@wentorai/research-plugins 1.0.0

package/skills/research/paper-review/paper-reading-assistant/SKILL.md

@@ -0,0 +1,266 @@
+---
+name: paper-reading-assistant
+description: "AI-assisted paper reading, PDF Q&A, and summarization workflows"
+metadata:
+  openclaw:
+    emoji: "reader"
+    category: "research"
+    subcategory: "paper-review"
+    keywords: ["paper reading assistant", "PDF Q&A", "document understanding", "paper summarization"]
+    source: "wentor-research-plugins"
+---
+
+# Paper Reading Assistant
+
+Systematic workflows for reading, annotating, and extracting insights from academic papers, including AI-assisted summarization and critical analysis techniques.
+
+## The Three-Pass Reading Method
+
+Srinivasan Keshav's three-pass approach provides a structured way to read papers at increasing depth:
+
+### Pass 1: Survey (5-10 minutes)
+
+Read only:
+1. Title, abstract, and keywords
+2. Introduction (first and last paragraph only)
+3. Section headings (all of them)
+4. Conclusion
+5. Glance at figures and tables (read captions)
+6. Check the reference list for familiar papers
+
+After Pass 1, you should know:
+- **Category**: Is this an empirical study, theoretical contribution, system paper, survey?
+- **Context**: What related work does it build on?
+- **Correctness**: Do the assumptions and claims seem reasonable?
+- **Contributions**: What are the main claimed contributions?
+- **Clarity**: Is the paper well-written?
+
+**Decision**: Stop here if the paper is not relevant, or continue to Pass 2.
+
+### Pass 2: Comprehension (30-60 minutes)
+
+Read the full paper, but skip proofs and complex derivations:
+1. Examine figures and tables carefully
+2. Mark unread references for later
+3. Annotate key claims, methods, and results
+4. Try to summarize each section in one sentence
+
+After Pass 2, you should be able to:
+- Summarize the paper's main contribution to someone else
+- Identify the key evidence supporting the claims
+- List the paper's strengths and weaknesses
+
+### Pass 3: Recreation (1-4 hours)
+
+For papers you need to deeply understand:
+1. Try to mentally re-derive the key results
+2. Challenge every assumption
+3. Identify implicit assumptions not stated
+4. Think about how you would improve the work
+5. Compare the approach to alternatives
+
+## Structured Note-Taking Template
+
+Use a consistent template for every paper you read:
+
+```markdown
+# Paper Notes: [Short Title]
+
+## Metadata
+- **Title**: Full title
+- **Authors**: First Author et al. (Year)
+- **Venue**: Conference/Journal
+- **DOI/URL**: link
+- **Date read**: YYYY-MM-DD
+
+## Summary (2-3 sentences)
+What does this paper do, and what are the main findings?
+
+## Problem
+What problem does this paper address? Why is it important?
+
+## Method
+How do they approach the problem? Key technical details.
+
+## Key Results
+- Result 1: ...
+- Result 2: ...
+- Result 3: ...
+
+## Strengths
+- Strength 1: ...
+- Strength 2: ...
+
+## Weaknesses / Limitations
+- Weakness 1: ...
+- Weakness 2: ...
+
+## Questions / Things I Don't Understand
+- Question 1: ...
+
+## Relevance to My Work
+How does this connect to my research? What can I use?
+
+## Key References to Follow Up
+- [Author, Year] - Why it seems relevant
+```
+
+## AI-Assisted Paper Analysis
+
+### Summarization Prompts
+
+Use structured prompts to extract specific information from papers:
+
+```python
+# Prompt template for paper summarization
+summarize_prompt = """Read the following academic paper and provide:
+
+1. ONE-SENTENCE SUMMARY: The core contribution in a single sentence.
+
+2. KEY FINDINGS (3-5 bullet points):
+   - Finding 1 with specific numbers/results
+   - Finding 2 ...
+
+3. METHODOLOGY: Describe the approach in 2-3 sentences.
+
+4. LIMITATIONS: List 2-3 limitations acknowledged or unacknowledged.
+
+5. RELEVANCE: How does this relate to [your research topic]?
+
+Paper text:
+{paper_text}
+"""
+
+# Prompt for critical analysis
+critique_prompt = """Analyze the following paper critically:
+
+1. VALIDITY: Are the experimental design and statistical analyses sound?
+   Identify any threats to internal/external validity.
+
+2. NOVELTY: What is genuinely new? What is incremental?
+
+3. REPRODUCIBILITY: Could you replicate this study from the description given?
+   What information is missing?
