@wentorai/research-plugins 1.0.0

package/skills/writing/composition/literature-review-writing/SKILL.md

@@ -0,0 +1,196 @@
+---
+name: literature-review-writing
+description: "Structure and write comprehensive literature reviews for any field"
+metadata:
+  openclaw:
+    emoji: "scroll"
+    category: "writing"
+    subcategory: "composition"
+    keywords: ["literature review", "systematic review", "narrative review", "synthesis", "academic writing", "review paper"]
+    source: "wentor-research-plugins"
+---
+
+# Literature Review Writing
+
+A skill for structuring, synthesizing, and writing literature reviews. Covers narrative reviews, systematic reviews, scoping reviews, and literature review sections within empirical papers. Provides frameworks for organizing sources, identifying themes, and writing with synthesis rather than summary.
+
+## Types of Literature Reviews
+
+### Choosing the Right Review Type
+
+| Type | Purpose | Search | Analysis | Length |
+|------|---------|--------|----------|--------|
+| Narrative | Broad overview of a topic | Selective | Qualitative synthesis | 5-30 pages |
+| Systematic | Answer a specific question exhaustively | Exhaustive, documented | May include meta-analysis | 10-40 pages |
+| Scoping | Map the extent of research on a topic | Broad, systematic | Charting and categorizing | 10-20 pages |
+| Integrative | Synthesize diverse methodologies | Targeted | Conceptual synthesis | 10-25 pages |
+| Umbrella | Review of systematic reviews | Focused on SRs | Synthesis of syntheses | 10-20 pages |
+
+## Organizing Your Sources
+
+### Building a Literature Matrix
+
+```python
+def create_literature_matrix(sources: list[dict]) -> dict:
+    """
+    Create a structured matrix for organizing reviewed literature.
+
+    Args:
+        sources: List of dicts with keys: author, year, title, method,
+                 sample, key_findings, themes, limitations
+    """
+    matrix = {
+        "headers": [
+            "Author (Year)", "Research Question", "Method",
+            "Sample/Data", "Key Findings", "Themes", "Limitations"
+        ],
+        "rows": [],
+        "theme_index": {}
+    }
+
+    for src in sources:
+        row = {
+            "citation": f"{src['author']} ({src['year']})",
+            "question": src.get("research_question", ""),
+            "method": src.get("method", ""),
+            "sample": src.get("sample", ""),
+            "findings": src.get("key_findings", ""),
+            "themes": src.get("themes", []),
+            "limitations": src.get("limitations", "")
+        }
+        matrix["rows"].append(row)
+
+        for theme in src.get("themes", []):
+            matrix["theme_index"].setdefault(theme, []).append(
+                row["citation"]
+            )
+
+    return matrix
+```
+
+### Thematic vs. Chronological Organization
+
+```
+Chronological (rarely ideal for reviews):
+  "In 2010, Smith found X. Then in 2012, Jones found Y.
+   In 2015, Lee found Z."
+  Problem: Reads like an annotated bibliography, not a synthesis.
+
+Thematic (recommended):
+  "Three factors have been identified as predictors of X.
+   First, [factor A] has been consistently supported (Smith, 2010;
+   Jones, 2012; Lee, 2015). Second, [factor B] shows mixed results..."
+  Advantage: Synthesizes findings around conceptual themes.
+
+Methodological (useful for systematic reviews):
+  "Studies using qualitative methods (n=12) found [pattern],
+   while quantitative studies (n=25) reported [different pattern].
+   This methodological divide suggests..."
+```
+
+## Writing with Synthesis
+
+### Summary vs. Synthesis
+
+```
+Summary (weak -- describes one paper at a time):
+  "Smith (2020) studied 200 undergraduates and found that sleep
+   quality predicted academic performance. Jones (2021) surveyed
+   150 graduate students and found a similar relationship."
+
+Synthesis (strong -- integrates multiple sources around a point):
+  "Sleep quality has been consistently linked to academic performance
+   across both undergraduate (Smith, 2020; Lee, 2019) and graduate
+   (Jones, 2021) populations, with effect sizes ranging from r=0.25
+   to r=0.42. However, this relationship may be confounded by
+   socioeconomic factors (Park, 2022), which only two studies
+   controlled for."
+```
+
+### Synthesis Sentence Starters
+
+```
+Agreement:
+  "There is broad consensus that..."
+  "Multiple studies converge on the finding that..."
+  "This finding has been replicated across [contexts]..."
+
+Disagreement:
+  "However, findings diverge regarding..."
+  "In contrast to the majority view, [author] argues..."
