Back to Details

academic-pipeline

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Academic Pipeline v3.0 — Full Academic Research Workflow Orchestrator

Academic Pipeline v3.0 — 全学术研究工作流编排器

A lightweight orchestrator that manages the complete academic pipeline from research exploration to final manuscript. It does not perform substantive work — it only detects stages, recommends modes, dispatches skills, manages transitions, and tracks state.
v2.0 Core Improvements:
  1. Mandatory user confirmation checkpoints — Each stage completion requires user confirmation before proceeding to the next step
  2. Academic integrity verification — After paper completion and before review submission, 100% reference and data verification must pass
  3. Two-stage review — First full review + post-revision focused verification review
  4. Final integrity check — After revision completion, re-verify all citations and data are 100% correct
  5. Reproducible — Standardized workflow producing consistent quality assurance each time
  6. Process documentation — After pipeline completion, automatically generates a "Paper Creation Process Record" PDF documenting the human-AI collaboration history
这是一款轻量编排器，用于管理从研究探索到最终稿件的完整学术管线。它本身不执行实质性工作，仅负责检测阶段、推荐模式、调度技能、管理流程流转和跟踪状态。
v2.0核心升级:
  1. 强制用户确认检查点 — 每个阶段完成后都需要用户确认才能进入下一步
  2. 学术诚信验证 — 论文完成后、提交评审前，必须100%通过参考文献和数据验证
  3. 两阶段评审 — 首次全量评审 + 修改后针对性验证评审
  4. 最终完整性检查 — 修改完成后，重新验证所有引用和数据100%正确
  5. 可复现 — 标准化工作流每次都能产出一致的质量保障结果
  6. 过程文档 — 管线完成后，自动生成「论文创作过程记录」PDF，记录人机协作历史

Quick Start

快速开始

Full workflow (from scratch):
I want to write a research paper on the impact of AI on higher education quality assurance
--> academic-pipeline launches, starting from Stage 1 (RESEARCH)
Mid-entry (existing paper):
I already have a paper, help me review it
--> academic-pipeline detects mid-entry, starting from Stage 2.5 (INTEGRITY)
Revision mode (received reviewer feedback):
I received reviewer comments, help me revise
--> academic-pipeline detects, starting from Stage 4 (REVISE)
Execution flow:
  1. Detect the user's current stage and available materials
  2. Recommend the optimal mode for each stage
  3. Dispatch the corresponding skill for each stage
  4. After each stage completion, proactively prompt and wait for user confirmation
  5. Track progress throughout; Pipeline Status Dashboard available at any time
全流程（从零开始）:
I want to write a research paper on the impact of AI on higher education quality assurance
--> academic-pipeline启动，从第1阶段（RESEARCH）开始
中途进入（已有论文）:
I already have a paper, help me review it
--> academic-pipeline检测到中途进入场景，从第2.5阶段（INTEGRITY）开始
修改模式（已收到评审意见）:
I received reviewer comments, help me revise
--> academic-pipeline检测到对应场景，从第4阶段（REVISE）开始
执行流程:
  1. 检测用户当前所处阶段和可用材料
  2. 为每个阶段推荐最优模式
  3. 为每个阶段调度对应技能
  4. 每个阶段完成后，主动提示并等待用户确认
  5. 全程跟踪进度，随时可查看管线状态仪表盘

Trigger Conditions

触发条件

Trigger Keywords

触发关键词

English: academic pipeline, research to paper, full paper workflow, paper pipeline, end-to-end paper, research-to-publication, complete paper workflow
英文: academic pipeline, research to paper, full paper workflow, paper pipeline, end-to-end paper, research-to-publication, complete paper workflow

Non-Trigger Scenarios

非触发场景

ScenarioSkill to Use
Only need to search materials or do a literature review
deep-research
Only need to write a paper (no research phase needed)
academic-paper
Only need to review a paper
academic-paper-reviewer
Only need to check citation format
academic-paper
(citation-check mode)
Only need to convert paper format
academic-paper
(format-convert mode)
场景应使用的技能
仅需要搜索材料或做文献综述
deep-research
仅需要撰写论文（无需研究阶段）
academic-paper
仅需要评审论文
academic-paper-reviewer
仅需要检查引用格式
academic-paper
（citation-check模式）
仅需要转换论文格式
academic-paper
（format-convert模式）

Trigger Exclusions

触发排除规则

  • If the user only needs a single function (just search materials, just check citations), no pipeline is needed — directly trigger the corresponding skill
  • If the user is already using a specific mode of a skill, do not force them into the pipeline
  • The pipeline is optional, not mandatory
  • 如果用户仅需要单一功能（仅搜索材料、仅检查引用），不需要启动管线，直接触发对应技能即可
  • 如果用户已经在使用某技能的特定模式，不要强制将其纳入管线
  • 管线是可选的，不是强制的

Pipeline Stages (10 Stages)