+
+4. ALTERNATIVE EXPLANATIONS: Are there alternative interpretations
+   of the results that the authors do not consider?
+
+5. FOLLOW-UP QUESTIONS: What would you want to investigate next?
+
+Paper text:
+{paper_text}
+"""
+```
+
+### PDF Processing Pipeline
+
+```python
+import fitz  # PyMuPDF
+
+def extract_paper_text(pdf_path):
+    """Extract structured text from an academic paper PDF."""
+    doc = fitz.open(pdf_path)
+    sections = []
+    current_section = {"heading": "Preamble", "text": ""}
+
+    for page_num, page in enumerate(doc):
+        blocks = page.get_text("dict")["blocks"]
+        for block in blocks:
+            if "lines" not in block:
+                continue
+            for line in block["lines"]:
+                text = "".join(span["text"] for span in line["spans"])
+                font_size = max(span["size"] for span in line["spans"])
+                is_bold = any("Bold" in span.get("font", "") for span in line["spans"])
+
+                # Heuristic: detect section headings
+                if is_bold and font_size > 11 and len(text.strip()) < 80:
+                    if current_section["text"].strip():
+                        sections.append(current_section)
+                    current_section = {"heading": text.strip(), "text": ""}
+                else:
+                    current_section["text"] += text + " "
+
+    if current_section["text"].strip():
+        sections.append(current_section)
+
+    doc.close()
+    return sections
+
+# Extract and display
+sections = extract_paper_text("paper.pdf")
+for s in sections:
+    print(f"\n## {s['heading']}")
+    print(s['text'][:200] + "...")
+```
+
+### Batch Paper Processing
+
+```python
+import os
+import json
+
+def process_paper_batch(pdf_dir, output_file):
+    """Process a batch of papers and save structured notes."""
+    results = []
+
+    for filename in os.listdir(pdf_dir):
+        if not filename.endswith(".pdf"):
+            continue
+
+        pdf_path = os.path.join(pdf_dir, filename)
+        sections = extract_paper_text(pdf_path)
+
+        # Find title (usually first bold text or first line)
+        title = sections[0]["heading"] if sections else filename
+
+        # Find abstract
+        abstract = ""
+        for s in sections:
+            if "abstract" in s["heading"].lower():
+                abstract = s["text"].strip()
+                break
+
+        results.append({
+            "filename": filename,
+            "title": title,
+            "abstract": abstract,
+            "num_sections": len(sections),
+            "total_chars": sum(len(s["text"]) for s in sections)
+        })
+
+    with open(output_file, "w") as f:
+        json.dump(results, f, indent=2)
+
+    return results
+```
+
+## Annotation Tools Comparison
+
+| Tool | Platform | Highlights | PDF Annotation | AI Features | Collaboration |
+|------|----------|-----------|---------------|-------------|---------------|
+| Zotero + ZotFile | All | Reference management + PDF | Yes | No (plugins available) | Group libraries |
+| Paperpile | Web/Chrome | Google Docs integration | Yes | No | Shared folders |
+| ReadCube Papers | All | Smart citations | Yes | Recommendations | Shared libraries |
+| Semantic Reader | Web | AI-augmented reading | Yes | Inline explanations, TLDRs | No |
+| Elicit | Web | AI paper search | No | Automated extraction | Tables |
+| Scholarcy | Web | Flashcard summaries | Yes | Auto-summarization | No |
+
+## Reading Strategies by Paper Type
+
+| Paper Type | Focus On | Time Budget |
+|-----------|----------|-------------|
+| **Seminal paper** | Full three-pass reading, understand every detail | 3-4 hours |
+| **Survey/review** | Section headings, taxonomy, open questions | 1-2 hours |
+| **Methods paper** | Algorithm/procedure sections, pseudocode, evaluation | 1-2 hours |
+| **Results paper** | Figures, tables, statistical tests, effect sizes | 30-60 min |
+| **Position paper** | Arguments, assumptions, counterarguments | 30-60 min |
+| **Related work (peripheral)** | Abstract + conclusion only (Pass 1) | 5-10 min |
+
+## Building a Paper Reading Habit
+
+1. **Set a regular schedule**: Read 2-3 papers per week during dedicated time blocks.
+2. **Maintain a reading log**: Track papers read with dates, ratings, and one-line takeaways.
+3. **Use a reference manager**: Add papers to your library as you read them, with tags and notes.
+4. **Discuss papers**: Join or start a reading group; explaining papers to others deepens understanding.
+5. **Connect to your research**: End every reading session by writing one sentence about how the paper relates to your own work.

