@wentorai/research-plugins 1.0.0

package/skills/research/methodology/mixed-methods-guide/SKILL.md

@@ -0,0 +1,208 @@
+---
+name: mixed-methods-guide
+description: "Guide to designing and conducting mixed methods research"
+metadata:
+  openclaw:
+    emoji: "blend"
+    category: "research"
+    subcategory: "methodology"
+    keywords: ["mixed methods research", "multimethod design", "quantitative research design"]
+    source: "wentor-research-plugins"
+---
+
+# Mixed Methods Research Guide
+
+Design, execute, and report mixed methods research that integrates quantitative and qualitative approaches for more comprehensive and rigorous findings.
+
+## What Is Mixed Methods Research?
+
+Mixed methods research (MMR) systematically combines quantitative and qualitative data collection, analysis, and interpretation within a single study or program of inquiry. It goes beyond simply using both numbers and words; the core requirement is purposeful integration of the two strands.
+
+### When to Use Mixed Methods
+
+| Situation | Why MMR Helps |
+|-----------|--------------|
+| Quantitative results need explanation | Qualitative follow-up explains why and how |
+| Need to develop an instrument | Qualitative exploration informs survey items |
+| Testing a new intervention | Quantitative outcomes + qualitative experience |
+| Complex phenomena | Neither approach alone captures the full picture |
+| Conflicting prior findings | Triangulation resolves discrepancies |
+| Studying under-researched topics | Exploration (qual) then confirmation (quant) |
+
+## Major Mixed Methods Designs
+
+### Convergent Design (Concurrent)
+
+Both strands are collected simultaneously, analyzed separately, then merged.
+
+```
+    QUAN data collection          QUAL data collection
+           |                              |
+    QUAN data analysis            QUAL data analysis
+           |                              |
+           +---------- Merge ------------+
+                         |
+                  Interpretation
+```
+
+**Use when**: You want to compare, validate, or triangulate quantitative and qualitative findings on the same phenomenon.
+
+**Example**: Survey 500 teachers on burnout (QUAN) while simultaneously interviewing 20 teachers about their experiences (QUAL). Merge findings to see if themes align with statistical patterns.
+
+### Explanatory Sequential Design
+
+Quantitative phase first, followed by qualitative phase to explain or elaborate on quantitative results.
+
+```
+    QUAN data collection & analysis
+                |
+    Identify results needing explanation
+                |
+    QUAL data collection & analysis (informed by QUAN results)
+                |
+           Interpretation
+```
+
+**Use when**: You have surprising, confusing, or significant quantitative results that need deeper understanding.
+
+**Example**: Find that 30% of participants show an unexpected improvement pattern. Interview those participants to understand what drove their experience.
+
+### Exploratory Sequential Design
+
+Qualitative phase first to explore, followed by quantitative phase to test or generalize.
+
+```
+    QUAL data collection & analysis
+                |
+    Develop instrument / hypotheses / categories from QUAL findings
+                |
+    QUAN data collection & analysis (testing QUAL-derived constructs)
+                |
+           Interpretation
+```
+
+**Use when**: You are studying something new and need qualitative exploration to develop measurement instruments or hypotheses.
+
+**Example**: Interview 25 researchers about AI tool adoption (QUAL). Use themes to develop a survey instrument. Administer survey to 400 researchers (QUAN).
+
+### Embedded Design
+
+One strand is embedded within the other, serving a supplementary role.