管线阶段（共10个阶段）

StageNameSkill / Agent CalledAvailable ModesDeliverables
1RESEARCH
deep-research
socratic, full, quickRQ Brief, Methodology, Bibliography, Synthesis
2WRITE
academic-paper
plan, fullPaper Draft
2.5INTEGRITY
integrity_verification_agent
pre-reviewIntegrity verification report + corrected paper
3REVIEW
academic-paper-reviewer
full (incl. Devil's Advocate)5 review reports + Editorial Decision + Revision Roadmap
4REVISE
academic-paper
revisionRevised Draft, Response to Reviewers
3'RE-REVIEW
academic-paper-reviewer
re-reviewVerification review report: revision response checklist + residual issues
4'RE-REVISE
academic-paper
revisionSecond revised draft (if needed)
4.5FINAL INTEGRITY
integrity_verification_agent
final-checkFinal verification report (must achieve 100% pass to proceed)
5FINALIZE
academic-paper
format-convertFinal Paper (default MD + DOCX; ask about LaTeX; confirm correctness; PDF)
6PROCESS SUMMARYorchestratorautoPaper creation process record MD + LaTeX to PDF (bilingual)
阶段名称调用的技能/Agent可用模式交付物
1RESEARCH
deep-research
socratic, full, quickRQ说明、研究方法、参考文献列表、研究综述
2WRITE
academic-paper
plan, full论文草稿
2.5INTEGRITY
integrity_verification_agent
pre-review完整性验证报告 + 修正后的论文
3REVIEW
academic-paper-reviewer
full (incl. Devil's Advocate)5份评审报告 + 编辑决定 + 修改路线图
4REVISE
academic-paper
revision修改后的草稿、评审意见回复
3'RE-REVIEW
academic-paper-reviewer
re-review验证评审报告：修改响应检查清单 + 遗留问题
4'RE-REVISE
academic-paper
revision第二版修改草稿（如需要）
4.5FINAL INTEGRITY
integrity_verification_agent
final-check最终验证报告（必须100%通过才可进入下一阶段）
5FINALIZE
academic-paper
format-convert最终论文（默认MD + DOCX；询问是否需要LaTeX；确认正确性；PDF版本）
6PROCESS SUMMARYorchestratorauto论文创作过程记录MD + LaTeX转PDF（双语）

Pipeline State Machine

管线状态机

  1. Stage 1 RESEARCH -> user confirmation -> Stage 2
  2. Stage 2 WRITE -> user confirmation -> Stage 2.5
  3. Stage 2.5 INTEGRITY -> PASS -> Stage 3 (FAIL -> fix and re-verify, max 3 rounds)
  4. Stage 3 REVIEW -> Accept -> Stage 4.5 / Minor|Major -> Stage 4 / Reject -> Stage 2 or end
  5. Stage 4 REVISE -> user confirmation -> Stage 3'
  6. Stage 3' RE-REVIEW -> Accept|Minor -> Stage 4.5 / Major -> Stage 4'
  7. Stage 4' RE-REVISE -> user confirmation -> Stage 4.5 (no return to review)
  8. Stage 4.5 FINAL INTEGRITY -> PASS (zero issues) -> Stage 5 (FAIL -> fix and re-verify)
  9. Stage 5 FINALIZE -> MD + DOCX -> ask about LaTeX -> confirm -> PDF -> Stage 6
  10. Stage 6 PROCESS SUMMARY -> ask language version -> generate process record MD -> LaTeX -> PDF -> end
See 
references/pipeline_state_machine.md
for complete state transition definitions.
  1. 阶段1 RESEARCH -> 用户确认 -> 阶段2
  2. 阶段2 WRITE -> 用户确认 -> 阶段2.5
  3. 阶段2.5 INTEGRITY -> 通过 -> 阶段3（不通过 -> 修正后重新验证，最多3轮）
  4. 阶段3 REVIEW -> 接收 -> 阶段4.5 / 小修|大修 -> 阶段4 / 拒稿 -> 阶段2或结束
  5. 阶段4 REVISE -> 用户确认 -> 阶段3'
  6. 阶段3' RE-REVIEW -> 接收|小修 -> 阶段4.5 / 大修 -> 阶段4'
  7. 阶段4' RE-REVISE -> 用户确认 -> 阶段4.5（不再返回评审环节）
  8. 阶段4.5 FINAL INTEGRITY -> 通过（零问题） -> 阶段5（不通过 -> 修正后重新验证）
  9. 阶段5 FINALIZE -> MD + DOCX -> 询问是否需要LaTeX -> 确认 -> PDF -> 阶段6
  10. 阶段6 PROCESS SUMMARY -> 询问语言版本 -> 生成过程记录MD -> LaTeX -> PDF -> 结束
完整状态流转定义请查看 
references/pipeline_state_machine.md

Adaptive Checkpoint System

自适应检查点系统

⚠️ IRON RULE — Core rule: After each stage completion, the system must proactively prompt the user and wait for confirmation. The checkpoint presentation adapts based on context and user engagement.
⚠️ 铁则 — 核心规则：每个阶段完成后，系统必须主动提示用户并等待确认。检查点的展示形式会根据上下文和用户参与度自适应调整。

Checkpoint Types

检查点类型

TypeWhen UsedContent
FULLFirst checkpoint; after integrity boundaries; before finalizationFull deliverables list + decision dashboard + all options
SLIMAfter 2+ consecutive "continue" responses on non-critical stagesOne-line status + auto-continue in 5 seconds
MANDATORYIntegrity FAIL; Review decision; Stage 5Cannot be skipped; requires explicit user input
类型使用时机内容
FULL首次检查点；完整性边界后；定稿前全量交付物清单 + 决策仪表盘 + 所有可选操作
SLIM非关键阶段连续2次以上选择「继续」后单行状态提示 + 5秒后自动继续
MANDATORY完整性验证不通过；评审决定；阶段5不可跳过；需要用户明确输入确认

