@wentorai/research-plugins 1.0.0 → 1.2.0

package/skills/research/methodology/academic-mentor-guide/SKILL.md

@@ -0,0 +1,169 @@
+---
+name: academic-mentor-guide
+description: "AI research advisor for graduate students navigating academic careers"
+metadata:
+  openclaw:
+    emoji: "🎓"
+    category: "research"
+    subcategory: "methodology"
+    keywords: ["academic mentoring", "graduate research", "PhD guidance", "research strategy", "academic career", "thesis advising"]
+    source: "https://github.com/AcademicSkills/academic-mentor-guide"
+---
+
+# Academic Mentor Guide
+
+An AI-powered research advisor that provides strategic guidance for graduate students and early-career researchers navigating the complexities of academic research. Covers research question development, methodology selection, publication strategy, time management, advisor relationships, and career planning.
+
+## Overview
+
+Graduate school presents a unique set of challenges that extend far beyond coursework: identifying a viable research niche, developing original contributions, managing the advisor-advisee relationship, navigating peer review, and building a professional network. Many students receive excellent technical training but lack strategic guidance on how to position their work, when to pivot, and how to build a sustainable research program. This skill fills that gap by providing structured, evidence-based advice on the strategic dimensions of academic research.
+
+The skill is designed as a conversational advisor. Present your situation, dilemma, or question, and receive tailored advice drawing from best practices in research methodology, academic career development, and graduate education scholarship. It covers all stages from prospective student through early-career faculty.
+
+## Research Question Development
+
+### From Interest to Researchable Question
+
+```
+Stage 1: Broad Interest
+  "I'm interested in natural language processing for healthcare"
+
+Stage 2: Focused Topic
+  "Clinical note understanding using large language models"
+
+Stage 3: Research Gap
+  "Existing LLMs hallucinate medical facts in clinical summaries"
+
+Stage 4: Specific Question
+  "How does retrieval-augmented generation reduce factual
+   hallucinations in clinical note summarization compared to
+   standard fine-tuning?"
+
+Stage 5: Testable Hypothesis
+  H1: "RAG-augmented summarization produces fewer factual errors
+       (as measured by clinical expert annotation) than fine-tuned
+       models without retrieval, on the MIMIC-III discharge
+       summary dataset."
+```
+
+### Question Quality Checklist
+
+A strong research question should be:
+
+| Criterion | Test | Example Pass/Fail |
+|-----------|------|------------------|
+| **Specific** | Can you explain it in one sentence? | Pass: "Does X affect Y in context Z?" |
+| **Novel** | Does it add something new? | Fail: "Can neural networks classify images?" |
+| **Feasible** | Can you answer it with available resources? | Fail if you need data you cannot access |
+| **Significant** | Would the answer matter to the field? | Pass: fills an identified gap in literature |
+| **Measurable** | Can you define success criteria? | Pass: specific metrics and benchmarks identified |
+
+## Methodology Selection
+
+### Matching Method to Question
+
+| Question Type | Suggested Methods | Considerations |
+|--------------|-------------------|----------------|
+| "Does X cause Y?" | RCT, quasi-experiment, IV, DiD | Causation requires design, not statistics |
+| "How does X relate to Y?" | Correlation, regression, SEM | Cannot infer causation from observational data |
+| "What is the experience of...?" | Interviews, phenomenology | Qualitative rigor: saturation, reflexivity |
+| "How much of X exists?" | Survey, secondary data analysis | Sampling design determines generalizability |
+| "Does method A outperform B?" | Benchmark experiments, ablation | Control for confounds; use multiple metrics |
+| "What themes emerge from...?" | Grounded theory, thematic analysis | Systematic coding, inter-rater reliability |
+
+### Mixed Methods Considerations
+
+When a single method cannot fully address your question, consider:
+
+1. **Sequential explanatory**: Quantitative first, then qualitative to explain results.
+2. **Sequential exploratory**: Qualitative first, then quantitative to test emergent themes.