+
+```
+    QUAN experiment
+        |-- Embedded QUAL (interviews during intervention)
+        |-- QUAN outcome measures
+           |
+       Interpretation
+```
+
+## Integration Strategies
+
+Integration is what distinguishes mixed methods from simply running two separate studies. Key integration strategies:
+
+| Strategy | Description | When in Study |
+|----------|-------------|--------------|
+| **Merging** | Bring QUAN + QUAL results together for comparison | Analysis/interpretation |
+| **Connecting** | One strand's results inform the next strand's design | Between phases |
+| **Building** | QUAL results build a QUAN instrument (or vice versa) | Between phases |
+| **Embedding** | One strand is nested within the other's framework | Data collection |
+
+### Joint Display Table
+
+A joint display is a table or visualization that explicitly integrates both data types:
+
+```
+| Quantitative Finding | Qualitative Theme | Meta-Inference |
+|---------------------|-------------------|----------------|
+| 78% reported high stress (M=4.2/5) | Theme: "Always-on culture" — participants described checking email at midnight | Convergent: high stress scores align with descriptions of boundary erosion |
+| No significant gender difference (p=.34) | Women described unique stressors (caregiving + work), men described different ones (promotion pressure) | Divergent: similar overall levels but different sources of stress |
+| Time-management training reduced stress (d=0.45) | Theme: "Tools help but culture doesn't change" | Complementary: training has modest measurable effect but underlying issues persist |
+```
+
+## Sample Size Considerations
+
+| Strand | Typical Range | Rationale |
+|--------|---------------|-----------|
+| Quantitative (survey) | 100-1000+ | Power analysis, see power-analysis-guide |
+| Qualitative (interviews) | 12-30 | Saturation (no new themes emerging) |
+| Qualitative (focus groups) | 3-6 groups of 6-10 | Diversity of perspectives |
+| Qualitative (case study) | 3-10 cases | In-depth understanding |
+
+**For convergent designs**: The QUAN sample is typically much larger than the QUAL sample. This is acceptable because the two strands serve different purposes (generalizability vs. depth).
+
+## Data Analysis
+
+### Quantitative Analysis
+
+Standard statistical methods apply: descriptive statistics, t-tests, ANOVA, regression, SEM, etc. See the relevant analysis skill guides.
+
+### Qualitative Analysis
+
+Common approaches:
+
+```
+1. Thematic Analysis (Braun & Clarke, 2006)
+   Step 1: Familiarize with data (read transcripts multiple times)
+   Step 2: Generate initial codes
+   Step 3: Search for themes (group codes into higher-level themes)
+   Step 4: Review themes (check against data)
+   Step 5: Define and name themes
+   Step 6: Write up findings
+
+2. Coding Process:
+   - Open coding: label meaningful segments of text
+   - Axial coding: identify relationships between codes
+   - Selective coding: identify core categories
+
+3. Tools: NVivo, ATLAS.ti, MAXQDA, Dedoose, or manual coding in spreadsheets
+```
+
+### Integration Analysis
+
+```python
+# Example: Quantifying qualitative themes for integration
+import pandas as pd
+
+# After coding interviews, create a themes-by-participant matrix
+themes_matrix = pd.DataFrame({
+    "participant": ["P01", "P02", "P03", "P04", "P05"],
+    "high_stress": [1, 1, 0, 1, 1],      # 1 = theme present
+    "boundary_erosion": [1, 0, 0, 1, 1],
+    "coping_strategy": [0, 1, 1, 1, 0],
+    "quant_stress_score": [4.5, 3.8, 2.1, 4.2, 4.0]
+})
+
+# Now examine whether theme presence correlates with quantitative scores
+from scipy.stats import pointbiserialr
+
+r, p = pointbiserialr(themes_matrix["high_stress"],
+                       themes_matrix["quant_stress_score"])
+print(f"Correlation between stress theme and score: r={r:.3f}, p={p:.3f}")
+```
+
+## Reporting Mixed Methods Research
+
+### Essential Components
+
+1. **Research questions**: State both QUAN and QUAL questions plus the mixed methods question
+2. **Design rationale**: Explain why mixed methods is needed
+3. **Design type**: Name the specific design (convergent, explanatory sequential, etc.)
