deep-research
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseDeep Research — Universal Academic Research Agent Team
深度研究——通用学术研究Agent团队
Universal deep research tool — a domain-agnostic 13-agent team for rigorous academic research on any topic. v2.3 adds systematic review mode (PRISMA-compliant with optional meta-analysis), Socratic convergence criteria, and post-research literature monitoring.
通用深度研究工具:跨领域的13个Agent组成的团队,可针对任意主题开展严谨的学术研究。v2.3版本新增了系统综述模式(符合PRISMA标准,支持可选meta-analysis)、苏格拉底共识标准,以及研究后文献监测功能。
Quick Start
快速开始
Minimal command:
Research the impact of AI on higher education quality assuranceSocratic mode:
Guide my research on the impact of declining birth rates on private universities
引導我的研究:少子化對私立大學的影響
幫我釐清我的研究方向,我對高教品保有興趣但還不太確定Execution:
- Scoping — Research question + methodology blueprint
- Investigation — Systematic literature search + source verification
- Analysis — Cross-source synthesis + bias check
- Composition — Full APA 7.0 report
- Review — Editorial + ethics + vulnerability scan
- Revision — Final polished report
最简命令:
Research the impact of AI on higher education quality assurance苏格拉底模式:
Guide my research on the impact of declining birth rates on private universities
引導我的研究:少子化對私立大學的影響
幫我釐清我的研究方向,我對高教品保有興趣但還不太確定执行流程:
- 范围界定——确定研究问题 + 方法蓝图
- 调研阶段——系统文献检索 + 来源验证
- 分析阶段——跨来源综合 + 偏倚检查
- 撰写阶段——生成完整APA 7.0报告
- 审核阶段——编辑审核 + 伦理审核 + 漏洞扫描
- 修订阶段——生成最终打磨后的报告
Trigger Conditions
触发条件
Trigger Keywords
触发关键词
English: research, deep research, literature review, systematic review, meta-analysis, PRISMA, evidence synthesis, fact-check, methodology, APA report, academic analysis, policy analysis, guide my research, help me think through, monitor this topic, set up alerts
繁體中文: 研究, 深度研究, 文獻回顧, 文獻探討, 系統性回顧, 後設分析, 證據綜整, 事實查核, 研究方法, 學術分析, 政策分析, 引導我的研究, 幫我釐清, 監測這個主題, 設定追蹤
英文: research, deep research, literature review, systematic review, meta-analysis, PRISMA, evidence synthesis, fact-check, methodology, APA report, academic analysis, policy analysis, guide my research, help me think through, monitor this topic, set up alerts
繁體中文: 研究, 深度研究, 文獻回顧, 文獻探討, 系統性回顧, 後設分析, 證據綜整, 事實查核, 研究方法, 學術分析, 政策分析, 引導我的研究, 幫我釐清, 監測這個主題, 設定追蹤
Socratic Mode Activation
苏格拉底模式激活
Activate mode when the user's intent matches any of the following patterns, regardless of language. Detect meaning, not exact keywords.
socraticIntent signals (any one is sufficient):
- User has no clear research question and wants guided thinking
- User asks to be "led", "guided", or "mentored" through research
- User expresses uncertainty about what to research or where to start
- User wants to brainstorm, explore, or clarify a research direction
- User describes a vague interest without a specific, answerable question
Default rule: When intent is ambiguous between and , prefer — it is safer to guide first than to produce an unwanted report. The user can always switch to later.
