@wentorai/research-plugins 1.0.0 → 1.2.0

package/skills/research/paper-review/research-quality-filter/SKILL.md

@@ -0,0 +1,261 @@
+---
+name: research-quality-filter
+description: "Filter and assess research paper quality using structured criteria"
+metadata:
+  openclaw:
+    emoji: "🏷️"
+    category: "research"
+    subcategory: "paper-review"
+    keywords: ["quality assessment", "paper filtering", "evidence grading", "critical appraisal", "study quality", "screening"]
+    source: "https://github.com/AcademicSkills/research-quality-filter"
+---
+
+# Research Quality Filter
+
+A skill for systematically filtering and assessing the quality of research papers using structured appraisal criteria. Designed for researchers conducting literature reviews, systematic reviews, or evidence syntheses who need to triage large sets of candidate papers and evaluate the methodological rigor of included studies.
+
+## Overview
+
+When conducting any form of literature review, researchers face two sequential challenges: first, reducing a large set of search results to a manageable set of relevant papers (screening), and second, assessing the methodological quality of those papers to determine how much weight to give their findings (appraisal). Both tasks are time-consuming and prone to inconsistency when performed ad hoc.
+
+This skill provides structured tools for both stages. For screening, it implements a two-pass protocol (title/abstract screening followed by full-text screening) with explicit inclusion/exclusion criteria. For quality appraisal, it provides instrument-specific checklists adapted from established frameworks (CASP, Newcastle-Ottawa, JBI, GRADE) that produce numerical quality scores and standardized assessments.
+
+## Screening Protocol
+
+### Two-Pass Screening
+
+```
+Pass 1: Title and Abstract Screening
+  For each paper, apply inclusion/exclusion criteria:
+
+  INCLUDE if ALL of the following are met:
+    □ Addresses the research question (at least tangentially)
+    □ Published in a peer-reviewed venue (or recognized preprint server)
+    □ Written in an included language (typically English)
+    □ Published within the date range of interest
+    □ Reports original research OR is a systematic review
+
+  EXCLUDE if ANY of the following are met:
+    □ Clearly off-topic (different population, intervention, or outcome)
+    □ Wrong study type (e.g., editorial, letter, commentary if not included)
+    □ Duplicate of another included paper
+    □ Published in a known predatory journal
+    □ Retracted
+
+  Mark as UNCERTAIN if:
+    □ Relevance cannot be determined from title/abstract alone
+
+  Decision: INCLUDE | EXCLUDE | UNCERTAIN → move uncertain to Pass 2
+
+Pass 2: Full-Text Screening
+  Read full text of INCLUDE and UNCERTAIN papers.
+  Apply the same criteria with additional checks:
+    □ Methods are described sufficiently
+    □ Outcome of interest is actually measured/reported
+    □ Sample/population matches inclusion criteria
+```
+
+### Screening Tracker
+
+```python
+import pandas as pd
+
+def create_screening_tracker(papers: list, criteria: dict) -> pd.DataFrame:
+    """
+    Create a structured screening tracker for a set of candidate papers.
+    """
+    tracker = pd.DataFrame(papers)
+
+    # Add screening columns
+    tracker['pass1_decision'] = ''       # include / exclude / uncertain
+    tracker['pass1_reason'] = ''         # reason for exclusion
+    tracker['pass1_screener'] = ''       # who screened
+    tracker['pass2_decision'] = ''       # include / exclude (for pass2 candidates)
+    tracker['pass2_reason'] = ''
+    tracker['quality_score'] = None      # assigned after appraisal
+
+    return tracker
+
+def calculate_screening_agreement(screener_a: list, screener_b: list) -> dict:
+    """
+    Calculate inter-rater agreement for dual screening.