+3. **Convergent parallel**: Both simultaneously, then integrate at interpretation.
+
+Key rule: each method must be rigorous on its own terms. Mixed methods is not a shortcut to avoid depth in either tradition.
+
+## Publication Strategy
+
+### Planning Your Publication Pipeline
+
+```
+Year 1-2 of PhD:
+  - Systematic/scoping review paper (establishes expertise, builds lit knowledge)
+  - Workshop paper or short paper (low-stakes venue to get feedback)
+
+Year 2-3:
+  - Main contribution paper #1 (core of dissertation)
+  - Tool/dataset paper if applicable (broadens impact)
+
+Year 3-4:
+  - Main contribution paper #2 (extends or deepens #1)
+  - Invited talks or poster presentations at top conferences
+
+Year 4-5 (if applicable):
+  - Synthesis/position paper (demonstrates thought leadership)
+  - Dissertation defense (integrates everything)
+```
+
+### Venue Selection Framework
+
+| Criterion | Conference | Journal |
+|-----------|-----------|---------|
+| Speed of dissemination | Fast (3-6 months) | Slow (6-18 months) |
+| Networking | Presentations, hallway conversations | Less direct interaction |
+| Page limits | Usually strict (8-12 pages) | Flexible (often 20-40 pages) |
+| Revision opportunity | Usually accept/reject | Revise and resubmit common |
+| Impact factor | Varies by field | Often higher for journals |
+| Best for | Incremental results, new ideas | Complete, mature studies |
+
+## Time Management for Researchers
+
+### The Weekly Research Schedule
+
+Protect blocks of uninterrupted time for deep research work:
+
+- **Monday-Wednesday**: 3-4 hour morning blocks for writing and analysis (most cognitively demanding tasks).
+- **Thursday**: Meetings, literature reading, email, administrative tasks.
+- **Friday**: Experimentation, coding, data collection.
+- **Weekends**: Optional reading; avoid burnout by setting boundaries.
+
+### The 80/20 Rule for PhD Progress
+
+- Spend 80% of research time on your core contribution (the work that becomes your dissertation).
+- Spend 20% on exploratory reading, skill building, and collaborative side projects.
+- Audit your time monthly: if the ratio has flipped, recalibrate.
+
+## Navigating the Advisor Relationship
+
+### Communication Best Practices
+
+1. **Regular updates**: Send a brief weekly email summarizing progress, blockers, and next steps.
+2. **Come prepared**: Every meeting should have a written agenda with specific questions.
+3. **Manage expectations**: If a deadline is at risk, communicate early, not at the last minute.
+4. **Seek feedback explicitly**: "Could you review Section 3? I'm unsure about the framing of the contribution."
+5. **Document agreements**: Follow up meetings with an email summarizing decisions and action items.
+
+### When Things Go Wrong
+
+- **Advisor is unresponsive**: Escalate gradually: email reminder after 1 week, in-person conversation after 2 weeks, committee member consultation after a month.
+- **Disagreement on direction**: Present your reasoning in writing with evidence. If the impasse continues, involve a committee member as mediator.
+- **Advisor leaves institution**: This is more common than students expect. Document your progress, know your program's policies, and have a backup advisor relationship.
+
+## Career Decision Framework
+
+### Academic vs. Industry vs. Alternative Careers
+
+Consider these factors honestly:
+
+| Factor | Academia | Industry Research | Industry Applied |
+|--------|---------|-------------------|-----------------|
+| Autonomy | High (after tenure) | Moderate | Lower |
+| Compensation | Lower | Higher | Higher |
+| Geographic flexibility | Very low | Moderate | High |
+| Publication freedom | High | Varies | Limited |
+| Job security | Low until tenure | Moderate | Moderate |
+| Work-life balance | Self-managed (often poor) | Structured | Structured |
+
+## References
+
+- Dericks, G., et al. (2019). PhD Supervision: Understanding the Factors That Lead to Success. *Studies in Higher Education*.
