industrial-ai-research

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Industrial AI Research

工业AI研究

Run a lean, source-aware research workflow for Industrial AI.

为工业AI领域打造轻量、基于来源优先级的文献研究工作流。

Capability Summary

功能概述

Structured literature research for Industrial AI and automation topics
Mandatory four-question intake before any search or synthesis
Venue-aware source prioritization (arXiv, IEEE, automation venues)
Four deliverable modes: research-brief, literature-map, venue-ranked survey, research-gap memo
Contrarian synthesis pass to surface contradictions and under-explored gaps
Survey draft generation: outline-first writing with per-section evidence packs and optional LaTeX export

针对工业AI与自动化主题的结构化文献研究
在进行任何搜索或研究整合前，必须完成四个初始问题的调研
基于来源（会议/期刊）的文献优先级筛选（支持arXiv、IEEE及自动化领域专属来源）
四种交付模式：研究简报、文献图谱、来源分级调研、研究空白备忘录
反向整合环节：挖掘研究中的矛盾点与未充分探索的空白领域
调研草稿生成：先构建大纲再撰写内容，每个章节配套证据包，支持可选LaTeX导出

Triggering

触发场景

Use this skill when the user wants to:

Survey Industrial AI literature on a specific subtopic
Compare papers across venues or methods within Industrial AI
Identify research gaps in predictive maintenance, scheduling, anomaly detection, or smart manufacturing
Produce a structured research report with source-backed evidence
Draft a structured survey on an Industrial AI subtopic
Produce a survey manuscript with taxonomy, evidence packs, and section-by-section writing

当用户有以下需求时，可使用本工具：

调研工业AI特定子领域的文献内容
对比工业AI领域不同来源或不同方法的论文
识别预测性维护、调度、异常检测或智能制造领域的研究空白
生成带有来源支撑证据的结构化研究报告
撰写工业AI子领域的结构化调研草稿
生成包含分类体系、证据包及分章节内容的调研手稿

Do Not Use

禁用场景

Writing or compiling LaTeX/Typst papers (use
```
latex-paper-en
```
,
```
latex-thesis-zh
```
, or
```
typst-paper
```
). Note: survey-draft mode produces Markdown by default; for LaTeX output, it delegates final formatting to
```
latex-paper-en
```
.
Auditing paper quality or formatting (use
```
paper-audit
```
)
Systematic reviews or meta-analyses requiring IRB or clinical ethics
Topics outside the Industrial AI and automation domain
Auditing an existing paper's quality or formatting (use
```
paper-audit
```
)
Editing LaTeX/Typst source files (use the appropriate writing skill)

撰写或编译LaTeX/Typst论文（请使用
```
latex-paper-en
```
、
```
latex-thesis-zh
```
或
```
typst-paper
```
工具）。注意：调研草稿模式默认输出Markdown格式；若需要LaTeX输出，最终格式处理将委托给
```
latex-paper-en
```
。
审核论文质量或格式（请使用
```
paper-audit
```
工具）
需要IRB或临床伦理审查的系统性综述或元分析
工业AI与自动化领域以外的主题
审核现有论文的质量或格式（请使用
```
paper-audit
```
工具）
编辑LaTeX/Typst源文件（请使用对应的写作工具）

Safety Boundaries

安全边界

Never fabricate paper metadata (title, authors, venue, year, DOI)
Never present preprints as peer-reviewed publications
Never start synthesis before intake questions are answered
Never suppress contradictions or conflicting evidence
Never use Tier 4 sources (blogs, press releases) as primary evidence

不得捏造论文元数据（标题、作者、来源、年份、DOI）
不得将预印本标注为已同行评审的出版物
未完成初始问题调研前，不得开始研究整合
不得隐瞒研究中的矛盾点或冲突证据
不得将四级来源（博客、新闻稿）作为主要证据

Core Rules

核心规则

Ask the user the four intake questions (see
```
references/question-flow.md
```
) before starting any search or synthesis.
Keep the skill workflow in English only, even when the requested report language is not English.
Prefer recent arXiv plus top IEEE and automation venues over generic web articles.
Default to the last 3 years, but keep seminal older work when it is still necessary for context.
Cite every substantive claim and separate verified evidence from inference.
In survey-draft mode, complete all structure and evidence phases before generating any prose. Structure phases produce YAML/tables only.