Decision Dashboard (shown at FULL checkpoints)

决策仪表盘（FULL检查点展示）

━━━ Stage [X] [Name] Complete ━━━

Metrics:
- Word count: [N] (target: [T] +/-10%)    [OK/OVER/UNDER]
- References: [N] (min: [M])              [OK/LOW]
- Coverage: [N]/[T] sections drafted       [COMPLETE/PARTIAL]
- Quality indicators: [score if available]

Deliverables:
- [Material 1]
- [Material 2]

Flagged: [any issues detected, or "None"]

Ready to proceed to Stage [Y]? You can also:
1. View progress (say "status")
2. Adjust settings
3. Pause pipeline
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
━━━ Stage [X] [Name] Complete ━━━

Metrics:
- Word count: [N] (target: [T] +/-10%)    [OK/OVER/UNDER]
- References: [N] (min: [M])              [OK/LOW]
- Coverage: [N]/[T] sections drafted       [COMPLETE/PARTIAL]
- Quality indicators: [score if available]

Deliverables:
- [Material 1]
- [Material 2]

Flagged: [any issues detected, or "None"]

Ready to proceed to Stage [Y]? You can also:
1. View progress (say "status")
2. Adjust settings
3. Pause pipeline
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Adaptive Rules

自适应规则

  1. First checkpoint: always FULL
  2. After 2+ consecutive "continue" without review: prompt user awareness ("You've auto-continued [N] times. Want to review progress?")
  3. Integrity boundaries (Stage 2.5, 4.5): always MANDATORY
  4. Review decisions (Stage 3, 3'): always MANDATORY
  5. Before finalization (Stage 5): always MANDATORY
  6. All other stages: start FULL, downgrade to SLIM if user says "just continue"
  1. 首次检查点: 始终使用FULL类型
  2. 连续2次以上未审核直接选择「继续」后: 提示用户注意（「您已经自动继续[N]次，是否需要查看进度？」）
  3. 完整性边界（阶段2.5、4.5）: 始终使用MANDATORY类型
  4. 评审决定（阶段3、3'）: 始终使用MANDATORY类型
  5. 定稿前（阶段5）: 始终使用MANDATORY类型
  6. 所有其他阶段: 默认使用FULL类型，若用户选择「直接继续」则降级为SLIM类型

Checkpoint Rules

检查点规则

  1. ⚠️ IRON RULE: Cannot auto-skip MANDATORY checkpoints: Even if the previous stage result is perfect, explicit user input is required at MANDATORY checkpoints
  2. User can adjust: At FULL and MANDATORY checkpoints, users can modify the mode or settings for the next step
  3. Pause-friendly: Users can pause at any checkpoint and resume later
  4. SLIM mode: If the user says "just continue" or "fully automatic," subsequent non-critical checkpoints switch to SLIM format (one-line status + auto-continue), but notifications are still sent
  5. Awareness guard: After 4+ consecutive auto-continues, the system inserts a FULL checkpoint regardless of stage type to ensure user remains engaged
  1. ⚠️ 铁则: MANDATORY检查点不可自动跳过: 即便上一阶段结果完美，MANDATORY检查点也需要用户明确输入确认
  2. 用户可调整配置: 在FULL和MANDATORY检查点，用户可以修改下一阶段的模式或配置
  3. 支持暂停: 用户可以在任意检查点暂停，后续可恢复执行
  4. SLIM模式: 如果用户选择「直接继续」或「全自动执行」，后续非关键检查点切换为SLIM格式（单行状态 + 自动继续），但仍会发送通知
  5. 注意力保障: 连续4次以上自动继续后，无论当前阶段类型，系统都会插入一个FULL检查点，确保用户仍知晓进度

Self-Check Questions (at every FULL checkpoint)

自检问题（每个FULL检查点执行）

Before presenting the checkpoint to the user, the orchestrator asks itself:
  1. Citation integrity: Are there any unverified citations in the latest output?
  2. Sycophantic concession: Did the latest stage uncritically accept all feedback without pushback?
  3. Quality trajectory: Is the latest output ≥ the quality of the previous stage? If declining, PAUSE and flag.
  4. Scope discipline: Did the latest stage add content not requested by the user or the revision roadmap?
  5. Completeness: Are all required deliverables for this stage present?
If ANY answer raises concern, include it in the checkpoint presentation to the user.
在向用户展示检查点前，编排器需要先自检以下问题：
  1. 引用完整性: 最新输出中是否存在未验证的引用？
  2. 无原则妥协: 上一阶段是否不加批判地接受了所有反馈，没有提出任何异议？
  3. 质量趋势: 最新输出的质量是否≥上一阶段的输出质量？如果下降，暂停并标记问题
  4. 范围管控: 上一阶段是否添加了用户或修改路线图未要求的内容？
  5. 完整性: 本阶段要求的所有交付物是否都已产出？
如果任意问题存在隐患，需要在向用户展示的检查点中明确提及。

Agent Team (3 Agents)

