意图信号（满足任一即可）：

1. 用户没有明确的研究问题，需要引导性思考
2. 用户要求在研究过程中被“引导”、“指导”或“辅导”
3. 用户对研究什么或从哪里开始表示不确定
4. 用户想要头脑风暴、探索或澄清一个研究方向
5. 用户描述了一个模糊的兴趣，但没有具体、可回答的问题

默认规则：当意图在 socratic 和 full 之间模糊不清时，优先选择 socratic——先进行引导比产生一份不需要的报告更安全。用户之后随时可以切换到 full 模式。

触发示例（示意性，非穷举）：“guide my research”, “help me think through”, 「引導我的研究」「幫我釐清」，或任何语言的等效表达

不触发的情况

快速模式选择指南

不确定？从 socratic 开始——它会帮你弄清楚你需要什么。 不確定？先用 socratic 模式——它會幫你釐清你需要什麼。

智能体团队（13 个智能体）

| 智能体 | 角色 | 阶段

---|---|---|---
1 | research_question_agent | 将模糊主题转化为精确的、经过 FINER 评分的研究问题，并界定范围边界 | 阶段 1，苏格拉底层 1
2 | research_architect_agent | 设计方法论蓝图：范式、方法、数据策略、分析框架、效度标准 | 阶段 1
3 | bibliography_agent | 系统性文献检索、来源筛选、APA 7.0 格式的注释参考文献 | 阶段 2
4 | source_verification_agent | 事实核查、来源分级（证据等级）、掠夺性期刊检测、利益冲突标记 | 阶段 2
5 | synthesis_agent | 跨来源整合、矛盾解决、主题综合、差距分析 | 阶段 3
6 | report_compiler_agent | 起草完整的 APA 7.0 报告（标题 -> 摘要 -> 引言 -> 方法 -> 发现 -> 讨论 -> 参考文献） | 阶段 4, 6
7 | editor_in_chief_agent | Q1 期刊编辑评审：原创性、严谨性、证据充分性、裁决（接受/修改/拒绝） | 阶段 5
8 | devils_advocate_agent | 挑战假设、检验逻辑谬误、寻找替代解释、确认偏倚检查 | 阶段 1, 3, 5，苏格拉底层 2, 4
9 | ethics_review_agent | AI 辅助研究伦理、归属完整性、双重用途筛查、公平表述 | 阶段 5
10 | socratic_mentor_agent | Q1 期刊主编角色；通过苏格拉底式提问引导研究思维，涵盖 5 个层次 | 苏格拉底模式（层 1-5）
11 | risk_of_bias_agent | 使用 RoB 2（RCTs）和 ROBINS-I（非随机）评估偏倚风险；交通灯可视化 | 系统综述（阶段 2）
12 | meta_analysis_agent | 设计并执行荟萃分析或叙述性综合；效应量、异质性、GRADE | 系统综述（阶段 3）
13 | monitoring_agent | 研究后文献监测：摘要、撤稿提醒、矛盾发现检测 | 可选（流程后）

模式选择指南

详细指南请参见 references/mode_selection_guide.md。

User Input
    |
    +-- Already have a clear research question?
    |   +-- Yes --> Need PRISMA-compliant systematic review / meta-analysis?
    |   |           +-- Yes --> systematic-review mode
    |   |           +-- No --> Need a full report?
    |   |                      +-- Yes --> full mode
    |   |                      +-- No --> Only need literature?
    |   |                                 +-- Yes --> lit-review mode
    |   |                                 +-- No --> quick mode
    |   +-- No --> Want to be guided through thinking?
    |              +-- Yes --> socratic mode
    |              +-- No --> full mode (Phase 1 will be interactive)
    |
    +-- Already have text to review? --> review mode
    +-- Only need fact-checking? --> fact-check mode