+    """
+    from sklearn.metrics import cohen_kappa_score
+    kappa = cohen_kappa_score(screener_a, screener_b)
+    agreement_pct = sum(a == b for a, b in zip(screener_a, screener_b)) / len(screener_a) * 100
+
+    return {
+        'cohens_kappa': round(kappa, 3),
+        'percent_agreement': round(agreement_pct, 1),
+        'interpretation': (
+            'almost perfect' if kappa > 0.81 else
+            'substantial' if kappa > 0.61 else
+            'moderate' if kappa > 0.41 else
+            'fair' if kappa > 0.21 else 'poor'
+        ),
+        'disagreements': sum(a != b for a, b in zip(screener_a, screener_b))
+    }
+```
+
+## Quality Appraisal Instruments
+
+### Selecting the Right Tool
+
+| Study Design | Appraisal Tool | Items |
+|-------------|---------------|-------|
+| Randomized controlled trial | Cochrane Risk of Bias (RoB 2) | 5 domains |
+| Cohort study | Newcastle-Ottawa Scale (NOS) | 8 items |
+| Case-control study | Newcastle-Ottawa Scale (NOS) | 8 items |
+| Cross-sectional | JBI Checklist for Analytical Cross-Sectional | 8 items |
+| Qualitative study | CASP Qualitative Checklist | 10 items |
+| Systematic review | AMSTAR 2 | 16 items |
+| Diagnostic accuracy | QUADAS-2 | 4 domains |
+| Mixed methods | MMAT | 5 criteria per component |
+
+### Generic Quality Assessment
+
+```python
+def assess_paper_quality(paper: dict, study_type: str) -> dict:
+    """
+    Apply a structured quality assessment to a research paper.
+    Returns scores on standardized criteria.
+    """
+    criteria = {
+        'research_question': {
+            'description': 'Is the research question clearly stated?',
+            'options': {'yes': 2, 'partially': 1, 'no': 0},
+            'score': None
+        },
+        'study_design': {
+            'description': 'Is the study design appropriate for the question?',
+            'options': {'yes': 2, 'partially': 1, 'no': 0},
+            'score': None
+        },
+        'sampling': {
+            'description': 'Is the sample adequate and representative?',
+            'options': {'yes': 2, 'partially': 1, 'no': 0},
+            'score': None
+        },
+        'measurement': {
+            'description': 'Are outcome measures valid and reliable?',
+            'options': {'yes': 2, 'partially': 1, 'no': 0},
+            'score': None
+        },
+        'analysis': {
+            'description': 'Is the statistical analysis appropriate?',
+            'options': {'yes': 2, 'partially': 1, 'no': 0},
+            'score': None
+        },
+        'confounding': {
+            'description': 'Are potential confounders addressed?',
+            'options': {'yes': 2, 'partially': 1, 'no': 0},
+            'score': None
+        },
+        'results_reporting': {
+            'description': 'Are results clearly and completely reported?',
+            'options': {'yes': 2, 'partially': 1, 'no': 0},
+            'score': None
+        },
+        'limitations': {
+            'description': 'Are limitations honestly discussed?',
+            'options': {'yes': 2, 'partially': 1, 'no': 0},
+            'score': None
+        }
+    }
+
+    # Calculate total score
+    max_score = len(criteria) * 2
+    total = sum(c['score'] for c in criteria.values() if c['score'] is not None)
+    pct = total / max_score * 100
+
+    quality_rating = (
+        'High' if pct >= 75 else
+        'Medium' if pct >= 50 else
+        'Low'
+    )
+
+    return {
+        'criteria': criteria,
+        'total_score': total,
+        'max_score': max_score,
+        'percentage': round(pct, 1),
+        'quality_rating': quality_rating
+    }
+```
+
+## Evidence Grading with GRADE
+
+### GRADE Framework Application
+
+The Grading of Recommendations, Assessment, Development and Evaluation (GRADE) framework rates the overall quality of evidence for each outcome:
+
+| Starting Level | Study Type | Initial Quality |