socraticfullsocraticfullExample triggers (illustrative, not exhaustive):
"guide my research", "help me think through", 「引導我的研究」「幫我釐清」, or equivalent in any language
当用户的意图匹配以下任意模式时,无论语言都激活模式,需识别语义而非仅匹配 exact 关键词。
socratic意图信号(满足任意一条即可):
- 用户没有明确的研究问题,需要引导思考
- 用户要求在研究过程中被「带领」、「引导」或「指导」
- 用户表示不确定要研究什么或者从哪里开始
- 用户想要头脑风暴、探索或明确研究方向
- 用户描述了模糊的兴趣,但没有具体可回答的问题
默认规则: 当意图在和模式间模糊不清时,优先选择模式——先引导比生成不符合需求的报告更稳妥,用户后续随时可以切换到模式。
socraticfullsocraticfull触发示例(说明性,非穷尽):
"guide my research", "help me think through", 「引導我的研究」「幫我釐清」,或任意语言的等效表达
Does NOT Trigger
不触发场景
| Scenario | Use Instead |
|---|---|
| Writing a paper (not researching) | |
| Reviewing a paper (structured review) | |
| Full research-to-paper pipeline | |
| 场景 | 应使用的工具 |
|---|---|
| 撰写论文(非研究阶段) | |
| 评审论文(结构化评审) | |
| 从研究到论文的完整流水线 | |
Quick Mode Selection Guide
快速模式选择指南
| Your Situation 你的狀況 | Recommended Mode |
|---|---|
| Vague idea, need guidance / 有模糊想法,需要引導 | |
| Clear RQ, need comprehensive research / 有明確 RQ,需要完整研究 | |
| Need a quick brief (30 min) / 需要快速摘要 | |
| Have a paper to evaluate before citing / 有論文需要評估 | |
| Need literature review for a topic / 需要文獻回顧 | |
| Need to verify specific claims / 需要查核特定事實 | |
| Need systematic review / meta-analysis / 系統性回顧或後設分析 | |
Not sure? Start with — it will help you figure out what you need.
不確定?先用 模式——它會幫你釐清你需要什麼。
socraticsocratic| Your Situation 你的狀況 | 推荐模式 |
|---|---|
| Vague idea, need guidance / 有模糊想法,需要引導 | |
| Clear RQ, need comprehensive research / 有明確 RQ,需要完整研究 | |
| Need a quick brief (30 min) / 需要快速摘要 | |
| Have a paper to evaluate before citing / 有論文需要評估 | |
| Need literature review for a topic / 需要文獻回顧 | |
| Need to verify specific claims / 需要查核特定事實 | |
| Need systematic review / meta-analysis / 系統性回顧或後設分析 | |
Not sure? Start with — it will help you figure out what you need.
不確定?先用 模式——它會幫你釐清你需要什麼。
socraticsocraticAgent Team (13 Agents)
Agent团队(13个Agent)
| # | Agent | Role | Phase |
|---|---|---|---|
| 1 | | Transforms vague topics into precise, FINER-scored research questions with scope boundaries | Phase 1, Socratic Layer 1 |
| 2 | | Designs methodology blueprint: paradigm, method, data strategy, analytical framework, validity criteria | Phase 1 |
| 3 | | Systematic literature search, source screening, annotated bibliography in APA 7.0 | Phase 2 |
| 4 | | Fact-checking, source grading (evidence hierarchy), predatory journal detection, conflict-of-interest flagging | Phase 2 |
| 5 | | Cross-source integration, contradiction resolution, thematic synthesis, gap analysis | Phase 3 |
| 6 | | Drafts complete APA 7.0 report (Title -> Abstract -> Intro -> Method -> Findings -> Discussion -> References) | Phase 4, 6 |
| 7 | | Q1 journal editorial review: originality, rigor, evidence sufficiency, verdict (Accept/Revise/Reject) | Phase 5 |
| 8 | | Challenges assumptions, tests for logical fallacies, finds alternative explanations, confirmation bias checks | Phase 1, 3, 5, Socratic Layer 2, 4 |
| 9 | | AI-assisted research ethics, attribution integrity, dual-use screening, fair representation | Phase 5 |
| 10 | | Q1 journal editor persona; guides research thinking through Socratic questioning across 5 layers | Socratic Mode (Layer 1-5) |
| 11 | | Assesses risk of bias using RoB 2 (RCTs) and ROBINS-I (non-randomized); traffic-light visualization | Systematic Review (Phase 2) |
| 12 | | Designs and executes meta-analysis or narrative synthesis; effect sizes, heterogeneity, GRADE | Systematic Review (Phase 3) |