编排工作流程（6 个阶段）

User: "Research [topic]"
     |
=== Phase 1: SCOPING (Interactive) ===
     |
     |-> [research_question_agent] -> RQ Brief
     |   - FINER criteria scoring (Feasible, Interesting, Novel, Ethical, Relevant)
     |   - Scope boundaries (in-scope / out-of-scope)
     |   - 2-3 sub-questions
     |
     |-> [research_architect_agent] -> Methodology Blueprint
     |   - Research paradigm (positivist / interpretivist / pragmatist)
     |   - Method selection (qualitative / quantitative / mixed)
     |   - Data strategy (primary / secondary / both)
     |   - Analytical framework
     |   - Validity & reliability criteria
     |
     +-> [devils_advocate_agent] -- CHECKPOINT 1
         - RQ clarity and answerable?
         - Method appropriate for question?
         - Scope too broad or too narrow?
         - Verdict: PASS / REVISE (with specific feedback)
     |
     ** User confirmation before Phase 2 **
     |
=== Phase 2: INVESTIGATION ===
     |
     |-> [bibliography_agent] -> Source Corpus + Annotated Bibliography
     |   - Systematic search strategy (databases, keywords, Boolean)
     |   - Inclusion/exclusion criteria
     |   - PRISMA-style flow (if applicable)
     |   - Annotated bibliography (APA 7.0)
     |
     +-> [source_verification_agent] -> Verified & Graded Sources
         - Evidence hierarchy grading (Level I-VII)
         - Predatory journal screening
         - Conflict-of-interest flagging
         - Currency assessment (publication date relevance)
         - Source quality matrix
     |
=== Phase 3: ANALYSIS ===
     |
     |-> [synthesis_agent] -> Synthesis Narrative + Gap Analysis
     |   - Thematic synthesis across sources
     |   - Contradiction identification & resolution
     |   - Evidence convergence/divergence mapping
     |   - Knowledge gap analysis
     |   - Theoretical framework integration
     |
     +-> [devils_advocate_agent] -- CHECKPOINT 2
         - Cherry-picking check
         - Confirmation bias detection
         - Logic chain validation
         - Alternative explanations explored?
         - Verdict: PASS / REVISE
     |
=== Phase 4: COMPOSITION ===
     |
     +-> [report_compiler_agent] -> Full APA 7.0 Draft
         - Title Page
         - Abstract (150-250 words)
         - Introduction (context, problem, purpose, RQ)
         - Literature Review / Theoretical Framework
         - Methodology
         - Findings / Results
         - Discussion (interpretation, implications, limitations)
         - Conclusion & Recommendations
         - References (APA 7.0)
         - Appendices (if applicable)
     |
=== Phase 5: REVIEW (Parallel) ===
     |
     |-> [editor_in_chief_agent] -> Editorial Verdict + Line Feedback
     |   - Originality assessment
     |   - Methodological rigor
     |   - Evidence sufficiency
     |   - Argument coherence
     |   - Writing quality (clarity, conciseness, flow)
     |   - Verdict: ACCEPT / MINOR REVISION / MAJOR REVISION / REJECT
     |
     |-> [ethics_review_agent] -> Ethics Clearance
     |   - AI disclosure compliance
     |   - Attribution integrity
     |   - Dual-use screening
     |   - Fair representation check
     |   - Verdict: CLEARED / CONDITIONAL / BLOCKED
     |
     +-> [devils_advocate_agent] -- CHECKPOINT 3
         - Final vulnerability scan
         - Strongest counter-argument test
         - "So what?" significance check
         - Verdict: PASS / REVISE
     |
=== Phase 6: REVISION ===
     |
     +-> [report_compiler_agent] -> Final Report
         - Address editorial feedback
         - Resolve ethics conditions
         - Incorporate devil's advocate insights
         - Max 2 revision loops
         - Remaining issues -> "Acknowledged Limitations" section

检查点规则

1. Devil's Advocate 有 3 个强制检查点；严重问题会阻碍流程推进
2. 修订循环上限为 2 次迭代；剩余问题归入“已承认的局限性”部分
3. Ethics Review 可因严重伦理问题而暂停交付
4. 阶段 1 完成后需要用户确认才能继续

苏格拉底模式：引导式研究对话

核心原则：从 Q1 国际期刊主编的视角，通过苏格拉底式提问引导用户澄清研究问题。绝不直接给出答案；而是通过后续问题帮助用户自己思考问题。

详细智能体定义请参见 agents/socratic_mentor_agent.md。提问框架请参见 references/socratic_questioning_framework.md。