在开始任何搜索或整合前，必须向用户询问四个初始问题（详见
```
references/question-flow.md
```
）。
即使用户要求的报告语言不是英文，本工具的工作流全程使用英文。
优先选用近期arXiv论文及顶级IEEE、自动化领域来源，而非通用网络文章。
默认时间范围为过去3年，但对于仍具有重要参考价值的经典早期研究，可纳入范围。
所有实质性结论必须标注引用来源，区分已验证证据与推论内容。
在调研草稿模式下，必须完成所有结构搭建和证据收集环节后，才能开始撰写正文内容。结构搭建阶段仅生成YAML/表格格式内容。

Intake Contract

初始调研约定

Always start by asking the four intake questions defined in

references/question-flow.md

Report language (English / Simplified Chinese / Bilingual summary)
Deliverable mode (research-brief / literature-map / venue-ranked survey / research-gap memo / survey-draft)
Time window (last 12 months / last 3 years / last 5 years / custom)
Industrial AI emphasis (predictive maintenance / intelligent scheduling / industrial anomaly detection / smart manufacturing and process optimization / CPS and edge AI / robotics crossover)

If the user does not choose, default to

last 3 years

and the subdomain implied by their prompt.

必须首先询问用户

references/question-flow.md

中定义的四个初始问题：

报告语言（英文/简体中文/双语摘要）
交付模式（研究简报/文献图谱/来源分级调研/研究空白备忘录/调研草稿）
时间范围（过去12个月/过去3年/过去5年/自定义）
工业AI重点领域（预测性维护/智能调度/工业异常检测/智能制造与流程优化/CPS与边缘AI/机器人交叉领域）

若用户未明确选择，默认时间范围为

过去3年

，重点领域为用户提问中隐含的子领域。

Required Inputs

必要输入

A concrete Industrial AI topic or question.
User choices for report language, deliverable mode, time window, and domain emphasis.
Optional preferences on peer-reviewed-only filtering, benchmarks vs deployment evidence, or desired output format.

If any intake item is missing, ask the mandatory questions from

references/question-flow.md

before you search.

具体的工业AI研究主题或问题
用户选定的报告语言、交付模式、时间范围及重点领域
可选需求：仅筛选同行评审论文、对比基准与部署证据、指定输出格式等

若任何初始调研项缺失，必须先询问

references/question-flow.md

中的必填问题，再进行搜索。

Source Strategy

来源策略

Read these files before searching:

```
references/source-priority.md
```
```
references/venue-map.md
```

Primary sources:

arXiv:
```
eess.SY
```
,
```
cs.AI
```
IEEE and automation anchors:
```
T-ASE
```
,
```
CASE
```

Supporting crossover sources:

arXiv:
```
cs.RO
```
,
```
cs.LG
```
IEEE robotics venues:
```
ICRA
```
,
```
IROS
```
,
```
RA-L
```
,
```
T-RO
```
Adjacent industrial and control venues listed in
```
references/venue-map.md
```

When the user asks for the latest work, prefer:

arXiv recent streams for rapid updates
top IEEE and automation venues for stronger publication filtering
secondary crossover venues only when they materially improve coverage

开始搜索前，请阅读以下文件：

```
references/source-priority.md
```
```
references/venue-map.md
```

主要来源：

arXiv：
```
eess.SY
```
、
```
cs.AI
```
分区
IEEE及自动化领域核心来源：
```
T-ASE
```
、
```
CASE
```

交叉领域补充来源：

arXiv：
```
cs.RO
```
、
```
cs.LG
```
分区
IEEE机器人领域来源：
```
ICRA
```
、
```
IROS
```
、
```
RA-L
```
、
```
T-RO
```
```
references/venue-map.md
```
中列出的其他工业与控制领域来源

当用户要求获取最新研究时，优先级如下：

arXiv近期论文流，获取快速更新内容
顶级IEEE及自动化领域来源，确保出版物质量
仅当能显著提升覆盖范围时，才选用二级交叉领域来源

Workflow

工作流程

Phase 1. Scope

阶段1：范围确定

Rewrite the request as a precise Industrial AI research objective.
Lock the report language, deliverable mode, time window, and domain emphasis.
State explicit in-scope and out-of-scope boundaries.

将用户请求改写为精准的工业AI研究目标
锁定报告语言、交付模式、时间范围及重点领域
明确标注研究的纳入范围与排除范围

Phase 2. Search Plan

阶段2：搜索计划

Build venue buckets and keyword groups from
```
references/source-priority.md
```
.
Separate primary sources from secondary crossover sources.
State the recency policy and any seminal-paper exceptions.