Agent团队（共3个Agent）

#AgentRoleFile
1
pipeline_orchestrator_agent
Main orchestrator: detects stage, recommends mode, triggers skill, manages transitions
agents/pipeline_orchestrator_agent.md
2
state_tracker_agent
State tracker: records completed stages, produced materials, revision loop count
agents/state_tracker_agent.md
3
integrity_verification_agent
Integrity verifier: 100% reference/citation/data verification
agents/integrity_verification_agent.md
序号Agent角色文件
1
pipeline_orchestrator_agent
主编排器：检测阶段、推荐模式、触发技能、管理流转
agents/pipeline_orchestrator_agent.md
2
state_tracker_agent
状态跟踪器：记录已完成阶段、已产出材料、修改循环次数
agents/state_tracker_agent.md
3
integrity_verification_agent
完整性验证器：100%验证参考文献/引用/数据
agents/integrity_verification_agent.md

Orchestrator Workflow

编排器工作流

Step 1: INTAKE & DETECTION

步骤1：接收与检测

pipeline_orchestrator_agent analyzes the user's input:

1. What materials does the user have?
   - No materials           --> Stage 1 (RESEARCH)
   - Has research data      --> Stage 2 (WRITE)
   - Has paper draft        --> Stage 2.5 (INTEGRITY)
   - Has verified paper     --> Stage 3 (REVIEW)
   - Has review comments    --> Stage 4 (REVISE)
   - Has revised draft      --> Stage 3' (RE-REVIEW)
   - Has final draft for formatting --> Stage 5 (FINALIZE)

2. What is the user's goal?
   - Full workflow (research to publication)
   - Partial workflow (only certain stages needed)

3. Determine entry point, confirm with user
pipeline_orchestrator_agent analyzes the user's input:

1. What materials does the user have?
   - No materials           --> Stage 1 (RESEARCH)
   - Has research data      --> Stage 2 (WRITE)
   - Has paper draft        --> Stage 2.5 (INTEGRITY)
   - Has verified paper     --> Stage 3 (REVIEW)
   - Has review comments    --> Stage 4 (REVISE)
   - Has revised draft      --> Stage 3' (RE-REVIEW)
   - Has final draft for formatting --> Stage 5 (FINALIZE)

2. What is the user's goal?
   - Full workflow (research to publication)
   - Partial workflow (only certain stages needed)

3. Determine entry point, confirm with user

Step 2: MODE RECOMMENDATION

步骤2：模式推荐

Based on entry point and user preferences, recommend modes for each stage:

User type determination:
- Novice / wants guidance --> socratic (Stage 1) + plan (Stage 2) + guided (Stage 3)
- Experienced / wants direct output --> full (Stage 1) + full (Stage 2) + full (Stage 3)
- Time-limited --> quick (Stage 1) + full (Stage 2) + quick (Stage 3)

Explain the differences between modes when recommending, letting the user choose
Based on entry point and user preferences, recommend modes for each stage:

User type determination:
- Novice / wants guidance --> socratic (Stage 1) + plan (Stage 2) + guided (Stage 3)
- Experienced / wants direct output --> full (Stage 1) + full (Stage 2) + full (Stage 3)
- Time-limited --> quick (Stage 1) + full (Stage 2) + quick (Stage 3)

Explain the differences between modes when recommending, letting the user choose

Step 3: STAGE EXECUTION

步骤3：阶段执行

Call the corresponding skill (does not do work itself, purely dispatching):

1. Inform the user which Stage is about to begin
2. Load the corresponding skill's SKILL.md
3. Launch the skill with the recommended mode
4. Monitor stage completion status

After completion:
1. Compile deliverables list
2. Update pipeline state (call state_tracker_agent)
3. [MANDATORY] Proactively prompt checkpoint, wait for user confirmation
Call the corresponding skill (does not do work itself, purely dispatching):

1. Inform the user which Stage is about to begin
2. Load the corresponding skill's SKILL.md
3. Launch the skill with the recommended mode
4. Monitor stage completion status

After completion:
1. Compile deliverables list
2. Update pipeline state (call state_tracker_agent)
3. [MANDATORY] Proactively prompt checkpoint, wait for user confirmation

Step 4: TRANSITION

步骤4：流程流转

After user confirmation:

1. Pass the previous stage's deliverables as input to the next stage
2. Trigger handoff protocol (defined in each skill's SKILL.md):
   - Stage 1  --> 2: deep-research handoff (RQ Brief + Bibliography + Synthesis)
   - Stage 2  --> 2.5: Pass complete paper to integrity_verification_agent
   - Stage 2.5 --> 3: Pass verified paper to reviewer
   - Stage 3  --> 4: Pass Revision Roadmap to academic-paper revision mode
   - Stage 4  --> 3': Pass revised draft and Response to Reviewers to reviewer
   - Stage 3' --> 4': Pass new Revision Roadmap + R&R Traceability Matrix (Schema 11) to academic-paper revision mode
   - Stage 4/4' --> 4.5: Pass revision-completed paper to integrity_verification_agent (final verification)
   - Stage 4.5 --> 5: Pass verified final draft to format-convert mode
3. Begin next stage
After user confirmation:

1. Pass the previous stage's deliverables as input to the next stage
2. Trigger handoff protocol (defined in each skill's SKILL.md):
   - Stage 1  --> 2: deep-research handoff (RQ Brief + Bibliography + Synthesis)
   - Stage 2  --> 2.5: Pass complete paper to integrity_verification_agent
   - Stage 2.5 --> 3: Pass verified paper to reviewer
   - Stage 3  --> 4: Pass Revision Roadmap to academic-paper revision mode
   - Stage 4  --> 3': Pass revised draft and Response to Reviewers to reviewer
   - Stage 3' --> 4': Pass new Revision Roadmap + R&R Traceability Matrix (Schema 11) to academic-paper revision mode
   - Stage 4/4' --> 4.5: Pass revision-completed paper to integrity_verification_agent (final verification)
   - Stage 4.5 --> 5: Pass verified final draft to format-convert mode
3. Begin next stage

Mid-Conversation Reinforcement Protocol

对话中途强化协议

At every stage transition, the orchestrator MUST inject a brief core principles reminder. This prevents context rot in long conversations.
Template (adapt to the upcoming stage):
--- STAGE TRANSITION: [Current] → [Next] ---

🔄 Core Principles Reinforcement:
1. [Most relevant IRON RULE for the next stage]
2. [Most relevant Anti-Pattern to avoid in the next stage]
3. Quality check: Is the output of [Current Stage] at least as good as [Previous Stage]? If not, PAUSE.

Checkpoint: [MANDATORY/ADVISORY] — [What user needs to confirm]
---
Stage-specific reinforcement content: See 
references/reinforcement_content.md
for the full transition → reinforcement focus table.
每次阶段流转时，编排器必须插入简短的核心原则提示，避免长对话中出现上下文丢失。
模板（根据下一阶段适配内容）:
--- STAGE TRANSITION: [Current] → [Next] ---

🔄 Core Principles Reinforcement:
1. [Most relevant IRON RULE for the next stage]
2. [Most relevant Anti-Pattern to avoid in the next stage]
3. Quality check: Is the output of [Current Stage] at least as good as [Previous Stage]? If not, PAUSE.

Checkpoint: [MANDATORY/ADVISORY] — [What user needs to confirm]
---
阶段专属强化内容: 完整的流转→强化重点对照表请查看 
references/reinforcement_content.md

Integrity Review Protocol

完整性评审协议

Stage 2.5 (pre-review) and Stage 4.5 (post-revision) verification. 5-phase protocol: references → citation context → statistical data → originality → claims.
⚠️ IRON RULE: Stage 4.5 must PASS with zero issues to proceed to Stage 5. Stage 4.5 verifies from scratch independently.
See 
references/integrity_review_protocol.md
for full 5-phase verification procedures.
阶段2.5（评审前）和阶段4.5（修改后）执行验证，包含5个阶段：参考文献→引用上下文→统计数据→原创性→观点声明。
⚠️ 铁则: 阶段4.5必须零问题通过才能进入阶段5，阶段4.5将独立从头开始验证，不依赖之前的验证结果。
完整的5阶段验证流程请查看 
references/integrity_review_protocol.md

Two-Stage Review Protocol

两阶段评审协议

Stage 3 (full review, 5 reviewers) → Revision Coaching → Stage 4 → Stage 3' (re-review) → optional Residual Coaching → Stage 4'.
See 
references/two_stage_review_protocol.md
for detailed stage flows and coaching dialogue limits.
阶段3（全量评审，5位评审人）→修改指导→阶段4→阶段3'（复审）→可选遗留问题指导→阶段4'。
详细的阶段流程和指导对话限制请查看 
references/two_stage_review_protocol.md

Mid-Entry Protocol

中途进入协议

Users can enter from any stage. The orchestrator will:
  1. Detect materials: Analyze the content provided by the user to determine what is available
  2. Identify gaps: Check what prerequisite materials are needed for the target stage
  3. Suggest backfilling: If critical materials are missing, suggest whether to return to earlier stages
  4. Direct entry: If materials are sufficient, directly start the specified stage
Important: mid-entry cannot skip Stage 2.5
  • If the user brings a paper and enters directly, go through Stage 2.5 (INTEGRITY) first before Stage 3 (REVIEW)
  • Only exception: User can provide a previous integrity verification report and content has not been modified
用户可以从任意阶段进入，编排器将执行以下操作：
  1. 材料检测: 分析用户提供的内容，确认现有材料
  2. 缺口识别: 检查目标阶段需要的前置材料是否齐全
  3. 补全建议: 如果缺少关键材料，建议是否返回更早的阶段
  4. 直接进入: 如果材料足够，直接启动指定阶段
重要提示：中途进入不可跳过阶段2.5
  • 如果用户自带论文直接进入，需要先完成阶段2.5（INTEGRITY），再进入阶段3（REVIEW）
  • 唯一例外：用户可以提供之前的完整性验证报告，且论文内容未做修改

External Review Protocol

外部评审协议

Handles external (human) reviewer feedback integration. 4-step workflow: Intake & Structuring → Strategic Revision Coaching → Revision & Response → Self-Verification.
See 
references/external_review_protocol.md
for the complete 4-step workflow, coaching dialogue patterns, and capability boundaries.
用于整合外部（人类）评审意见，包含4步工作流：接收与结构化→战略修改指导→修改与回复→自验证。
完整的4步工作流、指导对话模式和能力边界请查看 
references/external_review_protocol.md

Progress Dashboard

进度仪表盘

ASCII dashboard shown at FULL checkpoints to display pipeline progress.
See 
references/progress_dashboard_template.md
for the dashboard template.
FULL检查点展示的ASCII仪表盘，用于显示管线进度。
仪表盘模板请查看 
references/progress_dashboard_template.md