+|---------------|-----------|-----------------|
+| High | Randomized trials | +4 |
+| Low | Observational studies | +2 |
+
+**Factors that lower quality:**
+
+| Factor | When to Downgrade | Impact |
+|--------|------------------|--------|
+| Risk of bias | Serious methodological limitations | -1 or -2 |
+| Inconsistency | Unexplained heterogeneity across studies | -1 or -2 |
+| Indirectness | Population/intervention/outcome mismatch | -1 or -2 |
+| Imprecision | Wide confidence intervals, small samples | -1 or -2 |
+| Publication bias | Evidence of missing studies | -1 or -2 |
+
+**Factors that raise quality (observational studies only):**
+
+| Factor | When to Upgrade | Impact |
+|--------|----------------|--------|
+| Large effect | OR > 2 or OR < 0.5 consistently | +1 or +2 |
+| Dose-response | Clear gradient observed | +1 |
+| Confounders | Would reduce effect (strengthens finding) | +1 |
+
+### Final GRADE Ratings
+
+| Rating | Meaning |
+|--------|---------|
+| **High** | Very confident the true effect is close to the estimate |
+| **Moderate** | Moderately confident; true effect likely close to estimate |
+| **Low** | Limited confidence; true effect may differ substantially |
+| **Very Low** | Very little confidence; true effect likely substantially different |
+
+## PRISMA Flow Diagram
+
+### Tracking the Filtering Process
+
+```
+Identification:
+  Records from databases: n = ____
+  Records from other sources: n = ____
+  Total records: n = ____
+
+Screening:
+  Records after duplicates removed: n = ____
+  Records screened (title/abstract): n = ____
+  Records excluded at screening: n = ____ (reasons: ____)
+
+Eligibility:
+  Full-text articles assessed: n = ____
+  Full-text articles excluded: n = ____ (reasons: ____)
+
+Included:
+  Studies in qualitative synthesis: n = ____
+  Studies in quantitative synthesis (meta-analysis): n = ____
+```
+
+## Best Practices
+
+- Use dual screening (two independent reviewers) for systematic reviews; calculate inter-rater agreement.
+- Document exclusion reasons for every paper excluded at full-text stage.
+- Apply the same quality assessment tool consistently across all included studies.
+- Do not exclude studies based on quality alone; instead, perform sensitivity analysis with and without low-quality studies.
+- Present the PRISMA flow diagram in every systematic review to show the filtering process transparently.
+- Record screening decisions in a structured tracker, not in email threads or ad hoc notes.
+
+## References
+
+- Moher, D., et al. (2009). Preferred Reporting Items for Systematic Reviews and Meta-Analyses: The PRISMA Statement. *BMJ*, 339, b2535.
+- Schunemann, H. J., et al. (2013). GRADE Handbook. *Cochrane Collaboration*.
+- Wells, G. A., et al. (2000). The Newcastle-Ottawa Scale (NOS) for Assessing the Quality of Nonrandomised Studies. *Ottawa Hospital Research Institute*.

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

@@ -0,0 +1,275 @@
+---
+name: review-response-guide
+description: "Craft effective point-by-point reviewer response letters"
+metadata:
+  openclaw:
+    emoji: "envelope"
+    category: "research"
+    subcategory: "paper-review"
+    keywords: ["reviewer response", "response letter", "revision strategy", "author reply", "manuscript revision", "editorial decision"]
+    source: "wentor-research-plugins"
+---
+
+# Review Response Guide
+
+A skill for crafting effective, professional point-by-point response letters to peer reviewer comments. Covers response letter structure, strategies for different types of reviewer feedback, prioritization of revisions, managing conflicting reviewer opinions, and navigating the revision-resubmission cycle to maximize acceptance probability.
+
+## Response Letter Architecture
+
+### Structural Template
+
+A well-organized response letter follows a consistent structure that makes it easy for editors and reviewers to verify that all concerns have been addressed.