User: "Guide my research on [topic]"
     |
=== Layer 1: PROBLEM FRAMING (corresponds to first half of Phase 1) ===
     |
     +-> [socratic_mentor_agent] -> Follow-up on research motivation and problem definition
         [research_question_agent] -> Provide FINER guidance framework
         - "What is the question you truly want to answer?"
         - "Why does this question matter? To whom?"
         - "If your research succeeds, how would the world be different?"
         Extract [INSIGHT: ...] each round
         At least 2 rounds of dialogue before entering Layer 2
     |
=== Layer 2: METHODOLOGY REFLECTION (corresponds to second half of Phase 1) ===
     |
     +-> [socratic_mentor_agent] -> Follow-up on rationale for methodology choices
         [devils_advocate_agent] -> Challenge methodology assumptions at end of Layer 2
         - "How do you plan to answer this question? Why this approach?"
         - "Is there a completely different method that could also answer your question?"
         - "What is the biggest weakness of your method?"
         At least 2 rounds of dialogue before entering Layer 3
     |
=== Layer 3: EVIDENCE DESIGN (corresponds to Phase 2-3) ===
     |
     +-> [socratic_mentor_agent] -> Follow-up on evidence strategy
         - "What kind of evidence would convince you of your conclusion?"
         - "What evidence would make you change your conclusion?"
         - "What are you most worried about not finding?"
         At least 2 rounds of dialogue before entering Layer 4
     |
=== Layer 4: CRITICAL SELF-EXAMINATION (corresponds to Phase 5) ===
     |
     +-> [socratic_mentor_agent] -> Follow-up on limitations and risks
         [devils_advocate_agent] -> Challenge conclusion assumptions
         - "What does your research assume? What if those assumptions don't hold?"
         - "How would someone with the opposite view refute you?"
         - "What negative impact could your research have?"
         At least 2 rounds of dialogue before entering Layer 5
     |
=== Layer 5: SIGNIFICANCE & CONTRIBUTION (conclusion) ===
     |
     +-> [socratic_mentor_agent] -> Follow-up on "so what?"
         - "Why should readers care about your findings?"
         - "What aspects of our understanding of this issue does your research change?"
         At least 1 round of dialogue
     |
     +-> Compile all [INSIGHT]s into Research Plan Summary
         Can directly hand off to academic-paper (plan mode)

苏格拉底模式对话管理规则

• 每层至少进行 2 轮对话才能进入下一层（第 5 层至少需要 1 轮）
• 用户可以随时请求跳转到下一层
• 导师回复限制在 200-400 字
• 如果 10 轮后仍未收敛 -> 建议切换到 full 模式（参见失败路径 F6）
• 如果对话超过 15 轮 -> 自动编译 INSIGHT 并结束
• 如果用户要求直接答案 -> 委婉拒绝，解释引导式学习的价值

系统综述模式

完整的符合 PRISMA 标准的系统性文献综述，可选荟萃分析。此模式扩展了标准的 6 阶段流程，增加了用于偏倚风险评估（RoB 2、ROBINS-I）和定量综合的专用智能体。

详细智能体定义请参见 agents/risk_of_bias_agent.md 和 agents/meta_analysis_agent.md。Cochrane/PRISMA/GRADE 参考指南请参见 references/systematic_review_toolkit.md。

User: "Systematic review of [topic]" / "Meta-analysis of [topic]"
     |
=== Phase 1: SCOPING (Generates Protocol, not just RQ) ===
     |
     |-> [research_question_agent] -> PICOS-formatted RQ
     |   - Population, Intervention, Comparator, Outcome, Study design
     |   - Explicit eligibility criteria (inclusion/exclusion)
     |
     |-> [research_architect_agent] -> Systematic Review Protocol
     |   - Protocol follows PRISMA-P 2015 (templates/prisma_protocol_template.md)
     |   - Pre-specified subgroup analyses and sensitivity analyses
     |   - Risk of bias tool selection (RoB 2 / ROBINS-I)
     |   - Meta-analysis feasibility pre-assessment
     |
     +-> [devils_advocate_agent] -- CHECKPOINT 1
         - PICOS specificity check
         - Search strategy comprehensiveness
         - Protocol completeness
         - Verdict: PASS / REVISE
     |
     ** User confirmation of protocol before Phase 2 **
     |
=== Phase 2: INVESTIGATION (PRISMA-Compliant Search + RoB) ===
     |
     |-> [bibliography_agent] -> PRISMA Flow Diagram + Source Corpus
     |   - Search ≥ 2 databases with documented strategy
     |   - Dual-pass screening (title/abstract → full text)
     |   - PRISMA 2020 flow diagram with counts at each stage
     |   - Excluded studies with reasons documented
     |
     |-> [source_verification_agent] -> Verified Sources
     |   - Standard verification + predatory journal screening
     |
     +-> [risk_of_bias_agent] -> RoB Assessment
         - Per-study domain assessment with signaling questions
         - Traffic-light summary table across all studies
         - Distribution summary (% Low / Some Concerns / High)
     |
=== Phase 3: ANALYSIS (Meta-Analysis or Narrative Synthesis) ===
     |
     |-> [meta_analysis_agent] -> Quantitative or Narrative Synthesis
     |   - Feasibility assessment (pool or not?)
     |   - If feasible: effect size calculation, forest plot data,
     |     heterogeneity (I², Q, tau²), subgroup/sensitivity analyses
     |   - If not feasible: structured narrative synthesis (SWiM)
     |   - GRADE certainty of evidence for each outcome
     |
     |-> [synthesis_agent] -> Qualitative Themes + Gap Analysis
     |   - Thematic synthesis across studies
     |   - Integration with quantitative findings
     |
     +-> [devils_advocate_agent] -- CHECKPOINT 2
         - Cherry-picking check
         - Heterogeneity explanation adequacy
         - GRADE assessment validity
         - Verdict: PASS / REVISE
     |
=== Phase 4: COMPOSITION ===
     |
     +-> [report_compiler_agent] -> PRISMA 2020 Report
         - Uses templates/prisma_report_template.md
         - All 27 PRISMA items mapped to sections
         - Study characteristics table
         - Risk of bias summary table
         - Forest plot data (if meta-analysis)
         - GRADE Summary of Findings table
     |
=== Phase 5: REVIEW (Parallel) ===
     |
     |-> [editor_in_chief_agent] -> Editorial Verdict
     |-> [ethics_review_agent] -> Ethics Clearance
     +-> [devils_advocate_agent] -- CHECKPOINT 3
     |
=== Phase 6: REVISION ===
     |
     +-> [report_compiler_agent] -> Final PRISMA Report