package/skills/research/paper-review/peer-review-guide/SKILL.md

@@ -0,0 +1,227 @@
+---
+name: peer-review-guide
+description: "Conduct thorough, constructive peer reviews and evaluate research papers crit..."
+metadata:
+  openclaw:
+    emoji: "detective"
+    category: "research"
+    subcategory: "paper-review"
+    keywords: ["peer review", "reviewer comments", "paper evaluation", "paper reading assistant", "manuscript assessment"]
+    source: "wentor"
+---
+
+# Peer Review Guide
+
+A skill for conducting thorough, fair, and constructive peer reviews of academic manuscripts. Covers systematic evaluation frameworks, writing effective reviewer reports, and common evaluation criteria across disciplines.
+
+## Review Process Overview
+
+### Systematic Reading Strategy
+
+```
+First Pass (30 min): Skim for overall assessment
+  - Read title, abstract, introduction, conclusion
+  - Scan figures and tables
+  - Assess: Is this paper in scope? Is the question important?
+
+Second Pass (60-90 min): Detailed critical reading
+  - Read the full paper carefully
+  - Annotate unclear points, potential errors, missing references
+  - Check methodology, statistical analyses, interpretation
+
+Third Pass (30-60 min): Constructive feedback
+  - Formulate your major and minor comments
+  - Identify strengths to highlight
+  - Draft your review report
+```
+
+## Evaluation Framework
+
+### Core Assessment Dimensions
+
+```python
+def evaluate_manuscript(assessments: dict) -> dict:
+    """
+    Structured manuscript evaluation across key dimensions.
+
+    Args:
+        assessments: Dict mapping dimension to score (1-5) and comments
+    """
+    dimensions = {
+        'novelty': {
+            'weight': 0.20,
+            'questions': [
+                'Does this paper present new findings, methods, or perspectives?',
+                'How does it advance beyond existing work?',
+                'Is the contribution incremental or substantial?'
+            ]
+        },
+        'significance': {
+            'weight': 0.20,
+            'questions': [
+                'Is the research question important to the field?',
+                'Will this work influence future research or practice?',
+                'Is the scope appropriate for this journal?'
+            ]
+        },
+        'methodology': {
+            'weight': 0.25,
+            'questions': [
+                'Is the study design appropriate for the research question?',
+                'Are methods described in sufficient detail to reproduce?',
+                'Are statistical analyses appropriate and correctly applied?',
+                'Are there threats to validity that are not addressed?'
+            ]
+        },
+        'presentation': {
+            'weight': 0.15,
+            'questions': [
+                'Is the paper clearly written and well organized?',
+                'Are figures and tables informative and properly labeled?',
+                'Is the paper an appropriate length?'
+            ]
+        },
+        'literature': {
+            'weight': 0.10,
+            'questions': [
+                'Is the related work section comprehensive?',
+                'Are key prior studies cited and discussed?',
+                'Is the paper properly positioned within the literature?'
+            ]
+        },
+        'reproducibility': {
+            'weight': 0.10,
+            'questions': [
+                'Are data and code available or described sufficiently?',
+                'Could another researcher replicate this study?',
+                'Are all materials, procedures, and analyses documented?'
+            ]
+        }
+    }
+
+    overall_score = 0
+    evaluation = {}
+    for dim, info in dimensions.items():
+        score = assessments.get(dim, {}).get('score', 3)
+        comment = assessments.get(dim, {}).get('comment', '')
+        overall_score += score * info['weight']
+        evaluation[dim] = {
+            'score': score,
+            'weight': info['weight'],
+            'weighted_score': score * info['weight'],
+            'comment': comment
+        }
+
+    evaluation['overall_score'] = round(overall_score, 2)
+    evaluation['recommendation'] = (
+        'Accept' if overall_score >= 4.0
+        else 'Minor Revision' if overall_score >= 3.5
+        else 'Major Revision' if overall_score >= 2.5
+        else 'Reject'
+    )
+
+    return evaluation
+```
+
+## Writing the Review Report
+
+### Structure Template
+
+```
+SUMMARY (2-3 sentences)
+Briefly describe what the paper does and its main contribution.
+This shows the authors you read and understood their work.
+
+STRENGTHS (3-5 bullet points)
+- Specific positive aspects
+- "The experimental design is rigorous, with appropriate controls..."
+- "The visualization in Figure 3 effectively communicates..."
+
+MAJOR COMMENTS (numbered, typically 2-5)
+Issues that must be addressed before the paper can be accepted.
+These concern correctness, validity, or significant gaps.