+  "The evidence is mixed, with some studies reporting [X] and others [Y]..."
+
+Gap identification:
+  "Notably absent from this literature is..."
+  "While [aspect] has been well studied, [gap] remains unexplored..."
+  "No studies to date have examined [specific gap]..."
+
+Transition:
+  "Taken together, these findings suggest..."
+  "Building on this body of work, recent studies have begun to..."
+  "This line of research has evolved from [earlier focus] to [current focus]..."
+```
+
+## Structuring the Review
+
+### Standard Sections
+
+```
+1. Introduction (1-2 pages)
+   - Define the topic and scope
+   - Explain why this review is needed (gap, timeliness, controversy)
+   - State the review's objectives or research questions
+
+2. Methods (for systematic/scoping reviews)
+   - Search strategy, databases, date range
+   - Inclusion/exclusion criteria
+   - Screening process (PRISMA flow diagram)
+
+3. Body: Thematic Sections (bulk of the review)
+   - Each section covers a theme, construct, or sub-question
+   - Synthesize rather than summarize
+   - Use tables to compare studies when appropriate
+
+4. Discussion / Synthesis
+   - What is the overall state of knowledge?
+   - Where do studies agree and disagree?
+   - What are the gaps?
+
+5. Conclusion / Future Directions
+   - Summarize the key takeaways
+   - Propose a research agenda addressing identified gaps
+```
+
+## Common Pitfalls
+
+### What Reviewers Look For
+
+```
+Problem: "Laundry list" structure
+  - Each paragraph describes one study in isolation
+  Fix: Group studies by theme and synthesize across them
+
+Problem: Missing recent literature
+  - Review stops at 2020 in a fast-moving field
+  Fix: Search within the last 12 months before submission
+
+Problem: Uncritical acceptance
+  - All studies treated as equally valid
+  Fix: Evaluate methodological quality and note study limitations
+
+Problem: No conceptual framework
+  - Sources listed without a guiding structure
+  Fix: Start with a framework (theoretical, conceptual, or thematic map)
+
+Problem: Omitting contradictory evidence
+  - Only citing studies that support the authors' position
+  Fix: Actively seek and discuss disconfirming evidence
+```
+
+## Tools for Literature Review Management
+
+- **Zotero + ZotFile**: Organize PDFs, tag by theme, generate bibliographies
+- **Covidence**: Systematic review screening and data extraction
+- **Rayyan**: Free AI-assisted abstract screening for systematic reviews
+- **Notion/Obsidian**: Build a literature matrix with linked notes
+- **VOSviewer**: Bibliometric visualization of citation networks and keyword clusters

package/skills/writing/composition/methods-section-guide/SKILL.md

@@ -0,0 +1,185 @@
+---
+name: methods-section-guide
+description: "Guide to writing clear and reproducible methodology sections"
+metadata:
+  openclaw:
+    emoji: "gear"
+    category: "writing"
+    subcategory: "composition"
+    keywords: ["methods writing", "methodology section", "reproducible methods"]
+    source: "wentor-research-plugins"
+---
+
+# Methods Section Writing Guide
+
+Write methodology sections that are clear, complete, and reproducible, following discipline-specific conventions and best practices.
+
+## Purpose of the Methods Section
+
+The methods section answers: "How did you do this study, and can someone else replicate it?" A well-written methods section:
+
+- Provides enough detail for replication by an independent researcher
+- Justifies why each method was chosen
+- Describes the study design, participants, materials, and procedures
+- Specifies statistical or analytical approaches
+- Addresses ethical considerations
+
+## Standard Structure
+
+The methods section typically follows this order (adapt to your discipline):
+
+| Subsection | Contents |
+|-----------|----------|
+| **Study Design** | Overall approach (experimental, observational, computational, qualitative) |
+| **Participants / Samples** | Population, sampling strategy, inclusion/exclusion criteria, sample size justification |
+| **Materials / Instruments** | Equipment, software, reagents, questionnaires, datasets |
+| **Procedure** | Step-by-step protocol, chronological order of data collection |
+| **Data Analysis** | Statistical tests, software, significance thresholds, model specifications |
+| **Ethical Considerations** | IRB approval, informed consent, data privacy |
+
+## Writing by Discipline
+
+### Experimental Sciences (Biology, Chemistry, Physics)
+
+```markdown
+## Materials and Methods
+
+### Cell Culture and Treatment
+HeLa cells (ATCC CCL-2) were maintained in DMEM (Gibco, #11965092)
+supplemented with 10% FBS (Gibco, #26140079) and 1% penicillin-
+streptomycin (Gibco, #15140122) at 37C in 5% CO2. Cells were
+seeded at 5 x 10^4 cells/well in 24-well plates and treated with
+compound X (0.1, 1, 10 uM) for 24 hours.
