@wentorai/research-plugins 1.2.2 → 1.3.0

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

@@ -1,231 +0,0 @@
----
-name: paper-research-assistant
-description: "Read papers, generate structured reports, find code and datasets"
-metadata:
-  openclaw:
-    emoji: "📄"
-    category: "research"
-    subcategory: "paper-review"
-    keywords: ["paper reading", "research report", "code extraction", "dataset discovery", "paper analysis", "structured summary"]
-    source: "https://github.com/AcademicSkills/paper-research-assistant"
----
-
-# Paper Research Assistant
-
-A skill for systematically reading academic papers and generating structured analysis reports. Goes beyond simple summarization by extracting methodology details, identifying associated code repositories and datasets, evaluating reproducibility, and generating actionable summaries suitable for lab meetings, journal clubs, or literature review inclusion.
-
-## Overview
-
-Reading academic papers efficiently is a core skill for researchers, yet many lack a systematic approach. The result is either superficial skimming that misses critical details or time-consuming deep reads of papers that turn out to be marginally relevant. This skill provides a structured reading protocol that adapts its depth to the paper's relevance, extracts standardized metadata, and produces reports that can be shared with collaborators or filed for future reference.
-
-A distinguishing feature is the automated search for associated resources: code repositories, datasets, pre-trained models, and supplementary materials that are often scattered across GitHub, institutional pages, and data repositories. These resources are essential for reproducibility and building upon published work.
-
-## Structured Reading Protocol
-
-### Three-Pass Reading Method
-
-```
-Pass 1: SURVEY (5-10 minutes)
-  Read: Title, abstract, introduction (last paragraph), section headings,
-        figures/tables (captions only), conclusion (first paragraph)
-  Decide: Is this paper relevant enough for a deeper read?
-  Output: One-paragraph relevance assessment
-
-Pass 2: COMPREHENSION (30-60 minutes)
-  Read: Full paper, but skip mathematical derivations and implementation details
-  Focus: What problem? What approach? What results? What limitations?
-  Mark: Key claims, novel contributions, and points of confusion
-  Output: Structured summary (see template below)
-
-Pass 3: CRITICAL ANALYSIS (30-60 minutes, only for highly relevant papers)
-  Read: Every detail including proofs, appendices, supplementary materials
-  Focus: Are the claims justified? Are there hidden assumptions?
-         Could I reproduce this? What would I do differently?
-  Output: Critical evaluation with reproducibility assessment
-```
-
-### Structured Summary Template
-
-```yaml
-paper_summary:
-  title: ""
-  authors: []
-  venue: ""  # journal/conference name
-  year: 0
-  doi: ""
-
-  classification:
-    type: ""  # empirical, theoretical, methodological, review, position
-    domain: ""
-    subdomain: ""
-
-  core_content:
-    problem: |
-      What specific problem does this paper address?
-      Why is it important?
-    approach: |
-      What method/framework/model is proposed?
-      What is novel about the approach?
-    key_results:
-      - result: ""
-        metric: ""
-        value: ""
-        baseline_comparison: ""
-    limitations:
-      - ""
-    future_work:
-      - ""
-
-  methodology:
-    data:
-      datasets_used: []
-      sample_size: ""
-      data_availability: ""  # public, restricted, proprietary
-    method:
-      type: ""  # experimental, observational, simulation, etc.
-      tools: []  # software, libraries, frameworks used
-      reproducibility_score: ""  # high, medium, low
-    evaluation:
-      metrics: []
-      baselines: []
-      statistical_tests: []
-
-  resources:
-    code_repository: ""
-    datasets: []
-    pretrained_models: []
-    supplementary_url: ""
-    demo_url: ""
-
-  assessment:
-    relevance_to_my_work: ""  # high, medium, low
-    quality_rating: ""  # 1-5 scale
-    key_takeaway: ""
-    follow_up_actions: []
-```
-
-## Code and Dataset Discovery
-
-### Finding Associated Resources
-
-```python
-def find_paper_resources(title: str, authors: list, doi: str = None) -> dict:
-    """
-    Search for code, datasets, and other resources associated with a paper.
-
-    Search locations (in priority order):
-    1. Paper itself (check "Code Availability" section)