+- Lovitts, B. E. (2005). Being a Good Course-Taker Is Not Enough. *Studies in Higher Education*, 30(2), 137-154.
+- Bolker, J. (1998). *Writing Your Dissertation in Fifteen Minutes a Day*. Henry Holt.

package/skills/research/methodology/claude-scientific-guide/SKILL.md

@@ -0,0 +1,122 @@
+---
+name: claude-scientific-guide
+description: "Ready-to-use agent skills for scientific research and engineering"
+version: 1.0.0
+author: wentor-community
+source: https://github.com/zyphlar/claude-scientific-skills
+metadata:
+  openclaw:
+    category: "research"
+    subcategory: "methodology"
+    keywords:
+      - scientific-method
+      - research-skills
+      - claude
+      - agent-prompting
+      - experiment-design
+      - engineering
+---
+
+# Claude Scientific Guide
+
+A comprehensive skill that provides ready-to-use agent instructions for conducting scientific research, designing experiments, and solving engineering problems. Based on the claude-scientific-skills repository (14K stars), this skill distills best practices for leveraging Claude as a research methodology assistant across disciplines.
+
+## Overview
+
+Scientific research demands rigorous methodology: forming hypotheses, designing experiments, analyzing results, and iterating on findings. This skill equips the agent with structured approaches to each phase of the scientific process, drawing from proven prompt patterns that have been validated across thousands of research workflows.
+
+The skill covers three primary domains: fundamental research methodology, applied science workflows, and engineering problem-solving. Each domain includes step-by-step procedures, quality checkpoints, and common pitfalls to avoid.
+
+## Research Methodology Workflows
+
+When assisting with research methodology, follow these structured approaches:
+
+**Hypothesis Formation**
+- Gather existing literature context before proposing hypotheses
+- Ensure hypotheses are falsifiable and specific
+- Identify independent, dependent, and control variables
+- State null and alternative hypotheses explicitly
+- Consider confounding variables and propose mitigation strategies
+
+**Experiment Design**
+- Select appropriate experimental design (RCT, quasi-experimental, observational)
+- Calculate required sample sizes using power analysis principles
+- Define primary and secondary endpoints before data collection
+- Establish blinding protocols where applicable
+- Create pre-registration documents outlining analysis plans
+
+**Data Collection Planning**
+- Specify measurement instruments and their validity evidence
+- Design data collection forms that minimize entry errors
+- Plan for missing data handling before collection begins
+- Establish inter-rater reliability protocols for subjective measures
+- Create audit trails for data provenance tracking
+
+## Scientific Analysis Patterns
+
+The agent should apply these analysis patterns when helping researchers:
+
+**Exploratory Analysis**
+- Begin with descriptive statistics and data visualization
+- Check distributional assumptions before selecting tests
+- Identify outliers using both statistical and domain-knowledge criteria
+- Report effect sizes alongside p-values
+- Use appropriate corrections for multiple comparisons
+
+**Reproducibility Checklist**
+- Document all software versions and random seeds
+- Provide complete analysis code with inline comments
+- Report all conducted analyses, not just significant results
+- Include sensitivity analyses for key assumptions
+- Archive raw data alongside processed datasets
+
+**Literature Synthesis**
+- Use systematic search strategies across multiple databases
+- Apply PRISMA or similar reporting frameworks
+- Assess quality of evidence using established rubrics (GRADE, Newcastle-Ottawa)
+- Identify gaps and contradictions in existing findings
+- Summarize evidence strength for each research question
+
+## Engineering Problem-Solving
+
+For engineering-oriented research tasks, the agent follows structured problem-solving:
+
+**Problem Definition**
+- Decompose complex problems into tractable sub-problems
+- Define success criteria with quantitative thresholds
+- Identify constraints (physical, computational, budgetary)
+- Map dependencies between sub-problems
+- Prioritize by impact and feasibility
+
+**Solution Development**
+- Generate multiple candidate solutions before evaluating
+- Apply first-principles reasoning to validate feasibility