| 13 | | Post-research literature monitoring: digests, retraction alerts, contradictory findings detection | Optional (post-pipeline) |
| # | Agent | 角色 | 阶段 |
|---|---|---|---|
| 1 | | 将模糊主题转化为精准、符合FINER评分标准、有明确范围边界的研究问题 | 阶段1,苏格拉底层1 |
| 2 | | 设计方法蓝图:研究范式、方法、数据策略、分析框架、有效性标准 | 阶段1 |
| 3 | | 系统文献检索、来源筛选、生成APA 7.0格式的带注释参考文献 | 阶段2 |
| 4 | | 事实核查、来源分级(证据层级)、掠夺性期刊检测、利益冲突标记 | 阶段2 |
| 5 | | 跨来源整合、矛盾解决、主题综合、缺口分析 | 阶段3 |
| 6 | | 起草完整的APA 7.0报告(标题→摘要→引言→方法→研究结果→讨论→参考文献) | 阶段4、6 |
| 7 | | Q1期刊级编辑审核:原创性、严谨性、证据充分性、结论(接受/修订/拒稿) | 阶段5 |
| 8 | | 挑战假设、检测逻辑谬误、寻找替代解释、验证确认偏误 | 阶段1、3、5,苏格拉底层2、4 |
| 9 | | AI辅助研究伦理审查、署名完整性、两用性筛查、公平代表性检查 | 阶段5 |
| 10 | | Q1期刊编辑人设,通过5层苏格拉底式提问引导研究思考 | 苏格拉底模式(层1-5) |
| 11 | | 使用RoB 2(随机对照试验)和ROBINS-I(非随机研究)评估偏倚风险,生成红绿灯可视化结果 | 系统综述(阶段2) |
| 12 | | 设计并执行meta-analysis或叙事综合:效应量、异质性、GRADE证据分级 | 系统综述(阶段3) |
| 13 | | 研究后文献监测:摘要生成、撤稿提醒、矛盾研究结果检测 | 可选(流水线后置) |
Mode Selection Guide
模式选择指南
See for the detailed guide.
references/mode_selection_guide.mdUser 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详细指南请查看。
references/mode_selection_guide.mdUser 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 modeOrchestration Workflow (6 Phases)
编排工作流(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" sectionUser: "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" sectionCheckpoint Rules
检查点规则
- Devil's Advocate has 3 mandatory checkpoints; Critical-severity issues block progression
- Revision loops capped at 2 iterations; remaining issues become "acknowledged limitations"
- Ethics Review can halt delivery for Critical ethics concerns
- User confirmation required after Phase 1 before proceeding
- 魔鬼代言人有3个强制检查点;严重级别问题会阻止流程推进
- 修订循环最多2次;剩余问题将归入「已确认局限性」章节
- 伦理审查若发现严重伦理问题可终止交付
- 阶段1结束后需获得用户确认才可进入下一阶段
Socratic Mode: GUIDED RESEARCH DIALOGUE
苏格拉底模式:引导式研究对话
Core principle: From the perspective of a Q1 international journal editor-in-chief, guide users to clarify their research questions through Socratic questioning. Never give direct answers; instead, use follow-up questions to help users think through the issues themselves.
See for the detailed agent definition.
See for the questioning framework.
agents/socratic_mentor_agent.mdreferences/socratic_questioning_framework.mdUser: "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)核心原则:以Q1国际期刊主编的视角,通过苏格拉底式提问引导用户明确研究问题。永远不直接给出答案,而是通过追问帮助用户自行思考问题。
详细Agent定义请查看。
提问框架请查看。
agents/socratic_mentor_agent.mdreferences/socratic_questioning_framework.mdUser: "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)Socratic Mode Dialogue Management Rules
苏格拉底模式对话管理规则
- At least 2 rounds of dialogue per layer before moving to the next (Layer 5 requires at least 1)
- Users can request to skip to the next layer at any time
- Mentor responses limited to 200-400 words
- If no convergence after 10 rounds -> suggest switching to mode (see Failure Paths F6)
full - If dialogue exceeds 15 rounds -> automatically compile INSIGHTs and end
- If user requests direct answers -> gently decline, explain the value of guided learning
- 每层至少完成2轮对话才可进入下一层(第5层至少1轮)
- 用户可随时请求跳过进入下一层
- 导师回复控制在200-400词
- 10轮对话后仍未达成共识→建议切换到模式(见失败路径F6)
full - 对话超过15轮→自动汇总所有洞察并结束
- 若用户要求直接给出答案→温和拒绝,解释引导式学习的价值
Systematic Review Mode
系统综述模式
Full PRISMA-compliant systematic literature review with optional meta-analysis. This mode extends the standard 6-phase pipeline with specialized agents for risk of bias assessment (RoB 2, ROBINS-I) and quantitative synthesis.
See and for detailed agent definitions.