-    2. Papers With Code (paperswithcode.com)
-    3. GitHub search (title + author name)
-    4. Author institutional pages
-    5. Zenodo / Figshare (for datasets)
-    6. Hugging Face (for models and datasets)
-    """
-    resources = {
-        'code': [],
-        'datasets': [],
-        'models': [],
-        'supplementary': []
-    }
-
-    # Strategy 1: Papers With Code
-    # Search: https://paperswithcode.com/search?q={title}
-    # Returns: code repos, datasets, benchmark results
-
-    # Strategy 2: GitHub search
-    # Query: "{title}" OR "{first_author} {key_method_term}"
-    # Filter: recently updated, has README, has stars
-
-    # Strategy 3: Zenodo/Figshare
-    # Query: DOI or title
-    # Filter: type=dataset
-
-    # Strategy 4: Hugging Face
-    # Query: paper title or model name
-    # Filter: models, datasets
-
-    # Strategy 5: Google search
-    # Query: "{title}" (code OR github OR repository)
-    # Query: "{title}" (dataset OR data OR download)
-
-    return resources
-```
-
-### Reproducibility Assessment
-
-| Factor | Score 3 (High) | Score 2 (Medium) | Score 1 (Low) |
-|--------|---------------|-----------------|--------------|
-| Code availability | Public repo with instructions | Code available on request | No code |
-| Data availability | Public dataset with DOI | Available on request | Proprietary |
-| Method description | Sufficient to reimplement | Missing some details | Vague/incomplete |
-| Hyperparameters | All reported | Key ones reported | Not reported |
-| Environment | Docker/requirements.txt | Software versions listed | Not specified |
-| Random seeds | Fixed and reported | Fixed but not reported | Not controlled |
-
-## Report Generation
-
-### Lab Meeting Presentation Format
-
-```markdown
-## [Paper Title] - [First Author] et al. ([Year])
-
-### Problem
-[2-3 sentences on the problem and why it matters]
-
-### Approach
-[3-4 sentences on the method, emphasizing what is novel]
-
-### Key Results
-- [Result 1 with specific numbers]
-- [Result 2 with specific numbers]
-- [Comparison to best baseline]
-
-### Strengths
-- [Strength 1]
-- [Strength 2]
-
-### Weaknesses / Questions
-- [Weakness 1]
-- [Question for discussion]
-
-### Relevance to Our Work
-[1-2 sentences on how this connects to the lab's research]
-
-### Resources
-- Code: [URL or "not available"]
-- Data: [URL or "not available"]
-```
-
-### Literature Review Entry Format
-
-For inclusion in a systematic literature review, generate:
-
-1. **Bibliographic entry**: Full citation in the target format (APA, Vancouver, etc.).
-2. **Data extraction row**: Structured data for the evidence synthesis table.
-3. **Quality assessment**: Score on the relevant quality assessment tool (CASP, Newcastle-Ottawa, etc.).
-4. **Synthesis note**: How this paper relates to others in the review.
-
-## Batch Processing Workflow
-
-When reading multiple papers on the same topic:
-
-1. **Triage**: Read Pass 1 for all papers. Sort by relevance.
-2. **Prioritize**: Full read (Pass 2+3) only for high-relevance papers.
-3. **Cross-reference**: After reading all papers, build a comparison matrix.
-4. **Synthesize**: Identify points of agreement, disagreement, and gaps.
-5. **File**: Store all structured summaries for future retrieval.
-
-## Best Practices
-
-- Always start with Pass 1. Do not commit to a deep read before assessing relevance.
-- Read the figures and tables early. In empirical papers, they often tell the core story.
-- Note your questions and confusions during reading. These often point to genuine gaps or weaknesses.
-- Search for code and datasets before attempting to reproduce results manually.
-- When a paper cites a finding as established, trace back to the original source and verify.
-- Keep a running log of papers read with one-sentence summaries for quick future reference.
-
-## References
-
-- Keshav, S. (2007). How to Read a Paper. *ACM SIGCOMM Computer Communication Review*, 37(3), 83-84.
-- Pautasso, M. (2013). Ten Simple Rules for Writing a Literature Review. *PLoS Computational Biology*, 9(7).
-- Raff, E. (2019). A Step Toward Quantifying Independently Reproducible Machine Learning Research. *NeurIPS 2019*.

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

@@ -1,261 +0,0 @@
----
-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/tools/code-exec/contextplus-mcp-guide/SKILL.md

@@ -1,110 +0,0 @@
----
-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/)