基于
```
references/source-priority.md
```
构建来源分组与关键词组
区分主要来源与交叉领域补充来源
明确时效性规则及经典论文的例外情况

Phase 3. Source Collection

阶段3：来源收集

Gather papers from the prioritized source buckets.
Prefer official venue pages, arXiv recent listings, IEEE Xplore landing pages, and publisher or conference pages.
Record why each paper was included.

从优先级来源分组中收集论文
优先选用官方来源页面、arXiv近期列表、IEEE Xplore landing pages、出版社或会议官方页面
记录每篇论文的纳入原因

Phase 4. Verification and Triage

阶段4：验证与筛选

Check venue quality, publication type, year, and relevance.
Remove weak matches, duplicates, and generic blog-style sources.
Mark unreviewed preprints as preprints.

检查来源质量、出版物类型、年份及相关性
移除匹配度低、重复及通用博客类来源
将未评审预印本明确标记为预印本

Phase 5. Synthesis

阶段5：研究整合

Cluster the shortlisted papers by problem, method, dataset, deployment setting, and evaluation style.
Surface trends, gaps, contradictions, and under-explored opportunities.
Run a contrarian pass: what would challenge the dominant conclusion?

按问题、方法、数据集、部署场景及评估方式对入围论文进行聚类
挖掘研究趋势、空白、矛盾点及未充分探索的方向
执行反向验证环节：哪些内容可以挑战主流结论？

Phase 6. Report Assembly

阶段6：报告组装

Use the stable report structure from

references/report-modes.md

Every final report must include:

search scope
source buckets by venue
shortlisted papers
synthesis of trends and gaps
recommended next reading or next experiments

使用

references/report-modes.md

中的稳定报告结构。

最终报告必须包含以下内容：

搜索范围
按来源分组的文献列表
入围论文清单
研究趋势与空白的整合分析
推荐的后续阅读内容或实验方向

Survey-Draft Workflow (Phases S1–S4)

调研草稿工作流程（阶段S1–S4）

When the user selects

survey-draft

, Phases 1–4 (Scope, Search Plan, Source Collection, Verification) execute as normal, then S1–S4 replace the original Phases 5–6.

当用户选择

调研草稿

模式时，阶段1–4（范围确定、搜索计划、来源收集、验证）正常执行，随后用S1–S4替代原阶段5–6。

Phase S1. Outline Building

阶段S1：大纲搭建

Read

references/modules/SURVEY_OUTLINE.md

Extract a taxonomy from the verified literature.
Build the section skeleton as structured YAML.
Present the outline to the user for approval.
CHECKPOINT: do not enter S2 until the user approves the outline.

阅读

references/modules/SURVEY_OUTLINE.md

。

从已验证文献中提取分类体系
以结构化YAML格式构建章节框架
将大纲提交给用户审批
检查点：获得用户批准后，才能进入阶段S2

Phase S2. Evidence Pack Assembly

阶段S2：证据包组装

Read

references/modules/SURVEY_EVIDENCE.md

Assemble an evidence pack for every H3 subsection.
Lock the citation scope for each subsection.
Produce structured evidence bundles (no prose).

阅读

references/modules/SURVEY_EVIDENCE.md

。

为每个H3子章节组装证据包
锁定每个子章节的引用范围
生成结构化证据包（不含正文内容）

Phase S3. Section-by-Section Writing

阶段S3：分章节撰写

Read

references/modules/SURVEY_WRITER.md

Draft each H3 independently, grounded in its evidence pack.
Run the self-check gate on every H3 (depth, citation scope, tone).
Produce one Markdown file per H2 section.

阅读

references/modules/SURVEY_WRITER.md

。

基于每个子章节的证据包，独立撰写H3内容
对每个H3内容执行自检（深度、引用范围、语气）
每个H2章节生成一个Markdown文件

Phase S4. Merge and Quality Gate

阶段S4：合并与质量检查

Read

references/modules/SURVEY_MERGE.md

Merge all section drafts into a single document.
Run cross-section consistency checks.
Apply the final quality checklist.
If the user requested LaTeX output, delegate to
```
latex-paper-en
```
.