+- Prototype minimal viable solutions for rapid testing
+- Document assumptions and their sensitivity to variation
+- Plan for scalability from prototype to production
+
+**Validation and Iteration**
+- Define acceptance tests before implementation
+- Use A/B testing or equivalent comparison methods
+- Track metrics over time to detect regression
+- Conduct root cause analysis for failures
+- Iterate based on empirical evidence rather than intuition
+
+## Integration with Research-Claw
+
+This skill integrates with the Research-Claw agent to provide methodology assistance during active research sessions. When activated, the agent can:
+
+- Review research proposals and suggest methodological improvements
+- Help draft pre-registration documents for experiments
+- Guide statistical analysis selection based on data characteristics
+- Assist with writing methods sections that meet journal standards
+- Generate reproducibility checklists tailored to specific domains
+
+## Best Practices
+
+- Always start by understanding the researcher's domain context before applying generic methodology templates
+- Adapt statistical recommendations to the conventions of the specific field
+- Flag when a research question may require IRB or ethics review
+- Suggest pilot studies before committing to large-scale data collection
+- Recommend collaboration with statisticians for complex designs
+- Maintain awareness of field-specific reporting guidelines (CONSORT, STROBE, ARRIVE)

package/skills/research/methodology/deep-innovator-guide/SKILL.md

@@ -0,0 +1,242 @@
+---
+name: deep-innovator-guide
+description: "AI research for idea generation and scientific discovery methods"
+metadata:
+  openclaw:
+    emoji: "💡"
+    category: "research"
+    subcategory: "methodology"
+    keywords: ["idea generation", "scientific discovery", "innovation", "research ideation", "creative research", "hypothesis generation"]
+    source: "https://github.com/AcademicSkills/deep-innovator-guide"
+---
+
+# Deep Innovator Guide
+
+A skill for systematic idea generation and scientific discovery in academic research. Combines structured creativity techniques with computational methods to help researchers identify novel research directions, generate testable hypotheses, and find unexpected connections across disciplines.
+
+## Overview
+
+Scientific innovation rarely happens through pure serendipity. Research on scientific breakthroughs consistently shows that novel ideas emerge at the intersection of existing knowledge domains, from systematic exploration of anomalies, or through the creative recombination of known concepts. This skill provides structured methods for each of these innovation pathways, making the ideation process more systematic without sacrificing creativity.
+
+The skill is designed for researchers at any career stage who feel stuck in incremental thinking, who want to explore new research directions, or who need to generate a portfolio of potential research questions for a grant proposal or thesis prospectus. It draws on techniques from design thinking, TRIZ (Theory of Inventive Problem Solving), bibliometric innovation detection, and computational creativity research.
+
+## Structured Ideation Methods
+
+### Method 1: Cross-Domain Analogy Mining
+
+The most frequently cited source of scientific breakthroughs is the transfer of ideas from one domain to another. This method systematizes that process.
+
+```
+Step 1: Define your problem abstractly
+  Concrete: "How can we detect early-stage Alzheimer's from speech patterns?"
+  Abstract: "How to detect gradual degradation of a complex system from
+             its output signals?"
+
+Step 2: Identify analogous domains
+  - Manufacturing: detecting machine wear from vibration patterns
+  - Ecology: detecting ecosystem decline from biodiversity metrics
+  - Software: detecting code quality degradation from commit patterns
+  - Music: detecting performer fatigue from playing characteristics
+
+Step 3: Study solutions in analogous domains
+  - Manufacturing uses wavelet analysis on vibration frequency shifts
+  - Ecology uses species abundance distribution curves
+  - Software uses entropy measures on code change patterns
+
+Step 4: Transfer and adapt
+  Idea: Apply wavelet decomposition to speech prosody features to detect
+        frequency-domain shifts that precede clinical Alzheimer's diagnosis.
