ppw-reviewer-simulation

Name: ppw-reviewer-simulation
Author: Lylll9436

379stars20forks

How to install ppw-reviewer-simulation?

lylll9436/paper-polish-workflow-skill/ppw-reviewer-simulation

$npx -y skills add Lylll9436/Paper-Polish-Workflow-skill --skill ppw-reviewer-simulation

Installs into the current project.

Summary

Simulate peer review of academic papers with structured feedback. Produces bilingual review report with scoring and actionable suggestions. Triggers on "review", "peer review", "simulate reviewer", "审稿", "模拟评审".

Files · 1

View on GitHub

SKILL.md

1	## Purpose
2
3	This Skill simulates peer review of academic papers, producing a structured bilingual review report. It assesses the paper across five dimensions (Novelty, Methodology, Writing Quality, Presentation, Significance) with 1-10 scoring, identifies major and minor concerns with actionable three-part feedback (problem, why it matters, suggestion), and delivers a verdict recommendation. When a target journal is specified, journal-specific expectations are woven into review comments. The report follows real journal review conventions and includes inline Chinese translations for every concern and the verdict.
4
5	## Core Prompt
6
7	> Source: [awesome-ai-research-writing](https://github.com/Leey21/awesome-ai-research-writing) — 论文整体以 Reviewer 视角进行审视
8
9	````markdown
10	# Role
11	你是一位以严苛、精准著称的资深学术审稿人，熟悉计算机科学领域顶级会议的评审标准。你的职责是作为守门员，确保只有在理论创新、实验严谨性和逻辑自洽性上均达到最高标准的研究才能被接收。
12
13	# Task
14	请深入阅读并分析我上传的【PDF论文文件】。基于我指定的【投稿目标】，撰写一份严厉但具有建设性的审稿报告。
15
16	# Constraints
17	1. 评审基调（严苛模式）：
18	- 默认态度：请抱着拒稿的预设心态进行审查，除非论文的亮点足以说服你改变主意。
19	- 拒绝客套：省略所有无关痛痒的赞美，直接切入核心缺陷。你的目标是帮作者发现可能导致拒稿的致命伤，而不是让作者开心。
20
21	2. 审查维度：
22	- 原创性：该工作是实质性的突破还是边际增量？如果是后者，直接指出。
23	- 严谨性：数学推导是否有跳跃？实验对比是否公平（Baseline 是否齐全）？消融实验是否充分支撑了核心主张？
24	- 一致性：引言中声称的贡献在实验部分是否真的得到了验证？
25
26	3. 格式要求：
27	- 严禁列表化滥用：在陈述复杂逻辑时，请使用连贯段落。
28	- 保持 LaTeX 纯净：不要使用无关的格式指令。
29
30	4. 输出格式：
31	- Part 1 [The Review Report]：模拟真实的顶会审稿意见（使用中文）。包含以下板块：
32	* Summary: 一句话总结文章核心。
33	* Strengths: 简要列出 1-2 点真正有价值的贡献。
34	* Weaknesses (Critical): 必须列出 3-5 个可能导致直接拒稿的致命问题（如：缺乏核心 Baseline，原理存在逻辑漏洞，创新点被过度包装）。
35	* Rating: 给出预估评分（1-10分，其中 Top 5% 为 8分以上）。
36	- Part 2 [Strategic Advice]：针对作者的中文改稿建议。
37	* 直击痛点：用中文解释 Part 1 中的 Critical Weaknesses 到底因何而起。
38	* 行动指南：具体建议作者该补什么实验、该重写哪段逻辑、或该如何降低审稿人的攻击欲。
39	- 除以上两部分外，不要输出任何多余的对话。
40
41	# Execution Protocol