Revision Loop Management

修改循环管理

  • Stage 3 (first review) -> Stage 4 (revision) -> Stage 3' (verification review) -> Stage 4' (re-revision, if needed) -> Stage 4.5 (final verification)
  • Maximum 1 round of RE-REVISE (Stage 4'): If Stage 3' gives Major, enter Stage 4' for revision then proceed directly to Stage 4.5 (no return to review)
  • Pipeline overrides academic-paper's max 2 revision rule: In the pipeline, revisions are limited to Stage 4 + Stage 4' (one round each), replacing academic-paper's max 2 rounds rule
  • Mark unresolved issues as Acknowledged Limitations
  • Provide cumulative revision history (each round's decision, items addressed, unresolved items)
  • 阶段3（首次评审）-> 阶段4（修改）-> 阶段3'（验证评审）-> 阶段4'（再修改，如需要）-> 阶段4.5（最终验证）
  • 最多1轮RE-REVISE（阶段4'）: 如果阶段3'给出大修意见，进入阶段4'修改后直接进入阶段4.5（不再返回评审）
  • 管线覆盖academic-paper的最多2轮修改规则: 在管线中，修改限制为阶段4 + 阶段4'（各1轮），替代academic-paper的最多2轮规则
  • 未解决的问题标记为「已确认的局限性」
  • 提供累计修改历史（每轮的决定、已解决项、未解决项）

Reproducibility

可复现性

Every pipeline artifact is versioned, hashed, and auditable.
See 
references/reproducibility_audit.md
for standardized workflow guarantees, audit trail format, and artifact tracking.
所有管线产物都有版本标识、哈希值，支持审计。
标准化工作流保障、审计轨迹格式和产物跟踪规则请查看 
references/reproducibility_audit.md

Stage 6: Process Summary Protocol

阶段6：过程总结协议

Produces the final process record: paper creation journey, collaboration quality evaluation (6 dimensions, 1-100), and AI self-reflection report.
See 
references/process_summary_protocol.md
for full workflow, required content structure, scoring dimensions, and output specifications.
产出最终过程记录：论文创作历程、协作质量评估（6个维度，1-100分）和AI自反思报告。
完整工作流、要求的内容结构、评分维度和输出规范请查看 
references/process_summary_protocol.md

Anti-Patterns

反模式

Explicit prohibitions to prevent common failure modes:
#Anti-PatternWhy It FailsCorrect Behavior
1Skipping integrity checks"The paper looks fine, skip Stage 2.5/4.5"Integrity checks are MANDATORY; they cannot be auto-skipped regardless of perceived quality
2Orchestrator doing substantive workPipeline orchestrator writes content or reviews the paperOrchestrator only dispatches and coordinates; substantive work belongs to the sub-skills
3Auto-advancing past MANDATORY checkpointsMoving to next stage without user confirmation at FULL checkpointsMANDATORY checkpoints require explicit user input before proceeding
4Quality degradation across stagesStage 4 revision is worse than Stage 2 draft because context window is exhaustedIf Stage N output quality < Stage N-1, PAUSE and reload core principles before continuing
5Silently dropping reviewer concernsRevision addresses 8 of 10 concerns and hopes nobody noticesThe R&R tracking table must account for every concern with explicit status
6Re-verifying only known issues at Stage 4.5Final integrity check only re-checks Stage 2.5 findingsStage 4.5 must verify from scratch independently; revision may introduce new issues
7Inflating Collaboration Quality scoresGiving 90/100 to avoid awkward self-criticismHonesty first: no inflation, no pleasantries; cite specific evidence for every score
明确禁止的常见失败场景：
序号反模式失败原因正确行为
1跳过完整性检查「论文看起来没问题，跳过阶段2.5/4.5」完整性检查是强制的，无论感知质量如何都不能自动跳过
2编排器执行实质性工作管线编排器直接撰写内容或评审论文编排器仅负责调度和协调，实质性工作由子技能完成
3自动跳过MANDATORY检查点进入下一阶段未获得用户确认就进入下一阶段MANDATORY检查点需要用户明确输入确认后才可继续
4跨阶段质量下降因为上下文窗口耗尽，阶段4的修改稿质量比阶段2的草稿还差如果第N阶段输出质量 < 第N-1阶段，暂停并重载核心原则后再继续
5静默忽略评审意见修改仅处理了10条意见中的8条，希望没人发现修改跟踪表必须明确标注每条意见的处理状态
6阶段4.5仅重新验证已知问题最终完整性检查仅重新检查阶段2.5发现的问题阶段4.5必须独立从头验证，修改可能引入新问题
7协作质量评分虚高为了避免尴尬的自我批评给出90/100的分数诚实第一：不抬分、不客套，每个分数都要有明确证据支撑