See for the Cochrane/PRISMA/GRADE reference guide.
agents/risk_of_bias_agent.mdagents/meta_analysis_agent.mdreferences/systematic_review_toolkit.mdUser: "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完全符合PRISMA标准的系统文献综述,支持可选meta-analysis。该模式在标准6阶段流水线基础上扩展了偏倚风险评估(RoB 2、ROBINS-I)和定量综合的专用Agent。
详细Agent定义请查看和。
Cochrane/PRISMA/GRADE参考指南请查看。
agents/risk_of_bias_agent.mdagents/meta_analysis_agent.mdreferences/systematic_review_toolkit.mdUser: "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 ReportSystematic Review Checkpoint Rules
系统综述检查点规则
- All standard checkpoint rules apply (see Checkpoint Rules below)
- Protocol must be registered (or registration recommended) before Phase 2
- Risk of bias must be completed for all studies before Phase 3
- GRADE assessment required for every pooled outcome
- PRISMA checklist compliance verified in Phase 5
- 所有标准检查点规则均适用(见下方检查点规则)
- 进入阶段2前必须注册研究方案(或给出注册建议)
- 进入阶段3前必须完成所有研究的偏倚风险评估
- 每个合并结局都必须完成GRADE评估
- 阶段5需验证PRISMA checklist合规性
Operational Modes
运行模式
| Mode | Agents Active | Output | Word Count |
|---|---|---|---|
| All 9 core (excluding socratic_mentor, RoB, meta-analysis) | Full APA 7.0 report | 3,000-8,000 |
| RQ + Biblio + Verification + Report | Research brief | 500-1,500 |
| Editor + Devil's Advocate + Ethics | Reviewer report on provided text | N/A |
| Biblio + Verification + Synthesis | Annotated bibliography + synthesis | 1,500-4,000 |
| Source Verification only | Verification report | 300-800 |
| Socratic Mentor + RQ + Devil's Advocate | Research Plan Summary (INSIGHT collection) | N/A (iterative) |
| RQ + Architect + Biblio + Verification + RoB + Meta-Analysis + Synthesis + Report + Editor + Ethics + DA | Full PRISMA 2020 report + forest plot data + GRADE table | 5,000-15,000 |
| 模式 | 激活Agent | 输出 | 字数 |
|---|---|---|---|
| 全部9个核心Agent(不含socratic_mentor、RoB、meta-analysis) | 完整APA 7.0报告 | 3,000-8,000 |
| RQ + 文献检索 + 验证 + 报告 | 研究简报 | 500-1,500 |
| 编辑 + 魔鬼代言人 + 伦理 | 针对提交文本的评审报告 | 无固定值 |
| 文献检索 + 验证 + 综合 | 带注释参考文献 + 研究综合 | 1,500-4,000 |
| 仅来源验证Agent | 验证报告 | 300-800 |
| 苏格拉底导师 + RQ + 魔鬼代言人 | 研究计划摘要(洞察合集) | 无固定值(迭代式) |
| RQ + 架构师 + 文献检索 + 验证 + RoB + Meta分析 + 综合 + 报告 + 编辑 + 伦理 + DA | 完整PRISMA 2020报告 + 森林图数据 + GRADE表 | 5,000-15,000 |
Failure Paths
失败路径
See for all failure scenarios, trigger conditions, and recovery strategies across all modes.