+
+```
+Response Letter Structure:
+
+1. COVER LETTER TO EDITOR (1 page max)
+   - Thank the editor and reviewers
+   - Summarize the 3-5 most significant changes
+   - Highlight any points where you respectfully disagree
+   - Note if conflicting reviewer requests required a judgment call
+   - State that all changes are marked in the revised manuscript
+
+2. SUMMARY OF CHANGES (optional but recommended)
+   - Bulleted list of all major changes
+   - Brief enough to read in 2 minutes
+   - Organized by theme, not by reviewer
+
+3. POINT-BY-POINT RESPONSES
+   For each reviewer, for each comment:
+
+   ---
+   REVIEWER [N], Comment [M]:
+
+   [Quote the reviewer's comment verbatim, italicized]
+
+   RESPONSE:
+   [Your substantive response]
+
+   CHANGES MADE:
+   [Exact description of what changed, with page/line numbers
+    or quoted text from the revised manuscript]
+   ---
+
+4. ADDITIONAL CHANGES (if any)
+   - Changes you made that were not requested by reviewers
+   - Example: "We also updated Figure 3 to use colorblind-
+     friendly colors throughout."
+```
+
+### Formatting Best Practices
+
+```
+Visual formatting for clarity:
+
+1. Use consistent fonts:
+   - Reviewer comments: italic
+   - Your responses: regular weight
+   - Changes made: indented or in a different color
+
+2. Numbering system:
+   - R1.1, R1.2, R1.3 for Reviewer 1's comments
+   - R2.1, R2.2 for Reviewer 2's comments
+   - Major comments first, then minor comments
+
+3. Cross-references:
+   - When one response addresses multiple comments:
+     "See our response to R1.3 above, which also addresses
+      this concern."
+   - When changes span multiple sections:
+     "See revised manuscript, pp. 8-9, paragraphs 2-3
+      (marked in blue)."
+
+4. Length calibration:
+   - Major comments: 100-300 words per response
+   - Minor comments: 20-50 words per response
+   - Total response letter: typically 5-20 pages
+   - Longer is fine if substantive; never pad with fluff
+```
+
+## Response Strategies by Comment Type
+
+### Methodological Concerns
+
+```
+When reviewers question your methodology:
+
+Scenario: "The sample size is too small for the claims made."
+
+Strong response structure:
+1. Acknowledge the concern explicitly
+2. Provide quantitative justification (power analysis)
+3. Add additional analysis if possible
+4. Acknowledge remaining limitations honestly
+
+Example:
+"We appreciate this important concern about statistical power.
+We have now added a formal power analysis (Supplementary
+Section S2) showing that our sample of N=120 provides 82%
+power to detect the medium effect size (d=0.5) that our
+hypotheses predicted, based on prior work by Chen et al.
+(2021). Our observed effects were larger than this threshold
+(d=0.72, 95% CI [0.41, 1.03]). We have also added a
+sensitivity analysis (new Table S3) confirming that results
+are robust to different analytical choices. We acknowledge
+the power limitation for detecting small effects and have
+added this to the Limitations section (p. 18, lines 4-8)."
+```
+
+### Requests for Additional Analysis
+
+```
+When reviewers ask for more analysis:
+
+If feasible - do it:
+  "We thank the reviewer for this excellent suggestion.
+   We have conducted the requested analysis and present
+   the results in new Table 4 (p. 12). The findings are
+   consistent with our main results, strengthening our
+   conclusions."
+
+If partially feasible - do what you can:
+  "We have conducted [part A] of the suggested analysis
+   (new Figure S5). Unfortunately, [part B] is not possible
+   with our current dataset because [specific reason].
+   We have added this as a direction for future research
+   (p. 19, line 12)."
+
+If not feasible - explain clearly:
+  "This analysis would require [data/resource] that is not
+   available in our study because [reason]. However, we have
+   conducted [alternative analysis] that addresses the
+   underlying concern. We also now discuss this limitation
+   explicitly (p. 17)."
+```
+
+### Contradictory Reviewer Requests
+
+```
+When Reviewer 1 and Reviewer 2 disagree:
+
+This happens frequently. The key is to:
+1. Acknowledge both perspectives
+2. Explain your reasoning transparently
+3. Ask the editor to adjudicate if needed
+
+Example:
+"Reviewer 1 suggests removing the qualitative analysis
+(R1.4), while Reviewer 2 asks us to expand it (R2.7).
