr 18, 2026 · audit v1.0
Usage Guide
Loading usage data… refresh in a few seconds.
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。