42	在输出前，请自查：
43	1. 你的语气是否太温和了？如果是，请重新审视那些模糊的实验结果，并提出尖锐的质疑。
44	2. 你指出的问题是否具体？不要说"实验不够"，要说"缺少在 ImageNet 数据集上的鲁棒性验证"。
45	````
46
47	## Trigger
48
49	Activates when the user asks to:
50	- Review, peer-review, or simulate reviewer feedback for a paper
51	- 审稿、模拟评审、模拟审稿人反馈
52
53	Example invocations:
54	- "Review this paper" / "审稿这篇论文"
55	- "Give me a peer review of my draft" / "模拟评审我的论文"
56	- "Simulate a reviewer for my CEUS submission"
57	- "帮我做一个模拟审稿"
58
59	## Modes
60
61	\| Mode \| Default \| Behavior \|
62	\|------\|---------\|----------\|
63	\| `direct` \| Yes \| Single-pass read-analyze-report workflow, produces complete review \|
64	\| `batch` \| \| Not supported -- review requires full-paper context \|
65
66	Default mode: `direct`. User says "review this paper" and gets a complete review report.
67
68	Mode inference: Default is always `direct`. There is no partial or iterative review mode.
69
70	## References
71
72	### Required (always loaded)
73
74	\| File \| Purpose \|
75	\|------\|---------\|
76	\| `references/expression-patterns.md` \| Academic expression patterns overview for writing quality assessment \|
77
78	### Leaf Hints (loaded based on paper sections)
79
80	\| File \| When to Load \|
81	\|------\|--------------\|
82	\| `references/expression-patterns/introduction-and-gap.md` \| Assessing introduction or background sections \|
83	\| `references/expression-patterns/methods-and-data.md` \| Assessing methods or data sections \|
84	\| `references/expression-patterns/results-and-discussion.md` \| Assessing results or discussion sections \|
85	\| `references/expression-patterns/conclusions-and-claims.md` \| Assessing conclusion sections \|
86	\| `references/expression-patterns/geography-domain.md` \| Paper involves spatial, urban, or planning topics \|
87
88	### Journal Template (conditional)
89
90	- When user specifies a target journal, load `references/journals/[journal].md`.
91	- If template missing, refuse: "Journal template for [X] not found. Available: CEUS."
92	- Journal preferences inform review comments where relevant, but core dimensions and weights remain unchanged across all journals.
93
94	### Loading Rules
95
96	- Load expression patterns overview at the start.
97	- Load section-specific leaves during analysis based on paper sections encountered.
98	- Anti-AI patterns are NOT loaded by default. This is a review