+We believe the qualitative component adds important
+context to our quantitative findings, consistent with
+mixed-methods best practices (Creswell, 2018). We have
+therefore retained the qualitative analysis but tightened
+it from 4 pages to 2 pages, focusing on the most
+illustrative quotes. We respectfully ask the editor to
+advise if further adjustment is needed."
+
+In the cover letter:
+"We note a point of divergence between Reviewers 1 and 2
+regarding the qualitative analysis (R1.4 vs R2.7). We have
+described our proposed compromise in the detailed responses
+and welcome the editor's guidance on this matter."
+```
+
+## Handling Difficult Reviews
+
+### When a Reviewer Is Factually Wrong
+
+```
+Strategy: Correct respectfully, blame your own writing
+
+Never: "The reviewer is incorrect about..."
+Never: "The reviewer failed to understand..."
+Never: "As any expert in this field would know..."
+
+Instead:
+"We appreciate this comment, which indicates that our
+description of [topic] was not sufficiently clear. We have
+rewritten Section 3.2 (pp. 9-10) to clarify that [correct
+information]. The key point, which we now state explicitly
+in the second paragraph, is that [clarification]. We hope
+the revised text prevents this misunderstanding."
+
+Why this works:
+- Acknowledges the reviewer's effort
+- Takes responsibility for the miscommunication
+- Improves the paper for future readers who might have
+  the same misunderstanding
+- Corrects the record without antagonizing the reviewer
+```
+
+### When a Review Is Hostile or Unfair
+
+```
+Strategy: Maintain professionalism, address substance
+
+If a comment is dismissive without substance:
+  Reviewer: "This paper is not interesting."
+  Response: "We have revised the Introduction to more
+  clearly articulate the significance of our research
+  question and its implications for [field]. Specifically,
+  we now explain [relevance point 1], [relevance point 2],
+  and [relevance point 3] (pp. 2-3)."
+
+If a comment reveals the reviewer did not read the paper:
+  Reviewer: "The authors did not control for age."
+  Response: "We appreciate this concern. Age was included
+  as a covariate in all models, as described in Section 3.4
+  (p. 11, line 3) and reported in Table 2, Column 3. We have
+  added bold formatting to make this control variable more
+  visible in the table."
+
+If appropriate, raise concerns with the editor:
+  In the cover letter (not the response):
+  "We note that Comment R2.5 appears to request an analysis
+  that is already reported in Table 4 of our manuscript.
+  We welcome the editor's assessment of whether our response
+  adequately addresses this concern."
+```
+
+## Revision Workflow
+
+### Organizing the Revision Process
+
+```
+Step-by-step revision workflow:
+
+1. Cooling-off period (1-2 days):
+   Read reviews once, then set them aside.
+   Initial emotional reactions are normal.
+
+2. Comment triage (1 day):
+   Create a spreadsheet with columns:
+   - Reviewer, Comment number, Category, Difficulty, Action
+   Categories: major/minor, methodological/theoretical/editorial
+   Difficulty: easy/medium/hard
+
+3. Easy wins first (1-2 days):
+   Address minor comments: typos, formatting, missing references
+   These require minimal thought and build momentum
+
+4. Hard problems (1-2 weeks):
+   Address major methodological and theoretical concerns
+   Run additional analyses
+   Rewrite substantial sections
+   Consult co-authors on strategy
+
+5. Response letter drafting (2-3 days):
+   Write point-by-point responses
+   Include specific page/line numbers for all changes
+
+6. Co-author review (3-5 days):
+   All co-authors review the revised manuscript AND the
+   response letter before resubmission
+
+7. Final checks (1 day):
+   Verify all page/line numbers are correct
+   Check that tracked changes match response descriptions
+   Ensure formatting meets journal requirements
+
+Timeline: Allow 4-8 weeks for a major revision
+Deadline: Most journals give 60-90 days; request extension
+if needed (editors almost always grant it)
+```
+
+A well-crafted response letter demonstrates intellectual maturity, thoroughness, and respect for the peer review process. The strongest response letters share a common trait: they treat every reviewer comment as an opportunity to improve the paper, even when the reviewer is wrong, because the revision process ultimately serves the reader.