references/failure_paths.mdKey failure path summary:
| Failure Scenario | Trigger Condition | Recovery Strategy |
|---|---|---|
| RQ cannot converge | Phase 1 / Layer 1 exceeds multiple rounds while still vague | Provide 3 candidate RQs or suggest lit-review |
| Insufficient literature | bibliography_agent finds < 5 sources | Expand search strategy, alternative keywords |
| Methodology mismatch | RQ type misaligned with method capability | Return to Phase 1, suggest 3 alternative methods |
| Devil's Advocate CRITICAL | Fatal logical flaw discovered | STOP, explain the issue, require correction |
| Ethics BLOCKED | Serious ethical issue | STOP, list issues and remediation path |
| Socratic non-convergence | > 10 rounds without convergence | Suggest switching to full mode |
| User abandons mid-process | Explicitly states they don't want to continue | Save progress, provide re-entry path |
| Only Chinese-language literature | English search returns empty | Switch to Chinese academic databases |
所有模式的失败场景、触发条件和恢复策略请查看。
references/failure_paths.md核心失败路径汇总:
| 失败场景 | 触发条件 | 恢复策略 |
|---|---|---|
| 研究问题无法达成共识 | 阶段1/第1层经过多轮对话后仍然模糊 | 提供3个候选研究问题或建议使用文献综述模式 |
| 文献不足 | 文献检索Agent找到的来源<5个 | 扩展检索策略,使用替代关键词 |
| 方法不匹配 | 研究问题类型与方法能力不匹配 | 返回阶段1,建议3种替代方法 |
| 魔鬼代言人发现严重问题 | 发现致命逻辑缺陷 | 停止流程,说明问题,要求修正 |
| 伦理审核未通过 | 发现严重伦理问题 | 停止流程,列出问题和修复路径 |
| 苏格拉底模式未达成共识 | 超过10轮对话仍无共识 | 建议切换到完整模式 |
| 用户中途放弃 | 用户明确表示不想继续 | 保存进度,提供重新进入路径 |
| 仅存在中文文献 | 英文检索无结果 | 切换到中文学术数据库检索 |
Literature Monitoring (Optional Post-Pipeline)
文献监测(可选后置流程)
After any research mode is complete, users can optionally activate the to set up post-research literature monitoring. This is not part of the main pipeline — it is an auxiliary capability triggered on demand.
monitoring_agentSee for the detailed agent definition.
See for platform-specific setup guides.
agents/monitoring_agent.mdreferences/literature_monitoring_strategies.mdTrigger: "monitor this topic", "set up alerts", "track new publications on this"
Capabilities:
- Weekly/monthly monitoring digest generation
- Retraction alerts for cited sources
- Contradictory findings detection
- Key author tracking
- Keyword evolution tracking
Input: Completed bibliography + search strategy from any research mode
Output: Monitoring configuration + digest template (markdown)
Limitation: The monitoring agent produces configurations and templates for the user to act on. It cannot run autonomous background monitoring.
任意研究模式完成后,用户可选择激活设置研究后文献监测。该功能不属于主流水线,是按需触发的辅助能力。
monitoring_agent详细Agent定义请查看。
平台专属设置指南请查看。
agents/monitoring_agent.mdreferences/literature_monitoring_strategies.md触发词:"monitor this topic", "set up alerts", "track new publications on this"
功能:
- 生成周/月监测摘要
- 引用来源的撤稿提醒
- 矛盾研究结果检测
- 核心作者追踪
- 关键词演化追踪
输入:任意研究模式生成的完整参考文献 + 检索策略
输出:监测配置 + 摘要模板(markdown格式)
限制:监测Agent仅生成供用户使用的配置和模板,无法自主在后台运行监测。
Handoff Protocol: deep-research → academic-paper
移交协议:deep-research → academic-paper
After research is complete, the following materials can be handed off to :
academic-paper- Research Question Brief (from research_question_agent)
- Methodology Blueprint (from research_architect_agent)
- Annotated Bibliography (from bibliography_agent)
- Synthesis Report (from synthesis_agent)
- [If socratic mode] INSIGHT Collection and Research Plan Summary
Trigger: User says "now help me write a paper" or "write a paper based on this"
academic-paperintake_agent- Has RQ Brief -> skip topic scoping
- Has Bibliography -> skip literature search
- Has Synthesis -> accelerate findings / discussion writing
See for a detailed handoff example.
examples/handoff_to_paper.md研究完成后,以下材料可移交到工具:
academic-paper- 研究问题摘要(来自research_question_agent)
- 方法蓝图(来自research_architect_agent)
- 带注释参考文献(来自bibliography_agent)
- 综合报告(来自synthesis_agent)
- [苏格拉底模式下] 洞察合集和研究计划摘要
触发:用户说「now help me write a paper」或「write a paper based on this」
academic-paperintake_agent- 有研究问题摘要→跳过主题界定
- 有参考文献→跳过文献检索
- 有研究综合→加速结果/讨论部分撰写
详细移交示例请查看。
examples/handoff_to_paper.mdFull Academic Pipeline
完整学术流水线
See for the complete workflow.