+4. **Strand descriptions**: Describe each strand's methods in detail
+5. **Integration procedure**: Explain how and when data are integrated
+6. **Joint display**: Present integrated findings in a table or figure
+7. **Meta-inferences**: Draw conclusions that leverage both data types
+
+### Quality Criteria
+
+| Criterion | Quantitative | Qualitative | Mixed Methods |
+|-----------|-------------|-------------|---------------|
+| Validity | Internal, external, construct, statistical conclusion | Credibility, transferability, dependability, confirmability | Inference quality, inference transferability |
+| Reliability | Cronbach's alpha, test-retest | Intercoder agreement, audit trail | Integration consistency |
+| Rigor | Randomization, control, blinding | Prolonged engagement, member checking, triangulation | Design coherence, integrative adequacy |
+
+### Recommended Reporting Guidelines
+
+- **APA JARS-Mixed** (Journal Article Reporting Standards for Mixed Methods)
+- **O'Cathain et al. (2008)** Good Reporting of a Mixed Methods Study (GRAMMS)
+- **Creswell & Plano Clark (2018)** Designing and Conducting Mixed Methods Research, 3rd Edition (the standard textbook)

package/skills/research/methodology/qualitative-research-guide/SKILL.md

@@ -0,0 +1,234 @@
+---
+name: qualitative-research-guide
+description: "Design and conduct qualitative research using grounded theory, case studies, ..."
+metadata:
+  openclaw:
+    emoji: "mag"
+    category: "research"
+    subcategory: "methodology"
+    keywords: ["qualitative research design", "case study", "grounded theory", "phenomenology", "thematic analysis"]
+    source: "wentor"
+---
+
+# Qualitative Research Guide
+
+A skill for designing and conducting rigorous qualitative research. Covers major qualitative traditions, data collection methods, coding and analysis techniques, and quality criteria for trustworthy qualitative findings.
+
+## Major Qualitative Traditions
+
+### Choosing an Approach
+
+| Approach | Research Question Type | Unit of Analysis | Sample Size | Output |
+|----------|----------------------|-----------------|-------------|--------|
+| Grounded Theory | How does a process work? | Process/action | 20-60 | Theory |
+| Phenomenology | What is the lived experience? | Experience | 5-25 | Essence description |
+| Case Study | How/why does this case work? | Bounded system | 1-5 cases | Case description |
+| Ethnography | How does this culture work? | Cultural group | Extended fieldwork | Cultural portrait |
+| Narrative | What is this person's story? | Individual life | 1-5 | Narrative account |
+| Thematic Analysis | What patterns exist in this data? | Themes across data | Variable | Theme map |
+
+### Grounded Theory Process
+
+```
+Data Collection (interviews, observations)
+       |
+       v
+Open Coding: Line-by-line coding of raw data
+       |
+       v
+Axial Coding: Grouping codes into categories,
+              identifying relationships
+       |
+       v
+Selective Coding: Identifying the core category
+                  that integrates all others
+       |
+       v
+Theoretical Saturation: Stop when new data
+                        no longer generates new codes
+       |
+       v
+Substantive Theory: A grounded explanation of the phenomenon
+```
+
+## Interview Design
+
+### Semi-Structured Interview Protocol
+
+```python
+def create_interview_protocol(research_questions: list[str],
+                                n_questions: int = 10) -> dict:
+    """
+    Generate a semi-structured interview protocol template.
+
+    Args:
+        research_questions: The study's research questions
+        n_questions: Target number of interview questions
+    """
+    protocol = {
+        'opening': {
+            'rapport_building': [
+                "Thank you for participating. Before we begin, could you "
+                "tell me a little about yourself and your background?",
+                "How did you first become involved in [topic]?"
+            ],
+            'time_estimate': '60-90 minutes'
+        },
+        'main_questions': [],
+        'closing': {
+            'wrap_up': [
+                "Is there anything else you would like to share that we "
+                "have not covered?",
+                "Looking back, what stands out most to you about [topic]?",
+                "Do you have any questions for me?"