+
+1. [Specific concern with reference to section/page]
+   "In Section 3.2, the assumption that X holds is questionable
+    because [reason]. The authors should either provide evidence
+    for this assumption or discuss what happens if it is relaxed."
+
+2. [Another major concern]
+
+MINOR COMMENTS (numbered, typically 3-10)
+Suggestions for improvement that are not critical but would
+strengthen the paper.
+
+1. "On page 5, line 23: consider citing Smith et al. (2023)
+    who address a similar phenomenon."
+
+TYPOS AND FORMATTING (optional, brief list)
+- Page 3, line 14: "effect" should be "affect"
+- Table 2: column headers are cut off
+
+CONFIDENTIAL COMMENTS TO THE EDITOR (separate section)
+Overall assessment, conflicts of interest, ethical concerns.
+This is NOT shared with the authors.
+```
+
+### Writing Effective Comments
+
+```python
+def format_review_comment(comment_type: str, section: str,
+                           issue: str, suggestion: str) -> str:
+    """
+    Format a review comment following best practices.
+
+    Args:
+        comment_type: 'major' or 'minor'
+        section: Where in the paper (e.g., 'Section 3.2, page 7')
+        issue: What the problem is
+        suggestion: How to address it
+    """
+    return (
+        f"[{comment_type.upper()}] {section}\n"
+        f"Issue: {issue}\n"
+        f"Suggestion: {suggestion}\n"
+    )
+
+# Good review comment (specific, actionable, constructive):
+print(format_review_comment(
+    'major',
+    'Section 4.1, Table 3',
+    'The comparison with baseline methods uses different evaluation metrics '
+    '(accuracy for the proposed method, F1 for baselines), making the '
+    'comparison unfair.',
+    'Please report the same set of metrics (precision, recall, F1, accuracy) '
+    'for all methods, including the proposed approach, to enable fair comparison.'
+))
+```
+
+## Common Red Flags to Check
+
+### Statistical Issues
+- p-hacking: Multiple comparisons without correction
+- Selective reporting: Only positive results shown
+- Inappropriate tests: Parametric tests on non-normal data
+- Missing effect sizes: Only p-values reported
+- Small sample with large claims: Low power, inflated effects
+
+### Methodological Issues
+- Lack of control group or baseline
+- Data leakage in ML (test data used during training/validation)
+- Confounding variables not addressed
+- Circular reasoning in analysis
+
+### Writing Issues
+- Claims not supported by the data presented
+- Overclaiming in the title or abstract
+- Missing limitations section
+- Insufficient detail for reproducibility
+
+## Ethical Responsibilities of Reviewers
+
+- Declare conflicts of interest promptly
+- Maintain confidentiality -- do not share the manuscript or discuss it
+- Complete reviews within the agreed timeline (typically 2-4 weeks)
+- Be constructive -- the goal is to improve the paper, not to display superiority
+- Do not use ideas from the manuscript under review in your own work
+- If you suspect misconduct (fabrication, falsification, plagiarism), report to the editor confidentially

package/skills/research/paper-review/rebuttal-writing-guide/SKILL.md

@@ -0,0 +1,185 @@
+---
+name: rebuttal-writing-guide
+description: "Write effective rebuttals to reviewer comments for journal submissions"
+metadata:
+  openclaw:
+    emoji: "memo"
+    category: "research"
+    subcategory: "paper-review"
+    keywords: ["rebuttal letter", "reviewer response", "revision", "peer review", "manuscript revision", "author response"]
+    source: "wentor-research-plugins"
+---
+
+# Rebuttal Writing Guide
+
+A skill for writing effective, professional responses to reviewer comments during the peer review revision process. Covers response letter structure, strategies for addressing criticism constructively, handling unfair reviews, and organizing major revisions.
+
+## Response Letter Structure
+
+### Standard Format
+
+```
+Response Letter Template:
+
+Dear Editor and Reviewers,
+
+Thank you for your thoughtful review of our manuscript
+"[Title]" (Manuscript ID: [ID]). We appreciate the
+constructive feedback and have carefully addressed all
+comments. Below, we provide point-by-point responses.
+
+Major changes include:
+  - [Summary of change 1]
+  - [Summary of change 2]
+  - [Summary of change 3]
+
+In the revised manuscript, all changes are highlighted in blue.
+
+---
+
+RESPONSE TO REVIEWER 1
+
+Comment R1.1: [Exact quote of reviewer comment]
+
+Response: [Your response]
+
+Changes made: [Description of what was changed and where]
+
+---
+
+Comment R1.2: [Next comment]
+...
+
+RESPONSE TO REVIEWER 2
+...