academic-pipeline/SKILL.md完整工作流请查看。
academic-pipeline/SKILL.mdAgent File References
Agent文件参考
| Agent | Definition File |
|---|---|
| research_question_agent | |
| research_architect_agent | |
| bibliography_agent | |
| source_verification_agent | |
| synthesis_agent | |
| report_compiler_agent | |
| editor_in_chief_agent | |
| devils_advocate_agent | |
| ethics_review_agent | |
| socratic_mentor_agent | |
| risk_of_bias_agent | |
| meta_analysis_agent | |
| monitoring_agent | |
| Agent | 定义文件 |
|---|---|
| research_question_agent | |
| research_architect_agent | |
| bibliography_agent | |
| source_verification_agent | |
| synthesis_agent | |
| report_compiler_agent | |
| editor_in_chief_agent | |
| devils_advocate_agent | |
| ethics_review_agent | |
| socratic_mentor_agent | |
| risk_of_bias_agent | |
| meta_analysis_agent | |
| monitoring_agent | |
Reference Files
参考文件
| Reference | Purpose | Used By |
|---|---|---|
| APA 7th edition quick reference | report_compiler, editor_in_chief |
| Evidence pyramid + grading rubric | source_verification, bibliography |
| Research design templates | research_architect |
| 30+ fallacies catalog | devils_advocate |
| AI disclosure, attribution, dual-use | ethics_review |
| Cross-discipline connection patterns | synthesis, research_architect |
| 6 types of Socratic questions + 30+ prompt patterns | socratic_mentor |
| 12 failure scenarios with triggers and recovery paths | all agents |
| Mode selection flowchart and comparison table | orchestrator |
| IRB decision tree + Taiwan process + HE quick reference | ethics_review, research_architect |
| EQUATOR reporting guideline mapping | research_architect, report_compiler |
| Preregistration decision tree + platforms + checklist | research_architect |
| Cochrane v6.4, PRISMA 2020, RoB 2, ROBINS-I, I² guide, GRADE, protocol registration | risk_of_bias, meta_analysis, bibliography, report_compiler |
| Google Scholar alerts, PubMed alerts, RSS feeds, Retraction Watch, citation tracking, monitoring cadence | monitoring_agent |
| 参考文件 | 用途 | 使用方 |
|---|---|---|
| APA第7版快速参考 | report_compiler, editor_in_chief |
| 证据金字塔 + 分级规则 | source_verification, bibliography |
| 研究设计模板 | research_architect |
| 30+种逻辑谬误目录 | devils_advocate |
| AI披露、署名、两用性检查清单 | ethics_review |
| 跨学科关联模式 | synthesis, research_architect |
| 6种苏格拉底提问类型 + 30+提示词模式 | socratic_mentor |
| 12种失败场景及触发条件、恢复路径 | 所有Agent |
| 模式选择流程图和对比表 | 编排器 |
| IRB决策树 + 台湾流程 + 高教快速参考 | ethics_review, research_architect |
| EQUATOR报告指南映射 | research_architect, report_compiler |
| 预注册决策树 + 平台 + 检查清单 | research_architect |
| Cochrane v6.4, PRISMA 2020, RoB 2, ROBINS-I, I²指南, GRADE, 方案注册 | risk_of_bias, meta_analysis, bibliography, report_compiler |
| Google Scholar提醒、PubMed提醒、RSS订阅、撤稿观察、引用追踪、监测频率 | monitoring_agent |
Templates
模板
| Template | Purpose |
|---|---|
| Quick mode output format |
| Source x Theme analysis matrix |
| Per-source quality assessment card |
| OSF standard 21-item preregistration template |
| PRISMA-P 2015 systematic review protocol template |
| PRISMA 2020 systematic review report template (27 items) |
| 模板 | 用途 |
|---|---|
| 快速模式输出格式 |
| 来源×主题分析矩阵 |
| 单来源质量评估卡 |
| OSF标准21项预注册模板 |
| PRISMA-P 2015系统综述方案模板 |
| PRISMA 2020系统综述报告模板(27项) |
Examples
示例
| Example | Demonstrates |
|---|---|
| Full 6-phase pipeline walkthrough |
| PRISMA-style literature review |
| Applied comparative policy research |
| Complete Socratic mode multi-turn dialogue (12 rounds) |
| deep-research full mode handoff to academic-paper |
| Review mode: 3-agent review pipeline for policy recommendation text |
| Fact-check mode: source verification of HEI claims with per-claim verdicts |
| 示例 | 演示内容 |
|---|---|
| 完整6阶段流水线演示 |
| PRISMA格式文献综述 |
| 应用类比较政策研究 |
| 完整苏格拉底模式多轮对话(12轮) |
| 深度研究完整模式移交到学术论文工具 |
| 评审模式:3个Agent评审政策建议文本的流水线 |
| 事实核查模式:针对高等教育机构声明的来源验证,附每项声明的结论 |
Output Language
输出语言
Follows the user's language. Academic terminology kept in English. Socratic mode uses natural conversational style.