+            ]
+        },
+        'guidelines': [
+            'Ask open-ended questions (how, what, tell me about)',
+            'Avoid leading questions',
+            'Use probes: "Can you give me an example?"',
+            'Use follow-ups: "You mentioned X, tell me more about that"',
+            'Allow silences -- do not rush to fill pauses',
+            'Record field notes immediately after each interview'
+        ]
+    }
+
+    # Generate question structure
+    for i, rq in enumerate(research_questions):
+        protocol['main_questions'].append({
+            'research_question': rq,
+            'interview_questions': [
+                f'Grand tour question for RQ{i+1}',
+                f'Follow-up probe for RQ{i+1}',
+                f'Example-seeking probe for RQ{i+1}'
+            ]
+        })
+
+    return protocol
+```
+
+### Sampling Strategies
+
+| Strategy | Description | When to Use |
+|----------|------------|------------|
+| Purposive | Select information-rich cases | Most qualitative studies |
+| Maximum variation | Select cases that differ on key dimensions | Capture range of experiences |
+| Snowball | Participants refer others | Hard-to-reach populations |
+| Theoretical | Driven by emerging theory | Grounded theory studies |
+| Critical case | Select cases that are pivotal | Testing theoretical propositions |
+| Convenience | Readily available participants | Pilot studies only |
+
+## Coding and Analysis
+
+### Thematic Analysis (Braun & Clarke, 2006)
+
+```python
+def thematic_analysis_workflow(transcripts: list[str]) -> dict:
+    """
+    Outline the six phases of reflexive thematic analysis.
+    """
+    phases = {
+        'phase_1_familiarization': {
+            'actions': [
+                'Read and re-read all transcripts',
+                'Note initial impressions in a research journal',
+                'Transcribe recordings if not already done'
+            ],
+            'output': 'Familiarity with data, initial notes'
+        },
+        'phase_2_coding': {
+            'actions': [
+                'Code every data segment systematically',
+                'Use open coding (inductive) or deductive codes from framework',
+                'Code inclusively -- same segment can have multiple codes',
+                'Maintain a codebook with definitions and examples'
+            ],
+            'output': 'Coded dataset, codebook'
+        },
+        'phase_3_generating_themes': {
+            'actions': [
+                'Collate codes into potential themes',
+                'Create a thematic map showing relationships',
+                'Distinguish between semantic and latent themes'
+            ],
+            'output': 'Candidate themes and sub-themes'
+        },
+        'phase_4_reviewing_themes': {
+            'actions': [
+                'Check themes against coded extracts',
+                'Check themes against entire dataset',
+                'Merge, split, or discard themes as needed'
+            ],
+            'output': 'Refined thematic map'
+        },
+        'phase_5_defining_themes': {
+            'actions': [
+                'Write a detailed description of each theme',
+                'Identify the essence of each theme',
+                'Name themes concisely and informatively'
+            ],
+            'output': 'Theme definitions and names'
+        },
+        'phase_6_writing_up': {
+            'actions': [
+                'Weave together analytic narrative and data extracts',
+                'Select vivid, compelling quotes for each theme',
+                'Connect themes to research questions and literature'
+            ],
+            'output': 'Final analysis write-up'
+        }
+    }
+
+    return {
+        'phases': phases,
+        'n_transcripts': len(transcripts),
+        'estimated_time': f'{len(transcripts) * 4}-{len(transcripts) * 8} hours'
+    }
+```
+
+### Codebook Structure
+
+```yaml
+codebook:
+  - code: "ADAPT"
+    definition: "Participant describes adapting their behavior in response to a challenge"
+    inclusion_criteria: "Explicit mention of changing approach or strategy"
+    exclusion_criteria: "Passive acceptance without behavioral change"
+    example_quote: "I started doing things differently after that..."
+    theme: "Resilience Strategies"
+
+  - code: "BARR"
+    definition: "Participant identifies a barrier or obstacle"
+    inclusion_criteria: "Something that prevented or hindered progress"
+    exclusion_criteria: "General complaints without specific barrier"
+    example_quote: "The main thing holding me back was..."
+    theme: "Challenges"
+```
+
+## Quality Criteria
+
+### Trustworthiness (Lincoln & Guba, 1985)
+
+| Criterion | Quantitative Equivalent | Strategies |
+|-----------|------------------------|-----------|
+| Credibility | Internal validity | Member checking, triangulation, prolonged engagement |
+| Transferability | External validity | Thick description, purposive sampling |
+| Dependability | Reliability | Audit trail, peer debriefing |
+| Confirmability | Objectivity | Reflexivity journal, negative case analysis |
+
+### Inter-Coder Reliability
+
+For team-based coding, calculate Cohen's kappa or percent agreement on a subset of data (at least 10-20% of the corpus). Aim for kappa > 0.70 before independent coding proceeds.