+```
+
+### Method 2: Contradiction Resolution (TRIZ-Inspired)
+
+```python
+def identify_research_contradictions(domain_knowledge: dict) -> list:
+    """
+    Identify contradictions in current knowledge that could lead to
+    innovative research questions.
+
+    Types of contradictions:
+    1. Technical: Improving A makes B worse
+    2. Physical: System needs property X and not-X simultaneously
+    3. Empirical: Study A finds effect, Study B finds opposite
+    """
+    contradictions = []
+
+    # Type 1: Technical contradictions
+    # "Increasing model accuracy requires more data, but more data
+    #  increases privacy risk"
+    # Resolution principle: SEPARATION (separate the contradictory
+    #  requirements in time, space, or condition)
+    # Idea: Federated learning separates data access from model training
+
+    # Type 2: Empirical contradictions
+    # "Drug X shows efficacy in lab but not in clinical trials"
+    # Resolution principle: INVESTIGATE THE BOUNDARY
+    # Idea: What differs between lab and clinical contexts? (dosage,
+    #  population heterogeneity, adherence, bioavailability)
+
+    return contradictions
+```
+
+### Method 3: Gap Matrix Analysis
+
+Create a matrix crossing two relevant dimensions to identify unexplored combinations:
+
+| | Method A | Method B | Method C | Method D |
+|---|---------|---------|---------|---------|
+| **Population 1** | Studied | Studied | GAP | Studied |
+| **Population 2** | Studied | GAP | GAP | Studied |
+| **Population 3** | GAP | GAP | GAP | GAP |
+| **Population 4** | Studied | GAP | Studied | GAP |
+
+Each GAP cell represents a potential novel study. Prioritize GAP cells by:
+- Theoretical interest (would the finding be surprising or informative?)
+- Feasibility (can you access this population and apply this method?)
+- Impact (would filling this gap change practice or theory?)
+
+## Computational Innovation Detection
+
+### Bibliometric Novelty Signals
+
+```python
+def detect_novelty_signals(papers: list) -> dict:
+    """
+    Detect signals of emerging innovation in a set of papers.
+    """
+    signals = {}
+
+    # Signal 1: New keyword combinations
+    # Papers that combine keywords from traditionally separate fields
+    # indicate cross-disciplinary innovation
+    signals['novel_keyword_pairs'] = find_new_keyword_cooccurrences(papers)
+
+    # Signal 2: Citation bridge papers
+    # Papers cited by two communities that rarely cite each other
+    signals['bridge_papers'] = find_citation_bridges(papers)
+
+    # Signal 3: Accelerating citation curves
+    # Recently published papers gaining citations faster than average
+    signals['sleeping_beauties'] = find_acceleration_anomalies(papers)
+
+    # Signal 4: Method migration
+    # Methods first published in Domain A appearing in Domain B
+    signals['method_transfers'] = find_method_migrations(papers)
+
+    # Signal 5: Terminology shifts
+    # Old terms being replaced by new ones (signals paradigm change)
+    signals['terminology_evolution'] = find_term_replacements(papers)
+
+    return signals
+```
+
+### Hypothesis Generation from Data
+
+```
+Observation-Driven Hypothesis Generation:
+
+1. ANOMALY DETECTION
+   Look for unexpected patterns in existing data:
+   - Results that deviate from theoretical predictions
+   - Subgroups that behave differently from the main sample
+   - Variables that correlate when they "should not"
+   Question template: "Why does [anomaly] occur in [context]?"
+
+2. BOUNDARY CONDITIONS
+   Test where known effects break down:
+   - At what sample size does effect X disappear?
+   - In which populations does intervention Y not work?
+   - Under what conditions does relationship Z reverse?
+   Question template: "Under what conditions does [known effect] not hold?"
+
+3. MECHANISM GAPS
+   Identify well-documented effects without known mechanisms:
+   - "We know X causes Y but not how"
+   - "The mediating pathway is unknown"
+   Question template: "What mechanism explains the effect of [X] on [Y]?"