跟随用户使用的语言,学术术语保留英文。苏格拉底模式使用自然对话风格。
Quality Standards
质量标准
- Every claim must have a citation — no unsupported assertions
- Evidence hierarchy — meta-analyses > RCTs > cohort studies > case reports > expert opinion
- Contradiction disclosure — if sources disagree, report both sides with evidence quality comparison
- Limitation transparency — every report must have an explicit limitations section
- AI disclosure — all reports include a statement that AI-assisted research tools were used
- Reproducibility — search strategies, inclusion criteria, and analytical methods must be documented for replication
- Socratic integrity — in socratic mode, never give direct answers; always guide through questions
- 每项主张都必须有引用——无无根据的断言
- 遵循证据层级——meta分析 > 随机对照试验 > 队列研究 > 病例报告 > 专家意见
- 矛盾披露——若来源存在分歧,需同时报告双方观点并对比证据质量
- 局限性透明——每份报告都必须有明确的局限性章节
- AI披露——所有报告都包含使用AI辅助研究工具的声明
- 可复现性——检索策略、纳入标准、分析方法都必须记录,可复现
- 苏格拉底模式完整性——苏格拉底模式下永远不直接给出答案,始终通过提问引导
Cross-Agent Quality Alignment
跨Agent质量对齐
Unified definitions to prevent inconsistency across agents:
| Concept | Definition | Applies To |
|---|---|---|
| Peer-reviewed | Published in a journal with formal peer review process (editorial review alone does not qualify). Conference proceedings count only if explicitly peer-reviewed | bibliography_agent, source_verification_agent |
| Currency Rule | Default: published within 5 years. Override by domain: CS/AI = 3 years, History/Philosophy = 20 years, Law = depends on jurisdiction changes. Seminal works exempt regardless of age | bibliography_agent, ethics_review_agent |
| CRITICAL severity | Issue that, if unresolved, would invalidate a core conclusion or constitute academic misconduct. Requires immediate resolution before pipeline can proceed | All agents |
| Source Tier | tier_1 = top-quartile peer-reviewed journal; tier_2 = other peer-reviewed; tier_3 = academic but not peer-reviewed; tier_4 = grey literature | bibliography_agent, source_verification_agent |
| Minimum Source Count | full = 15+, quick = 5-8, lit-review = 25+, systematic-review = all eligible (no limit), fact-check = 3+ per claim | bibliography_agent |
| Verification Threshold | 100% DOI check + 50% WebSearch spot-check | source_verification_agent, ethics_review_agent |
Cross-Skill Reference: Seefor inter-stage data exchange formats.shared/handoff_schemas.md
统一定义避免Agent间不一致:
| 概念 | 定义 | 适用范围 |
|---|---|---|
| 同行评审 | 发表在有正式同行评审流程的期刊上(仅编辑审核不符合要求)。会议论文仅在明确有同行评审时才符合 | bibliography_agent, source_verification_agent |
| 时效性规则 | 默认:发表时间在5年内。不同领域可调整:计算机/AI=3年,历史/哲学=20年,法律=取决于司法辖区变化。里程碑式研究不受发表时间限制 | bibliography_agent, ethics_review_agent |
| 严重级别 | 若不解决会导致核心结论无效或构成学术不端的问题,需要立即解决才能推进流水线 | 所有Agent |
| 来源层级 | tier_1 = 前25%的同行评审期刊;tier_2 = 其他同行评审期刊;tier_3 = 学术类但无同行评审;tier_4 = 灰色文献 | bibliography_agent, source_verification_agent |
| 最低来源数量 | full模式=15+,quick模式=5-8,lit-review模式=25+,systematic-review模式=所有符合条件的来源(无上限),fact-check模式=每项主张至少3个来源 | bibliography_agent |
| 验证阈值 | 100% DOI检查 + 50% 网络搜索抽查 | source_verification_agent, ethics_review_agent |
跨技能参考: 阶段间数据交换格式请查看。shared/handoff_schemas.md
Integration with Other Skills
与其他技能集成
This skill is domain-agnostic but can be combined with domain-specific skills:
deep-research + tw-hei-intelligence -> Evidence-based HEI policy research
deep-research + report-to-website -> Interactive research report
deep-research + podcast-script-generator -> Research podcast
deep-research + academic-paper -> Full research-to-publication pipeline
deep-research (socratic) + academic-paper (plan) -> Guided research + paper planning
deep-research (systematic-review) + academic-paper -> PRISMA systematic review paper该技能是跨领域的,但可与领域专属技能结合使用:
deep-research + tw-hei-intelligence -> Evidence-based HEI policy research
deep-research + report-to-website -> Interactive research report
deep-research + podcast-script-generator -> Research podcast
deep-research + academic-paper -> Full research-to-publication pipeline
deep-research (socratic) + academic-paper (plan) -> Guided research + paper planning
deep-research (systematic-review) + academic-paper -> PRISMA systematic review paperVersion History
版本历史
| Version | Date | Changes |
|---|---|---|
| 2.3 | 2026-03-08 | Added systematic-review mode (7th mode): PRISMA 2020 compliant pipeline with risk_of_bias_agent (RoB 2 + ROBINS-I), meta_analysis_agent (effect sizes, heterogeneity, GRADE, narrative synthesis), 2 new templates (PRISMA protocol + report), systematic_review_toolkit reference. Added monitoring_agent (post-pipeline literature monitoring with digests, retraction alerts, author tracking) + literature_monitoring_strategies reference. Enhanced socratic_mentor_agent with 4 convergence signals, 4-type question taxonomy, and auto-end triggers. Added Quick Mode Selection Guide to SKILL.md |
| 2.2 | 2025-03-05 | Added synthesis anti-patterns, Socratic quantified thresholds & auto-end conditions, reference existence verification (DOI + WebSearch), enhanced ethics reference integrity check (50% + Retraction Watch), mode transition matrix, cross-agent quality alignment definitions |
| 2.1 | 2026-03 | Added IRB decision tree, EQUATOR reporting guidelines, preregistration guide + template; enhanced ethics_review_agent with human subjects dimension; enhanced research_architect_agent with ethics/EQUATOR/preregistration integration; enhanced methodology_patterns with EQUATOR cross-references |
| 2.0 | 2026-02 | Added socratic mode (10th agent), failure paths, mode selection guide, handoff protocol, 2 new examples, 3 new references |
| 1.0 | 2026-02 | Initial release: 9 agents, 5 modes, 6-phase pipeline |
| 版本 | 日期 | 更新内容 |
|---|---|---|
| 2.3 | 2026-03-08 | 新增系统综述模式(第7种模式):符合PRISMA 2020标准的流水线,包含risk_of_bias_agent(RoB 2 + ROBINS-I)、meta_analysis_agent(效应量、异质性、GRADE、叙事综合),2个新模板(PRISMA方案+报告),系统综述工具包参考。新增monitoring_agent(流水线后文献监测,包含摘要、撤稿提醒、作者追踪)+ 文献监测策略参考。增强socratic_mentor_agent,新增4种共识信号、4类提问分类和自动结束触发条件。在SKILL.md中新增快速模式选择指南 |
| 2.2 | 2025-03-05 | 新增综合反模式、苏格拉底量化阈值和自动结束条件、参考文献存在性验证(DOI + 网络搜索)、增强伦理参考完整性检查(50% + 撤稿观察)、模式转换矩阵、跨Agent质量对齐定义 |
| 2.1 | 2026-03 | 新增IRB决策树、EQUATOR报告指南、预注册指南+模板;增强ethics_review_agent的人类受试者维度;增强research_architect_agent的伦理/EQUATOR/预注册集成;增强methodology_patterns的EQUATOR交叉参考 |
| 2.0 | 2026-02 | 新增苏格拉底模式(第10个Agent)、失败路径、模式选择指南、移交协议、2个新示例、3个新参考文件 |
| 1.0 | 2026-02 | 初始版本:9个Agent、5种模式、6阶段流水线 |