package/skills/tools/code-exec/contextplus-mcp-guide/SKILL.md

@@ -0,0 +1,110 @@
+---
+name: contextplus-mcp-guide
+description: "Semantic code search MCP with Tree-sitter AST and RAG"
+metadata:
+  openclaw:
+    emoji: "🌳"
+    category: "tools"
+    subcategory: "code-exec"
+    keywords: ["semantic search", "code search", "Tree-sitter", "AST", "MCP", "RAG"]
+    source: "https://github.com/ForLoopCodes/contextplus"
+---
+
+# ContextPlus MCP Guide
+
+## Overview
+
+ContextPlus is an MCP server that provides semantic code search using Tree-sitter AST parsing and RAG. It indexes codebases by extracting functions, classes, and modules as semantic units, embeds them for vector search, and serves results to any MCP-compatible LLM client. Helps AI agents understand large codebases by retrieving the most relevant code context.
+
+## Installation
+
+```bash
+npm install -g @contextplus/mcp-server
+
+# Or run directly
+npx @contextplus/mcp-server --workspace ./your-project
+```
+
+## MCP Configuration
+
+```json
+{
+  "mcpServers": {
+    "contextplus": {
+      "command": "npx",
+      "args": ["@contextplus/mcp-server",
+               "--workspace", "./project"],
+      "env": {
+        "EMBEDDING_MODEL": "all-MiniLM-L6-v2",
+        "MAX_RESULTS": "10"
+      }
+    }
+  }
+}
+```
+
+## Features
+
+```markdown
+### Semantic Understanding
+- **Tree-sitter parsing**: Extract functions, classes, types
+- **AST-aware chunking**: Split code at logical boundaries
+- **Cross-reference**: Track imports, calls, dependencies
+- **Multi-language**: Python, TypeScript, Go, Rust, Java, C++
+
+### Search Capabilities
+- Natural language code search ("find auth middleware")
+- Symbol search (function/class by name)
+- Dependency graph ("what calls this function")
+- Semantic similarity (find similar implementations)
+
+### MCP Tools Provided
+- `search_code(query)` — Semantic code search
+- `get_symbol(name)` — Get symbol definition + usages
+- `get_dependencies(file)` — File dependency graph
+- `get_context(file, line)` — Surrounding context for a location
+```
+
+## Usage Examples
+
+```markdown
+### In Claude Code / LLM Chat
+
+"Find all authentication-related functions"
+→ Returns: auth middleware, login handler, token validation
+
+"What functions call the database connection pool?"
+→ Returns: dependency graph with callers
+
+"Find code similar to this error handling pattern"
+→ Returns: semantically similar try/catch blocks
+```
+
+## Indexing Configuration
+
+```json
+{
+  "indexing": {
+    "include": ["src/**/*.ts", "lib/**/*.py"],
+    "exclude": ["node_modules", "__pycache__", ".git"],
+    "languages": ["typescript", "python"],
+    "chunk_strategy": "ast",
+    "max_chunk_tokens": 500,
+    "rebuild_on_change": true
+  }
+}
+```
+
+## Use Cases
+
+1. **Code understanding**: Navigate unfamiliar codebases
+2. **Agent context**: Provide relevant code to LLM agents
+3. **Code review**: Find related patterns and similar code
+4. **Refactoring**: Discover all usages before changing code
+5. **Documentation**: Generate docs from code structure
+
+## References
+
+- [ContextPlus GitHub](https://github.com/ForLoopCodes/contextplus)
+- [Tree-sitter](https://tree-sitter.github.io/tree-sitter/)
+- [MCP Specification](https://modelcontextprotocol.io/)