阅读

references/modules/SURVEY_MERGE.md

。

将所有章节草稿合并为单个文档
执行跨章节一致性检查
应用最终质量检查表
若用户要求LaTeX输出，委托给
```
latex-paper-en
```
处理

Deliverable Modes

交付模式

Read

references/report-modes.md

and follow the selected mode exactly.

```
research-brief
```
: short, decision-ready overview
```
literature-map
```
: thematic map across methods and subproblems
```
venue-ranked survey
```
: grouped by source quality and venue tier
```
research-gap memo
```
: open problems, design space, and next-step opportunities
```
survey-draft
```
: taxonomy-driven survey manuscript with outline-first writing and optional LaTeX export

阅读

references/report-modes.md

，严格遵循选定的交付模式。

```
research-brief
```
：简洁、可直接用于决策的概述
```
literature-map
```
：按方法与子问题分类的文献图谱
```
venue-ranked survey
```
：按来源质量与层级分组的调研内容
```
research-gap memo
```
：列出开放问题、设计空间及后续研究方向的备忘录
```
survey-draft
```
：基于分类体系的调研手稿，采用先大纲后撰写的模式，支持可选LaTeX导出

Output Contract

输出约定

State the locked intake choices and any defaults you applied before synthesis.
Distinguish verified evidence from inference in every deliverable.
Label preprints explicitly as preprints.
For non-survey modes, produce a structured report that includes: scope, source buckets, shortlisted papers, synthesis, and next reading or next experiments.
For
```
survey-draft
```
, keep stage outputs format-specific:
- S1: YAML outline only
- S2: evidence packs or tables only
- S3: section Markdown drafts grounded in the evidence packs
- S4: merged Markdown survey with cross-section consistency notes
If sources are sparse, inaccessible, or off-scope, say so directly and report the exact fallback you used.

在开始整合前，明确说明已锁定的初始调研选项及默认设置
在所有交付内容中区分已验证证据与推论
明确标注预印本
非调研草稿模式下，生成包含以下内容的结构化报告：搜索范围、来源分组、入围论文、整合分析、后续推荐
调研草稿模式下，按阶段输出对应格式内容：
- S1：仅输出YAML格式大纲
- S2：仅输出证据包或表格
- S3：基于证据包的Markdown章节草稿
- S4：合并后的Markdown调研文档及跨章节一致性说明
若来源稀缺、无法访问或超出范围，需直接说明，并在最终报告中标记该缺口

Module Router

模块路由

Module	Use when	Primary action	Read next
`research`	User selects any of the 4 report modes	Execute Phase 1–6 workflow	`references/report-modes.md`
`survey-outline`	User selects survey-draft (Phase S1)	Build taxonomy and section skeleton	`references/modules/SURVEY_OUTLINE.md`
`survey-evidence`	Outline approved by user (Phase S2)	Assemble per-H3 evidence packs	`references/modules/SURVEY_EVIDENCE.md`
`survey-write`	Evidence packs complete (Phase S3)	Draft prose per H3	`references/modules/SURVEY_WRITER.md`
`survey-merge`	All sections complete (Phase S4)	Merge, quality gate, optional LaTeX handoff	`references/modules/SURVEY_MERGE.md`

模块	使用场景	核心操作	后续参考文件
`research`	用户选择任意4种报告模式	执行阶段1–6工作流	`references/report-modes.md`
`survey-outline`	用户选择调研草稿模式（阶段S1）	构建分类体系与章节框架	`references/modules/SURVEY_OUTLINE.md`
`survey-evidence`	用户批准大纲后（阶段S2）	组装每个H3子章节的证据包	`references/modules/SURVEY_EVIDENCE.md`
`survey-write`	证据包完成后（阶段S3）	分章节撰写内容	`references/modules/SURVEY_WRITER.md`
`survey-merge`	所有章节完成后（阶段S4）	合并文档、质量检查、可选LaTeX交付	`references/modules/SURVEY_MERGE.md`

Quality Bar

质量标准

Read

references/quality-checklist.md

before finalizing.

Non-negotiable standards:

no unsupported claims
no venue-blind source mixing
no hiding contradictions
no synthesized report before intake questions are answered
no generic "latest research says" language without source-backed evidence

最终定稿前，请阅读

references/quality-checklist.md

。

不可妥协的标准：

无无支撑的结论
不得混合不同层级的来源内容
不得隐瞒矛盾点
未完成初始调研前，不得生成整合报告
无来源支撑时，不得使用“最新研究表明”类通用表述

Error Handling

错误处理

Zero results: Broaden keywords, relax the time window by one tier, and try adjacent venues. If still empty, report the negative result with the exact queries attempted.
Off-subdomain topic: State that the topic falls outside Industrial AI scope, suggest the closest supported subdomain, and ask the user whether to proceed or abort.
Inaccessible databases: Note which sources were unreachable, proceed with available sources, and flag the gap in the final report.
Too few papers (<5 shortlisted): Lower the time window threshold, include Tier 2/3 venues, and explicitly note the thin evidence base in the synthesis.