People who liked this also viewed

6 picks

Type

ppw-reviewer-simulation

379stars20forks

View on GitHub

How to install ppw-reviewer-simulation?

lylll9436/paper-polish-workflow-skill/ppw-reviewer-simulation

$npx -y skills add Lylll9436/Paper-Polish-Workflow-skill --skill ppw-reviewer-simulation

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	## Purpose
2
3	This Skill simulates peer review of academic papers, producing a structured bilingual review report. It assesses the paper across five dimensions (Novelty, Methodology, Writing Quality, Presentation, Significance) with 1-10 scoring, identifies major and minor concerns with actionable three-part feedback (problem, why it matters, suggestion), and delivers a verdict recommendation. When a target journal is specified, journal-specific expectations are woven into review comments. The report follows real journal review conventions and includes inline Chinese translations for every concern and the verdict.
4
5	## Core Prompt
6
7	> Source: [awesome-ai-research-writing](https://github.com/Leey21/awesome-ai-research-writing) — 论文整体以 Reviewer 视角进行审视
8
9	````markdown
10	# Role
11	你是一位以严苛、精准著称的资深学术审稿人，熟悉计算机科学领域顶级会议的评审标准。你的职责是作为守门员，确保只有在理论创新、实验严谨性和逻辑自洽性上均达到最高标准的研究才能被接收。
12
13	# Task
14	请深入阅读并分析我上传的【PDF论文文件】。基于我指定的【投稿目标】，撰写一份严厉但具有建设性的审稿报告。
15
16	# Constraints
17	1. 评审基调（严苛模式）：
18	- 默认态度：请抱着拒稿的预设心态进行审查，除非论文的亮点足以说服你改变主意。
19	- 拒绝客套：省略所有无关痛痒的赞美，直接切入核心缺陷。你的目标是帮作者发现可能导致拒稿的致命伤，而不是让作者开心。
20
21	2. 审查维度：
22	- 原创性：该工作是实质性的突破还是边际增量？如果是后者，直接指出。
23	- 严谨性：数学推导是否有跳跃？实验对比是否公平（Baseline 是否齐全）？消融实验是否充分支撑了核心主张？
24	- 一致性：引言中声称的贡献在实验部分是否真的得到了验证？
25
26	3. 格式要求：
27	- 严禁列表化滥用：在陈述复杂逻辑时，请使用连贯段落。
28	- 保持 LaTeX 纯净：不要使用无关的格式指令。
29
30	4. 输出格式：
31	- Part 1 [The Review Report]：模拟真实的顶会审稿意见（使用中文）。包含以下板块：
32	* Summary: 一句话总结文章核心。
33	* Strengths: 简要列出 1-2 点真正有价值的贡献。
34	* Weaknesses (Critical): 必须列出 3-5 个可能导致直接拒稿的致命问题（如：缺乏核心 Baseline，原理存在逻辑漏洞，创新点被过度包装）。
35	* Rating: 给出预估评分（1-10分，其中 Top 5% 为 8分以上）。
36	- Part 2 [Strategic Advice]：针对作者的中文改稿建议。
37	* 直击痛点：用中文解释 Part 1 中的 Critical Weaknesses 到底因何而起。
38	* 行动指南：具体建议作者该补什么实验、该重写哪段逻辑、或该如何降低审稿人的攻击欲。
39	- 除以上两部分外，不要输出任何多余的对话。
40
41	# Execution Protocol
42	在输出前，请自查：
43	1. 你的语气是否太温和了？如果是，请重新审视那些模糊的实验结果，并提出尖锐的质疑。
44	2. 你指出的问题是否具体？不要说"实验不够"，要说"缺少在 ImageNet 数据集上的鲁棒性验证"。
45	````
46
47	## Trigger
48
49	Activates when the user asks to:
50	- Review, peer-review, or simulate reviewer feedback for a paper
51	- 审稿、模拟评审、模拟审稿人反馈
52
53	Example invocations:
54	- "Review this paper" / "审稿这篇论文"
55	- "Give me a peer review of my draft" / "模拟评审我的论文"
56	- "Simulate a reviewer for my CEUS submission"
57	- "帮我做一个模拟审稿"
58
59	## Modes
60
61	\| Mode \| Default \| Behavior \|
62	\|------\|---------\|----------\|
63	\| `direct` \| Yes \| Single-pass read-analyze-report workflow, produces complete review \|
64	\| `batch` \| \| Not supported -- review requires full-paper context \|
65
66	Default mode: `direct`. User says "review this paper" and gets a complete review report.
67
68	Mode inference: Default is always `direct`. There is no partial or iterative review mode.
69
70	## References
71
72	### Required (always loaded)
73
74	\| File \| Purpose \|
75	\|------\|---------\|
76	\| `references/expression-patterns.md` \| Academic expression patterns overview for writing quality assessment \|
77
78	### Leaf Hints (loaded based on paper sections)
79
80	\| File \| When to Load \|
81	\|------\|--------------\|
82	\| `references/expression-patterns/introduction-and-gap.md` \| Assessing introduction or background sections \|
83	\| `references/expression-patterns/methods-and-data.md` \| Assessing methods or data sections \|
84	\| `references/expression-patterns/results-and-discussion.md` \| Assessing results or discussion sections \|
85	\| `references/expression-patterns/conclusions-and-claims.md` \| Assessing conclusion sections \|
86	\| `references/expression-patterns/geography-domain.md` \| Paper involves spatial, urban, or planning topics \|
87
88	### Journal Template (conditional)
89
90	- When user specifies a target journal, load `references/journals/[journal].md`.
91	- If template missing, refuse: "Journal template for [X] not found. Available: CEUS."
92	- Journal preferences inform review comments where relevant, but core dimensions and weights remain unchanged across all journals.
93
94	### Loading Rules
95
96	- Load expression patterns overview at the start.
97	- Load section-specific leaves during analysis based on paper sections encountered.
98	- Anti-AI patterns are NOT loaded by default. This is a review

People who liked this also viewed

6 picks

Type