+
+### Western Blot Analysis
+Total protein was extracted using RIPA buffer (Thermo, #89900)
+with protease inhibitor cocktail (Roche, #04693116001). Proteins
+(30 ug/lane) were separated on 10% SDS-PAGE gels and transferred
+to PVDF membranes. Primary antibodies: anti-TargetProtein
+(Cell Signaling, #1234, 1:1000), anti-beta-actin (Sigma, #A5441,
+1:5000). Secondary antibodies: HRP-conjugated (1:10000).
+```
+
+Key conventions:
+- Include catalog numbers for all reagents
+- Specify concentrations, temperatures, durations, and instrument models
+- Reference established protocols by citation rather than rewriting them in full
+- Use past tense throughout
+
+### Computational / Machine Learning Studies
+
+```markdown
+## Methods
+
+### Dataset
+We evaluated our method on three benchmark datasets:
+- **ImageNet-1K** (Russakovsky et al., 2015): 1.28M training images,
+  50K validation images across 1,000 classes
+- **CIFAR-100** (Krizhevsky, 2009): 50K training, 10K test, 100 classes
+- **Oxford Flowers-102** (Nilsback & Zisserman, 2008): 8,189 images, 102 classes
+
+### Model Architecture
+Our model extends the Vision Transformer (ViT-B/16) with the
+following modifications:
+1. Replaced standard self-attention with linear attention (Katharopoulos et al., 2020)
+2. Added a learnable class-conditional normalization layer after each block
+3. Used patch size 16x16 with input resolution 224x224
+
+### Training Details
+| Hyperparameter | Value |
+|---------------|-------|
+| Optimizer | AdamW (beta1=0.9, beta2=0.999) |
+| Learning rate | 1e-3 with cosine decay |
+| Weight decay | 0.05 |
+| Batch size | 256 (across 4 A100 GPUs) |
+| Training epochs | 300 |
+| Warmup epochs | 10 |
+| Data augmentation | RandAugment (N=2, M=9), Mixup (alpha=0.8) |
+| Label smoothing | 0.1 |
+
+All experiments were implemented in PyTorch 2.1 and run on 4x NVIDIA A100
+80GB GPUs. Training took approximately 18 hours per run. Code is available
+at [repository URL].
+```
+
+### Social Science / Survey Research
+
+```markdown
+## Methods
+
+### Participants
+A total of 412 participants (245 female, 162 male, 5 non-binary;
+M_age = 34.2, SD = 11.8) were recruited via Prolific. Inclusion
+criteria: (a) aged 18-65, (b) fluent in English, (c) resided in
+the US. Exclusion criteria: (a) failed two or more attention checks,
+(b) completed the survey in under 3 minutes. After exclusions,
+387 participants remained (attrition: 6.1%).
+
+Sample size was determined a priori using G*Power 3.1 (Faul et al., 2007).
+For a medium effect size (f^2 = 0.15), alpha = .05, and power = .80
+in a multiple regression with 5 predictors, the required sample was 92.
+We oversampled to ensure adequate power for subgroup analyses.
+
+### Measures
+
+**Perceived Stress Scale (PSS-10)** (Cohen et al., 1983): 10 items,
+5-point Likert scale (0 = never, 4 = very often). Cronbach's alpha
+in the current sample: .87.
+
+**Big Five Inventory (BFI-10)** (Rammstedt & John, 2007): 10 items,
+5-point Likert scale. Subscale alphas ranged from .68 to .81.
+
+### Procedure
+After providing informed consent, participants completed measures in
+the following fixed order: demographics, PSS-10, BFI-10, experimental
+task, manipulation check, debriefing. Median completion time: 14 minutes.
+Participants were compensated GBP 2.50.
+
+### Ethical Approval
+This study was approved by the [University] IRB (Protocol #2024-0123).
+All participants provided informed consent.
+```
+
+## Reproducibility Checklist
+
+Use this checklist to ensure your methods section is complete:
+
+### For All Studies
+
+- [ ] Study design and rationale clearly stated
+- [ ] Sample/dataset described with inclusion/exclusion criteria
+- [ ] Sample size justified (power analysis, saturation, or convention)
+- [ ] All measures and instruments described with psychometric properties or specifications
+- [ ] Procedure described in chronological order with enough detail for replication
+- [ ] Statistical/analytical methods specified, including software and version
+- [ ] Significance level (alpha) stated
+- [ ] Missing data handling described
+- [ ] Ethical approval and consent documented
+
+### For Computational Studies
+
+- [ ] Hardware specifications (GPU model, memory, training time)
+- [ ] Software framework and version (PyTorch 2.1, TensorFlow 2.15, etc.)