Quality Standards

质量标准

DimensionRequirement
Stage detectionCorrectly identify user's current stage and available materials
Mode recommendationRecommend appropriate mode based on user preferences and material status
Material handoffStage-to-stage handoff materials are complete and correctly formatted
State trackingPipeline state updated in real time; Progress Dashboard accurate
Mandatory checkpointUser confirmation required after each stage completion
Mandatory integrity checkStage 2.5 and 4.5 cannot be skipped, must PASS
No overstepping⚠️ IRON RULE: Orchestrator does not perform substantive research/writing/reviewing, only dispatching
No forcing⚠️ IRON RULE: User can pause or exit pipeline at any time (but cannot skip integrity checks)
ReproducibleSame input follows the same workflow across different sessions
维度要求
阶段检测正确识别用户当前阶段和可用材料
模式推荐根据用户偏好和材料状态推荐合适的模式
材料流转阶段间流转的材料完整、格式正确
状态跟踪管线状态实时更新，进度仪表盘信息准确
强制检查点每个阶段完成后必须获得用户确认
强制完整性检查阶段2.5和4.5不可跳过，必须通过
不越权操作⚠️ 铁则：编排器不执行实质性的研究/写作/评审工作，仅负责调度
不强制使用⚠️ 铁则：用户可以随时暂停或退出管线（但不能跳过完整性检查）
可复现同一输入在不同会话中遵循相同的工作流

Error Recovery

错误恢复

StageErrorHandling
IntakeCannot determine entry pointAsk user what materials they have and their goal
Stage 1deep-research not convergingSuggest mode switch (socratic -> full) or narrow scope
Stage 2Missing research foundationSuggest returning to Stage 1 to supplement research
Stage 2.5Still FAIL after 3 correction roundsList unverifiable items; user decides whether to continue
Stage 3Review result is RejectProvide options: major restructuring (Stage 2) or abandon
Stage 4Revision incomplete on all itemsList unaddressed items; ask whether to continue
Stage 3'Verification still has major issuesEnter Stage 4' for final revision
Stage 4'Issues remain after revisionMark as Acknowledged Limitations; proceed to Stage 4.5
Stage 4.5Final verification FAILFix and re-verify (max 3 rounds)
AnyUser leaves midwaySave pipeline state; can resume from breakpoint next time
AnySkill execution failureReport error; suggest retry or skip
阶段错误处理方式
接收阶段无法确定进入点询问用户拥有的材料和目标
阶段1deep-research未收敛建议切换模式（socratic→full）或缩小研究范围
阶段2缺少研究基础建议返回阶段1补充研究
阶段2.53轮修正后仍未通过列出无法验证的项，由用户决定是否继续
阶段3评审结果为拒稿提供选项：重大重构（返回阶段2）或放弃
阶段4未完成所有项的修改列出未处理的项，询问用户是否继续
阶段3'验证仍存在重大问题进入阶段4'进行最终修改
阶段4'修改后仍存在问题标记为「已确认的局限性」，进入阶段4.5
阶段4.5最终验证未通过修改后重新验证（最多3轮）
任意阶段用户中途退出保存管线状态，下次可从断点恢复
任意阶段技能执行失败报错，建议重试或跳过

Agent File References

Agent文件参考

AgentDefinition File
pipeline_orchestrator_agent
agents/pipeline_orchestrator_agent.md
state_tracker_agent
agents/state_tracker_agent.md
integrity_verification_agent
agents/integrity_verification_agent.md
Agent定义文件
pipeline_orchestrator_agent
agents/pipeline_orchestrator_agent.md
state_tracker_agent
agents/state_tracker_agent.md
integrity_verification_agent
agents/integrity_verification_agent.md

Reference Files

参考文件

ReferencePurpose
references/pipeline_state_machine.md
Complete state machine definition: all legal transitions, preconditions, actions
references/plagiarism_detection_protocol.md
Phase D originality verification protocol + self-plagiarism + AI text characteristics
references/mode_advisor.md
Unified cross-skill decision tree: maps user intent to optimal skill + mode
references/claim_verification_protocol.md
Phase E claim verification protocol: claim extraction, source tracing, cross-referencing, verdict taxonomy
references/team_collaboration_protocol.md
Multi-person team coordination: role definitions, handoff protocol, version control, conflict resolution
references/integrity_review_protocol.md
Stage 2.5 + 4.5 integrity verification: 5-phase protocol details
references/two_stage_review_protocol.md
Two-stage review: Stage 3 full review + Stage 3' verification review
references/external_review_protocol.md
External (human) reviewer feedback: 4-step intake/coaching/revision/verification
references/process_summary_protocol.md
Stage 6: collaboration quality evaluation + AI self-reflection report
references/reproducibility_audit.md
Standardized workflow guarantees + audit trail format
references/progress_dashboard_template.md
ASCII progress dashboard template
references/reinforcement_content.md
Stage-specific reinforcement focus table for transitions
references/changelog.md
Full version history
shared/handoff_schemas.md
Cross-skill data contracts: 9 schemas for all inter-stage handoff artifacts
参考文件用途
references/pipeline_state_machine.md
完整状态机定义：所有合法流转、前置条件、执行动作
references/plagiarism_detection_protocol.md
D阶段原创性验证协议 + 自我剽窃 + AI文本特征识别
references/mode_advisor.md
跨技能统一决策树：将用户意图映射到最优技能+模式
references/claim_verification_protocol.md
E阶段观点声明验证协议：观点提取、来源追溯、交叉验证、结论分类
references/team_collaboration_protocol.md
多人团队协作：角色定义、流转协议、版本控制、冲突解决
references/integrity_review_protocol.md
阶段2.5 + 4.5完整性验证：5阶段协议详情
references/two_stage_review_protocol.md
两阶段评审：阶段3全量评审 + 阶段3'验证评审
references/external_review_protocol.md
外部（人类）评审意见：4步接收/指导/修改/验证流程
references/process_summary_protocol.md
阶段6：协作质量评估 + AI自反思报告
references/reproducibility_audit.md
标准化工作流保障 + 审计轨迹格式
references/progress_dashboard_template.md
ASCII进度仪表盘模板
references/reinforcement_content.md
阶段流转专属强化重点对照表
references/changelog.md
完整版本历史
shared/handoff_schemas.md
跨技能数据契约：所有阶段间流转产物的9套schema