+
+4. SCALE TRANSITIONS
+   Phenomena may behave differently at different scales:
+   - Lab findings that may not scale to real-world settings
+   - Individual-level effects that may not apply at group level
+   Question template: "Does [finding at scale A] hold at [scale B]?"
+```
+
+## Innovation Portfolio Management
+
+### Balancing Risk and Impact
+
+Maintain a portfolio of research ideas at different risk-reward levels:
+
+| Category | Risk | Potential Impact | Portfolio % | Examples |
+|----------|------|-----------------|------------|---------|
+| **Incremental** | Low | Moderate | 40-50% | Replicate with new data, extend to new population |
+| **Substantial** | Medium | High | 30-40% | New method applied to existing problem |
+| **Transformative** | High | Very High | 10-20% | New framework, cross-disciplinary breakthrough |
+| **Exploratory** | Very High | Unknown | 5-10% | Speculative, curiosity-driven |
+
+### Idea Evaluation Rubric
+
+Score each idea on a 1-5 scale for each criterion:
+
+| Criterion | Question | Weight |
+|-----------|----------|--------|
+| Novelty | Has this been done before? | 25% |
+| Feasibility | Can I do this with my resources? | 25% |
+| Significance | Would the answer change the field? | 25% |
+| Fundability | Would an agency fund this? | 15% |
+| Personal fit | Does this align with my expertise and interests? | 10% |
+
+```python
+def evaluate_research_idea(scores: dict, weights: dict = None) -> dict:
+    """
+    Evaluate a research idea using the weighted scoring rubric.
+    """
+    if weights is None:
+        weights = {
+            'novelty': 0.25, 'feasibility': 0.25, 'significance': 0.25,
+            'fundability': 0.15, 'personal_fit': 0.10
+        }
+
+    weighted_score = sum(scores[k] * weights[k] for k in scores)
+    max_score = 5.0
+
+    return {
+        'scores': scores,
+        'weighted_total': round(weighted_score, 2),
+        'max_possible': max_score,
+        'percentage': round(weighted_score / max_score * 100, 1),
+        'recommendation': (
+            'Strong pursue' if weighted_score >= 4.0 else
+            'Worth developing' if weighted_score >= 3.0 else
+            'Needs refinement' if weighted_score >= 2.0 else
+            'Consider alternatives'
+        )
+    }
+```
+
+## Collaborative Ideation Sessions
+
+### Structured Brainstorming for Research Teams
+
+1. **Individual divergence** (10 min): Each team member silently generates 5-10 ideas.
+2. **Round-robin sharing** (15 min): Each person shares one idea at a time, no criticism allowed.
+3. **Affinity clustering** (10 min): Group similar ideas together on a whiteboard.
+4. **Build and combine** (15 min): Look for ways to merge or strengthen ideas across clusters.
+5. **Evaluation** (10 min): Apply the scoring rubric to the top 5 ideas.
+6. **Selection** (5 min): Choose 1-2 ideas to develop further with feasibility analysis.
+
+## Best Practices
+
+- Schedule regular ideation time (monthly) rather than waiting for inspiration to strike.
+- Keep an "idea notebook" where you record fleeting thoughts before they are lost.
+- Read outside your field deliberately. Subscribe to journals in adjacent disciplines.
+- When you find an anomaly in your data, resist the urge to explain it away immediately. Investigate it.
+- Test ideas cheaply before committing resources. A quick literature search or back-of-the-envelope calculation can eliminate weak ideas early.
+- Discuss ideas with people outside your specialty. They bring fresh perspectives and ask different questions.
+
+## References
+
+- Uzzi, B., et al. (2013). Atypical Combinations and Scientific Impact. *Science*, 342(6157), 468-472.
+- Foster, J. G., et al. (2015). Tradition and Innovation in Scientists' Research Strategies. *American Sociological Review*, 80(5), 875-908.
+- Wang, D., Song, C., & Barabasi, A.-L. (2013). Quantifying Long-Term Scientific Impact. *Science*, 342(6154), 127-132.