+- [ ] All hyperparameters listed in a table
+- [ ] Random seed policy described
+- [ ] Code and data availability statement
+- [ ] Evaluation metrics defined precisely
+- [ ] Baseline methods described or cited
+
+## Common Pitfalls
+
+| Issue | Example | Fix |
+|-------|---------|-----|
+| Vague descriptions | "Data was analyzed statistically" | Specify exact tests: "We used a two-tailed independent samples t-test" |
+| Missing software versions | "Analysis done in R" | "Analysis conducted in R 4.3.1 using lme4 v1.1-35" |
+| No sample size justification | Just reporting N | Include power analysis or justify based on conventions |
+| Ambiguous order | Reader cannot tell what happened when | Use numbered steps or chronological narrative |
+| Results in methods | Including p-values or outcomes | Save all results for the Results section |
+| Over-referencing | Citing a protocol without summarizing key details | Provide enough detail to understand without reading the reference |
+
+## Language and Tense
+
+- Use **past tense** for what you did: "Participants completed a questionnaire..."
+- Use **present tense** for established methods: "ANOVA tests for differences between group means..."
+- Use **passive voice** when the agent is unimportant: "Samples were centrifuged at 12,000 rpm..."
+- Use **active voice** when clarity is improved: "We excluded participants who..."

package/skills/writing/composition/response-to-reviewers/SKILL.md

@@ -0,0 +1,215 @@
+---
+name: response-to-reviewers
+description: "Write effective point-by-point responses to peer reviewer comments for revisions"
+metadata:
+  openclaw:
+    emoji: "envelope"
+    category: "writing"
+    subcategory: "composition"
+    keywords: ["response to reviewers", "revision letter", "point-by-point response", "cover letter writing", "manuscript revision"]
+    source: "wentor"
+---
+
+# Response to Reviewers Guide
+
+A skill for crafting professional, thorough responses to peer reviewer comments during manuscript revision. Covers structure, tone, strategies for handling difficult comments, and templates for common revision scenarios.
+
+## Response Document Structure
+
+### Standard Format
+
+```
+Dear Editor,
+
+Thank you for the opportunity to revise our manuscript entitled "[Title]"
+(Manuscript ID: [ID]). We appreciate the constructive feedback from the
+reviewers and have carefully addressed all comments. Below, we provide
+a point-by-point response to each comment.
+
+Major changes include:
+1. [Summary of major change 1]
+2. [Summary of major change 2]
+3. [Summary of major change 3]
+
+All changes in the revised manuscript are highlighted in blue.
+
+---
+
+REVIEWER 1
+
+Comment 1.1: [Quote or paraphrase the reviewer's comment]
+
+Response: [Your response]
+[Reference to specific changes: "We have revised Section 3.2,
+paragraph 2 (lines 145-158) to address this concern."]
+
+Comment 1.2: ...
+
+---
+
+REVIEWER 2
+
+Comment 2.1: ...
+
+---
+
+We believe these revisions have substantially strengthened the manuscript
+and hope you find it suitable for publication in [Journal Name].
+
+Sincerely,
+[Authors]
+```
+
+## Response Strategy Framework
+
+```python
+def classify_reviewer_comment(comment: str) -> dict:
+    """
+    Classify a reviewer comment to determine the appropriate response strategy.
+
+    Returns strategy recommendation for each comment type.