+
+## Software Tools
+
+- **NVivo**: Full-featured qualitative analysis (commercial)
+- **ATLAS.ti**: Comprehensive coding and analysis (commercial)
+- **MAXQDA**: Mixed-methods capable (commercial)
+- **Dedoose**: Cloud-based, collaborative (subscription)
+- **Taguette**: Free, open-source qualitative coding
+- **QualCoder**: Free, open-source Python-based tool
+
+## Reporting Standards
+
+Follow the COREQ (Consolidated Criteria for Reporting Qualitative Research) checklist: report researcher positionality, sampling strategy, data collection methods, analysis approach, and provide sufficient quotations to evidence each theme.

package/skills/research/methodology/scientify-idea-generation/SKILL.md

@@ -0,0 +1,222 @@
+---
+name: scientify-idea-generation
+description: "Generate research ideas from collected papers with gap analysis"
+metadata:
+  openclaw:
+    emoji: "💡"
+    category: "research"
+    subcategory: "methodology"
+    keywords: ["research question formulation", "hypothesis formulation", "research hypothesis", "conceptual model", "theoretical framework"]
+    source: "https://github.com/scientify-ai/skills"
+    requires:
+      bins: ["git"]
+---
+
+# Idea Generation
+
+**Don't ask permission. Just do it.**
+
+Generate innovative research ideas grounded in literature analysis. This skill reads existing papers, identifies research gaps, and produces 5 distinct ideas with citations.
+
+**Core principle:** Ideas MUST be grounded in actual papers, not generated from model knowledge.
+
+**Workspace:** See `../_shared/workspace-spec.md` for directory structure. Outputs go to `$WORKSPACE/ideas/`.
+
+## Step 1: Check Workspace Resources
+
+First, check what resources already exist:
+
+```bash
+# Check active project
+cat ~/.openclaw/workspace/projects/.active 2>/dev/null
+
+# Check papers
+ls ~/.openclaw/workspace/projects/*/papers/ 2>/dev/null | head -20
+
+# Check survey results
+cat ~/.openclaw/workspace/projects/*/survey/clusters.json 2>/dev/null | head -5
+```
+
+### Assess Available Resources
+
+| Resource | Location | Status |
+|----------|----------|--------|
+| Papers | `$WORKSPACE/papers/` | Count: ? |
+| Survey clusters | `$WORKSPACE/survey/clusters.json` | Exists: Y/N |
+| Repos | `$WORKSPACE/repos/` | Count: ? |
+
+## Step 2: Ask User About Search Strategy
+
+Based on workspace state, ask user:
+
+**If papers exist (>=5):**
+> Found {N} papers in workspace from previous survey.
+>
+> Options:
+> 1. **Use existing papers** - Generate ideas from current collection
+> 2. **Search more** - Run `/literature-survey` to expand collection
+> 3. **Quick search** - Add 5-10 more papers on specific topic
+
+**If no papers:**
+> No papers found in workspace.
+>
+> To generate grounded ideas, I need literature. Options:
+> 1. **Run /literature-survey** - Comprehensive search (100+ papers, recommended)
+> 2. **Quick search** - Fetch 10-15 papers on your topic now
+> 3. **You provide papers** - Point me to existing PDFs/tex files
+
+## Step 3: Acquire Resources (if needed)
+
+### Option A: Delegate to /literature-survey (Recommended)
+
+If user wants comprehensive search:
+```
+Please run: /literature-survey {topic}
+
+This will:
+- Search 100+ papers systematically
+- Filter by relevance (score >=4)
+- Cluster into research directions
+- Save to $WORKSPACE/papers/
+
+After survey completes, run /idea-generation again.