+```
+
+### Formatting Best Practices
+
+```python
+def format_response(reviewer_num: int, comment_num: int,
+                    comment: str, response: str,
+                    changes: str = None) -> str:
+    """
+    Format a single reviewer response entry.
+
+    Args:
+        reviewer_num: Reviewer number (1, 2, 3...)
+        comment_num: Comment number within this reviewer
+        comment: The reviewer's original comment (verbatim)
+        response: Your response
+        changes: Description of manuscript changes made
+    """
+    entry = (
+        f"**Comment R{reviewer_num}.{comment_num}:**\n"
+        f"*{comment}*\n\n"
+        f"**Response:**\n{response}\n"
+    )
+
+    if changes:
+        entry += f"\n**Changes made:** {changes}\n"
+
+    return entry
+```
+
+## Response Strategies
+
+### Handling Different Comment Types
+
+```
+Agreement (easiest -- just do it):
+  Reviewer: "Table 2 should include confidence intervals."
+  Response: "We agree. We have added 95% confidence intervals to
+            Table 2 (see revised manuscript, p. 12)."
+
+Partial agreement (do what you can, explain what you cannot):
+  Reviewer: "The authors should include 5 additional control variables."
+  Response: "We appreciate this suggestion. We have added controls for
+            age and income, which are theoretically motivated (p. 15).
+            We could not include education, occupation, and region
+            because [specific reason]. However, we now discuss this
+            limitation in Section 5.2."
+
+Respectful disagreement (provide evidence):
+  Reviewer: "The sample is too small to draw any conclusions."
+  Response: "We understand this concern. However, our power analysis
+            (now included as Supplementary Table S1) shows that our
+            sample of N=85 provides 80% power to detect a medium
+            effect (d=0.5) at alpha=0.05. Furthermore, our primary
+            effect sizes were large (d=0.8-1.2), well above the
+            detectable threshold. We have added this justification
+            to Section 3.1 (p. 8)."
+```
+
+### Golden Rules for Rebuttals
+
+```
+DO:
+  - Thank reviewers (sincerely, not sarcastically)
+  - Address EVERY comment, even minor ones
+  - Quote the reviewer's comment verbatim before responding
+  - Be specific about what changed and where (page/section numbers)
+  - Provide evidence for disagreements (citations, analyses, data)
+  - Run additional analyses when requested if feasible
+  - Use a respectful, professional tone throughout
+  - Keep responses concise but thorough
+
+DO NOT:
+  - Ignore any comment (even if trivial)
+  - Be defensive or dismissive
+  - Argue from authority ("We are experts in this area")
+  - Lie about changes you did not actually make
+  - Attack the reviewer's competence
+  - Submit essentially the same manuscript with a new cover letter
+```
+
+## Handling Difficult Reviews
+
+### When a Reviewer Is Wrong
+
+```
+Situation: The reviewer misunderstood your method.
+Strategy: Clarify without blaming the reviewer.
+
+Bad: "The reviewer clearly did not read our paper carefully."
+
+Good: "We appreciate this comment and recognize that our
+      description of the method may not have been sufficiently
+      clear. We have rewritten Section 3.2 to clarify that
+      [explanation]. The key distinction is [point], which we
+      now make explicit on p. 10."
+```
+
+### When a Reviewer Requests Impossible Changes
+
+```
+Situation: The reviewer asks for data you do not have.
+Strategy: Acknowledge, explain constraints, offer alternatives.
+
+Response: "This is an excellent suggestion that would strengthen
+          the study. Unfortunately, our dataset does not include
+          [variable] because [reason]. As an alternative, we have
+          [what you did instead]. We have also added this as a
+          limitation and future direction (Section 5.3, p. 18)."
+```
+
+## Organizing a Major Revision
+
+### Workflow for Revision
+
+```
+1. Read ALL reviews completely before making any changes
+2. Create a spreadsheet categorizing each comment:
+   - Reviewer, comment number, category, difficulty, action
+3. Address easy changes first (typos, formatting, missing refs)
+4. Tackle substantive comments in order of importance
+5. Run any new analyses requested by reviewers
+6. Revise the manuscript with tracked changes
+7. Write the response letter point by point
+8. Have a co-author review both the response and revised manuscript
+9. Submit within the deadline (ask for extension if needed)
+```
+
+## Cover Letter for Resubmission
+
+The cover letter to the editor should briefly summarize the major changes, highlight the most significant improvements, and note any disagreements with reviewers that you would like the editor to adjudicate. Keep it to one page. The detailed point-by-point responses belong in the separate response document, not the cover letter.