无搜索结果：扩大关键词范围，将时间范围放宽一个层级，尝试相邻领域来源。若仍无结果，需报告搜索失败，并列出尝试过的具体查询词。
超出子领域的主题：说明该主题超出工业AI范围，建议最接近的支持子领域，询问用户是否继续或终止。
数据库无法访问：记录无法访问的来源，使用可用来源继续执行，并在最终报告中标记该缺口。
论文数量过少（<5篇入围）：降低时间范围阈值，纳入二级/三级来源，并在整合分析中明确说明证据基础薄弱。

Reference Map

参考文件映射

File	Phase	When to read
`references/question-flow.md`	Intake	Before asking the user any questions
`references/source-priority.md`	Search Plan	Before building venue buckets
`references/venue-map.md`	Search Plan	Before selecting specific venues
`references/report-modes.md`	Report Assembly	Before structuring the final output
`references/quality-checklist.md`	Report Assembly	Before finalizing the report
`references/modules/SURVEY_OUTLINE.md`	Survey S1	When building the survey outline
`references/modules/SURVEY_EVIDENCE.md`	Survey S2	When assembling evidence packs
`references/modules/SURVEY_WRITER.md`	Survey S3	When drafting survey sections
`references/modules/SURVEY_MERGE.md`	Survey S4	When merging and running quality gate
`references/SURVEY_WRITING_GUIDE.md`	Survey S1–S4	Survey writing philosophy reference

文件	阶段	阅读时机
`references/question-flow.md`	初始调研	询问用户任何问题前
`references/source-priority.md`	搜索计划	构建来源分组前
`references/venue-map.md`	搜索计划	选择具体来源前
`references/report-modes.md`	报告组装	构建最终输出结构前
`references/quality-checklist.md`	报告组装	最终定稿前
`references/modules/SURVEY_OUTLINE.md`	调研S1	搭建调研大纲时
`references/modules/SURVEY_EVIDENCE.md`	调研S2	组装证据包时
`references/modules/SURVEY_WRITER.md`	调研S3	撰写调研章节时
`references/modules/SURVEY_MERGE.md`	调研S4	合并文档与质量检查时
`references/SURVEY_WRITING_GUIDE.md`	调研S1–S4	调研写作理念参考

Examples

示例

```
examples/predictive-maintenance.md
```
```
examples/intelligent-scheduling.md
```

examples/industrial-anomaly-detection.md

examples/survey-predictive-maintenance.md

```
examples/predictive-maintenance.md
```
```
examples/intelligent-scheduling.md
```

examples/industrial-anomaly-detection.md

examples/survey-predictive-maintenance.md

Example Requests

示例请求

“Research recent predictive maintenance papers from the last 3 years and return a research-brief.”
“Compare industrial anomaly detection papers across arXiv and IEEE automation venues, and show contradictions in evaluation setups.”
“Draft a survey on intelligent scheduling for researchers new to the subfield, but stop after the YAML outline for approval.”
“My topic is warehouse picking robotics. If that is outside scope, tell me the closest supported Industrial AI framing and proceed only with that.”

“调研过去3年的预测性维护相关论文，返回一份研究简报。”
“对比arXiv与IEEE自动化领域的工业异常检测论文，展示评估设置中的矛盾点。”
“为刚进入该子领域的研究者撰写智能调度主题的调研草稿，但仅输出YAML大纲供审批。”
“我的研究主题是仓库拣选机器人。若该主题超出范围，请告知最接近的支持工业AI方向，仅基于该方向继续执行。”

Boundaries

功能边界

This v1 skill does not implement:

systematic review mode
meta-analysis
IRB-heavy or clinical ethics branches
standalone automation scripts

If the user needs those, state the boundary and continue with the closest supported research mode.

本v1版本工具不支持以下功能：

系统性综述模式
元分析
涉及IRB或临床伦理的研究分支
独立自动化脚本

若用户需要以上功能，需说明功能边界，并使用最接近的支持研究模式继续执行。