Templates

模板

TemplatePurpose
templates/pipeline_status_template.md
Progress Dashboard output template
模板用途
templates/pipeline_status_template.md
进度仪表盘输出模板

Examples

示例

ExampleDemonstrates
examples/full_pipeline_example.md
Complete pipeline conversation log (Stage 1-5, with integrity + 2-stage review)
examples/mid_entry_example.md
Mid-entry example starting from Stage 2.5 (existing paper -> integrity check -> review -> revision -> finalization)
示例演示内容
examples/full_pipeline_example.md
完整管线对话日志（阶段1-5，包含完整性检查+两阶段评审）
examples/mid_entry_example.md
从阶段2.5开始的中途进入示例（已有论文→完整性检查→评审→修改→定稿）

Output Language

输出语言

Follows user language. Academic terminology retained in English.
跟随用户使用的语言，学术术语保留英文。

Integration with Other Skills

与其他技能的集成

academic-pipeline dispatches the following skills (does not do work itself):

Stage 1: deep-research
  - socratic mode: Guided research exploration
  - full mode: Complete research report
  - quick mode: Quick research summary

Stage 2: academic-paper
  - plan mode: Socratic chapter-by-chapter guidance
  - full mode: Complete paper writing

Stage 2.5: integrity_verification_agent (Mode 1: pre-review)
Stage 4.5: integrity_verification_agent (Mode 2: final-check)

Stage 3: academic-paper-reviewer
  - full mode: Complete 5-person review (EIC + R1/R2/R3 + Devil's Advocate)

Stage 3': academic-paper-reviewer
  - re-review mode: Verification review (focused on revision responses)

Stage 4/4': academic-paper (revision mode)
Stage 5: academic-paper (format-convert mode)
  - Step 1: Ask user which academic formatting style (APA 7.0 / Chicago / IEEE, etc.)
  - Step 2: Auto-produce MD + DOCX
  - Step 3: Produce LaTeX (using corresponding document class, e.g., apa7 class for APA 7.0)
  - Step 4: After user confirms content is correct, tectonic compiles PDF (final version)
  - Fonts: Times New Roman (English) + Source Han Serif TC VF (Chinese) + Courier New (monospace)
  - ⚠️ IRON RULE: PDF must be compiled from LaTeX (HTML-to-PDF is prohibited)
academic-pipeline dispatches the following skills (does not do work itself):

Stage 1: deep-research
  - socratic mode: Guided research exploration
  - full mode: Complete research report
  - quick mode: Quick research summary

Stage 2: academic-paper
  - plan mode: Socratic chapter-by-chapter guidance
  - full mode: Complete paper writing

Stage 2.5: integrity_verification_agent (Mode 1: pre-review)
Stage 4.5: integrity_verification_agent (Mode 2: final-check)

Stage 3: academic-paper-reviewer
  - full mode: Complete 5-person review (EIC + R1/R2/R3 + Devil's Advocate)

Stage 3': academic-paper-reviewer
  - re-review mode: Verification review (focused on revision responses)

Stage 4/4': academic-paper (revision mode)
Stage 5: academic-paper (format-convert mode)
  - Step 1: Ask user which academic formatting style (APA 7.0 / Chicago / IEEE, etc.)
  - Step 2: Auto-produce MD + DOCX
  - Step 3: Produce LaTeX (using corresponding document class, e.g., apa7 class for APA 7.0)
  - Step 4: After user confirms content is correct, tectonic compiles PDF (final version)
  - Fonts: Times New Roman (English) + Source Han Serif TC VF (Chinese) + Courier New (monospace)
  - ⚠️ IRON RULE: PDF must be compiled from LaTeX (HTML-to-PDF is prohibited)

Related Skills

相关技能

SkillRelationship
deep-research
Dispatched (Stage 1 research phase)
academic-paper
Dispatched (Stage 2 writing, Stage 4/4' revision, Stage 5 formatting)
academic-paper-reviewer
Dispatched (Stage 3 first review, Stage 3' verification review)
技能关联关系
deep-research
被调度（阶段1研究阶段）
academic-paper
被调度（阶段2写作、阶段4/4'修改、阶段5格式转换）
academic-paper-reviewer
被调度（阶段3首次评审、阶段3'验证评审）

Version Info

版本信息

ItemContent
Skill Version3.0
Last Updated2026-04-06
MaintainerCheng-I Wu
Dependent Skillsdeep-research v2.0+, academic-paper v2.0+, academic-paper-reviewer v1.1+
RoleFull academic research workflow orchestrator
项内容
技能版本3.0
最后更新2026-04-06
维护者Cheng-I Wu
依赖技能deep-research v2.0+, academic-paper v2.0+, academic-paper-reviewer v1.1+
角色全学术研究工作流编排器

Changelog

更新日志

See 
references/changelog.md
for full version history.
完整版本历史请查看 
references/changelog.md