+```
+
+### Option B: Quick Search (5-10 papers)
+
+For fast iteration, do minimal search:
+
+1. **ArXiv search:**
+```
+Tool: arxiv_search
+Arguments:
+  query: "{user_topic}"
+  max_results: 10
+```
+
+2. **Clone 3-5 reference repos:**
+```bash
+mkdir -p $WORKSPACE/repos
+git clone --depth 1 {repo_url} $WORKSPACE/repos/{name}
+```
+
+3. **Download paper sources:**
+```bash
+mkdir -p $WORKSPACE/papers/{arxiv_id}
+curl -L "https://arxiv.org/src/{arxiv_id}" | tar -xz -C $WORKSPACE/papers/{arxiv_id}
+```
+
+## Step 4: Analyze Literature
+
+**Prerequisites:** At least 5 papers in `$WORKSPACE/papers/`
+
+### 4.1 Read Papers
+
+For each paper, extract:
+- Core contribution (1 sentence)
+- Key method/formula
+- Limitations mentioned
+- Future work suggestions
+
+**Long papers (>50KB):** See `references/reading-long-papers.md`
+
+### 4.2 Identify Research Gaps
+
+Look for:
+- Common limitations across papers
+- Unexplored technique combinations
+- Scalability issues
+- Assumptions that could be relaxed
+
+Document gaps in `$WORKSPACE/ideas/gaps.md`:
+```markdown
+# Research Gaps Identified
+
+## Gap 1: [Description]
+- Mentioned in: [paper1], [paper2]
+- Why important: ...
+
+## Gap 2: [Description]
+...
+```
+
+## Step 5: Generate 5 Ideas
+
+Create `$WORKSPACE/ideas/idea_1.md` through `idea_5.md` using template in `references/idea-template.md`.
+
+**Requirements:**
+- Each idea cites >=2 papers by arXiv ID
+- Use different strategies:
+
+| Idea | Strategy |
+|------|----------|
+| 1 | Combination - merge 2+ techniques |
+| 2 | Simplification - reduce complexity |
+| 3 | Generalization - extend to new domain |
+| 4 | Constraint relaxation - remove assumption |
+| 5 | Architecture innovation - new design |
+
+**REJECTED if:** No arXiv IDs cited, or ideas not grounded in literature
+
+## Step 6: Select and Enhance Best Idea
+
+### 6.1 Score All Ideas
+
+| Idea | Novelty | Feasibility | Impact | Total |
+|------|---------|-------------|--------|-------|
+| 1 | /5 | /5 | /5 | /15 |
+| ... | | | | |
+
+### 6.2 Enhance Selected Idea
+
+Create `$WORKSPACE/ideas/selected_idea.md` with:
+- Detailed math (loss functions, gradients)
+- Architecture choices
+- Hyperparameters
+- Implementation roadmap
+
+### 6.3 (Optional but recommended) OpenReview Evidence Check
+
+For the top 1-2 shortlisted ideas, validate novelty/positioning risk with `openreview_lookup`:
+
+- Query using core title keywords or representative baseline paper title
+- Extract evidence:
+  - decision (if available)
+  - average rating/confidence
+  - reviewer weakness patterns
+- Add a short "submission risk note" section per idea:
+  - likely reviewer concern
+  - mitigation experiment to add
+  - positioning adjustment
+
+Do not claim accept/reject predictions as facts. Report evidence-backed risk signals only.
+
+## Step 7: Code Survey
+
+Map idea concepts to reference implementations.
+
+See `references/code-mapping.md` for template.
+
+**Output:** `$WORKSPACE/ideas/implementation_report.md`
+
+## Step 8: Summary
+
+Create `$WORKSPACE/ideas/summary.md`:
+- All 5 ideas with scores
+- Selected idea details
+- Next steps: `/research-pipeline` to implement
+
+## Commands
+
+| User Says | Action |
+|-----------|--------|
+| "Generate ideas for X" | Check workspace -> ask strategy -> generate |
+| "I have papers, generate ideas" | Skip to Step 4 |
+| "Enhance idea N" | Jump to Step 6 |
+| "Map to code" | Jump to Step 7 |
+
+## Integration
+
+- **Before:** `/literature-survey` to collect papers
+- **After:** `/research-pipeline` to implement selected idea
+- **Alternative:** `/write-review-paper` to write survey instead