系统综述检查点规则

1. 所有标准检查点规则均适用（见下方检查点规则）
2. 方案必须在阶段 2 前注册（或建议注册）
3. 所有研究的偏倚风险评估必须在阶段 3 前完成
4. 每个汇总结果都需要 GRADE 评估
5. PRISMA 清单合规性在阶段 5 验证

操作模式

失败路径

所有失败场景、触发条件和各模式的恢复策略请参见 references/failure_paths.md。

关键失败路径摘要：

文献监测（可选流程后）

任何研究模式完成后，用户可以选择激活 monitoring_agent 来设置研究后文献监测。这不是主流程的一部分——它是按需触发的辅助功能。

详细智能体定义请参见 agents/monitoring_agent.md。平台特定设置指南请参见 references/literature_monitoring_strategies.md。

触发：“monitor this topic”, “set up alerts”, “track new publications on this”

能力：

• 每周/每月监测摘要生成
• 已引用来源的撤稿提醒
• 矛盾发现检测
• 关键作者追踪
• 关键词演变追踪

输入：来自任何研究模式的已完成参考文献 + 搜索策略 输出：监测配置 + 摘要模板（markdown）

限制：监测智能体生成配置和模板供用户操作。它无法运行自主的后台监测。

交接协议：deep-research → academic-paper

研究完成后，以下材料可以交接给 academic-paper：

1. 研究问题简报（来自 research_question_agent）
2. 方法论蓝图（来自 research_architect_agent）
3. 注释参考文献（来自 bibliography_agent）
4. 综合报告（来自 synthesis_agent）
5. [如果是苏格拉底模式] INSIGHT 集合和研究计划摘要

触发：用户说“now help me write a paper”或“write a paper based on this”

academic-paper 的 intake_agent 将自动检测可用材料并跳过冗余步骤：

• 有 RQ 简报 -> 跳过主题范围界定
• 有参考文献 -> 跳过文献检索
• 有综合报告 -> 加速发现/讨论部分的撰写

详细交接示例请参见 examples/handoff_to_paper.md。

完整学术流程

完整工作流程请参见 academic-pipeline/SKILL.md。

智能体文件参考

参考文件

模板

示例

输出语言

遵循用户的语言。学术术语保持英文。苏格拉底模式使用自然的对话风格。

质量标准

1. 每个主张必须有引用——不支持无根据的断言
2. 证据等级——荟萃分析 > RCTs > 队列研究 > 病例报告 > 专家意见
3. 矛盾披露——如果来源有分歧，报告双方观点并比较证据质量
4. 局限性透明——每份报告必须有明确的局限性部分
5. AI 披露——所有报告都包含使用了 AI 辅助研究工具的声明
6. 可重复性——搜索策略、纳入标准和分析方法必须有文档记录以便复现
7. 苏格拉底完整性——在苏格拉底模式中，绝不直接给出答案；始终通过问题引导

跨智能体质量对齐

统一定义以防止各智能体间的不一致：

跨技能参考：阶段间数据交换格式请参见 shared/handoff_schemas.md。

与其他技能的集成

此技能是领域无关的，但可以与领域特定技能结合使用：

deep-research + tw-hei-intelligence     -> 基于证据的 HEI 政策研究
deep-research + report-to-website       -> 交互式研究报告
deep-research + podcast-script-generator -> 研究播客
deep-research + academic-paper          -> 完整的研究到发表流程
deep-research (socratic) + academic-paper (plan) -> 引导式研究 + 论文规划
deep-research (systematic-review) + academic-paper -> PRISMA 系统综述论文

版本历史

每周安装数

64

仓库

imbad0202/acade…h-skills

GitHub 星标数

1.2K

首次出现

Mar 10, 2026

安全审计

Gen Agent Trust HubPassSocketPassSnykWarn

安装于

opencode59

codex58

kimi-cli57

amp57

github-copilot57

gemini-cli57