+    """
+    strategies = {
+        'factual_error': {
+            'description': 'Reviewer points out a genuine error',
+            'strategy': 'Acknowledge, correct, and thank the reviewer',
+            'template': 'We thank the reviewer for identifying this error. '
+                       'We have corrected [specific change] in [location].',
+            'tone': 'grateful'
+        },
+        'clarification_needed': {
+            'description': 'Reviewer misunderstood due to unclear writing',
+            'strategy': 'Rewrite the unclear section; do not blame the reviewer',
+            'template': 'We appreciate this comment and recognize that our original '
+                       'wording was unclear. We have revised [section] to clarify that...',
+            'tone': 'constructive'
+        },
+        'additional_analysis': {
+            'description': 'Reviewer requests new analyses or experiments',
+            'strategy': 'Perform if feasible; explain limitations if not',
+            'template': 'We have performed the requested analysis. [Results]. '
+                       'These results are now presented in [Figure/Table X].',
+            'tone': 'responsive'
+        },
+        'methodological_concern': {
+            'description': 'Reviewer questions methodology',
+            'strategy': 'Provide justification with references; add robustness checks',
+            'template': 'This is an excellent point. Our methodological choice was based on '
+                       '[rationale + citation]. As a robustness check, we have also...',
+            'tone': 'scholarly'
+        },
+        'scope_expansion': {
+            'description': 'Reviewer asks to expand beyond paper scope',
+            'strategy': 'Acknowledge value; explain scope boundaries respectfully',
+            'template': 'We agree this is an interesting direction. However, this analysis '
+                       'is beyond the scope of the current study because [reason]. '
+                       'We have added this as a direction for future research in the Discussion.',
+            'tone': 'respectful_boundary'
+        },
+        'disagreement': {
+            'description': 'You disagree with the reviewer substantively',
+            'strategy': 'Present evidence-based counter-argument respectfully',
+            'template': 'We appreciate this perspective. After careful consideration, '
+                       'we respectfully maintain our original interpretation because [evidence]. '
+                       'However, we have added a discussion of this alternative view in [section].',
+            'tone': 'diplomatic'
+        }
+    }
+
+    # Simple keyword-based classification
+    comment_lower = comment.lower()
+    if any(w in comment_lower for w in ['error', 'mistake', 'incorrect', 'wrong']):
+        return strategies['factual_error']
+    elif any(w in comment_lower for w in ['unclear', 'confusing', 'what do you mean']):
+        return strategies['clarification_needed']
+    elif any(w in comment_lower for w in ['additional', 'also analyze', 'please include']):
+        return strategies['additional_analysis']
+    elif any(w in comment_lower for w in ['method', 'approach', 'why did you']):
+        return strategies['methodological_concern']
+    elif any(w in comment_lower for w in ['beyond', 'also consider', 'broader']):
+        return strategies['scope_expansion']
+    else:
+        return strategies['clarification_needed']  # default safe strategy
+```
+
+## Handling Difficult Situations
+
+### When You Disagree with a Reviewer
+
+Never dismiss a reviewer's concern outright. The formula:
+
+```
+1. Acknowledge the reviewer's point
+   "We appreciate this thoughtful observation."
+
+2. Present your reasoning with evidence
+   "Our approach is supported by [Author, Year] who demonstrated..."
+
+3. Show you have considered the alternative
+   "We have added a paragraph discussing this alternative interpretation
+    (Section 4.3, lines 312-325)."
+
+4. Offer a compromise when possible
+   "As a compromise, we have added a sensitivity analysis using the
+    reviewer's suggested approach, which yields consistent results
+    (Supplementary Table S3)."
+```
+
+### When a Requested Analysis is Infeasible
+
+```
+Structure:
+1. Explain why it cannot be done
+   "Unfortunately, [specific reason] prevents us from performing this
+    analysis. [Data was not collected / sample size is insufficient /
+    IRB protocol does not cover this]."
+
+2. Offer the closest feasible alternative
+   "As an alternative, we have conducted [alternative analysis],
+    which addresses the same underlying concern."
+
+3. Acknowledge the limitation
+   "We have added this as a limitation in Section 5.2."
+```
+
+## Cover Letter for Revision
+
+```python
+def generate_cover_letter(journal: str, manuscript_id: str, title: str,
+                           major_changes: list[str],
+                           editor_name: str = "Editor") -> str:
+    """Generate a revision cover letter template."""
+    changes_list = '\n'.join(f'  {i+1}. {c}' for i, c in enumerate(major_changes))
+
+    return f"""Dear {editor_name},
+
+We are pleased to submit our revised manuscript entitled "{title}"
+(Manuscript ID: {manuscript_id}) for consideration in {journal}.
+
+We thank you and the reviewers for the constructive and insightful
+comments, which have significantly improved the quality of our work.
+We have carefully addressed all reviewer comments in the attached
+point-by-point response document.
+
+The major revisions include:
+{changes_list}
+
+All changes are highlighted in blue in the revised manuscript.
+A clean version is also provided.
+
+We believe the revised manuscript now fully addresses the reviewers'
+concerns and is suitable for publication in {journal}.
+
+Sincerely,
+[Corresponding Author Name]
+[Affiliation]
+[Email]"""
+```
+
+## Revision Tracking Best Practices
+
+- Use track changes or highlight all modified text in the revised manuscript
+- Provide both a marked-up version and a clean version
+- Reference specific line numbers, figure numbers, or section numbers
+- If the revision substantially changes a figure or table, include the old and new versions side by side in the response document
+- Submit the revision within the editor's requested timeline (typically 30-90 days)