@wentorai/research-plugins 1.0.0 → 1.2.0

package/skills/research/deep-research/in-depth-research-guide/SKILL.md

@@ -0,0 +1,205 @@
+---
+name: in-depth-research-guide
+description: "Structured methodology for conducting exhaustive multi-source investigations"
+metadata:
+  openclaw:
+    emoji: "🔬"
+    category: "research"
+    subcategory: "deep-research"
+    keywords: ["deep research", "systematic investigation", "multi-source research", "evidence synthesis", "research methodology", "source evaluation"]
+    source: "https://clawhub.ai/ivangdavila/in-depth-research"
+---
+
+# In-Depth Research Methodology
+
+## Overview
+
+In-depth research goes beyond surface-level literature review to conduct exhaustive, multi-source investigations that synthesize evidence from academic papers, grey literature, industry reports, datasets, and primary sources. This methodology is used when a research question requires comprehensive coverage — for systematic reviews, policy briefs, competitive analyses, or foundational literature surveys in a new research direction.
+
+## The 5-Phase Investigation Framework
+
+### Phase 1: Scope Definition (10% of effort)
+
+Before searching, define boundaries explicitly:
+
+```markdown
+## Research Brief Template
+
+**Central Question**: [One sentence, specific and falsifiable]
+**Sub-Questions** (3-5):
+  1. [Decomposed aspect 1]
+  2. [Decomposed aspect 2]
+  3. [Decomposed aspect 3]
+
+**Inclusion Criteria**:
+  - Time range: [e.g., 2018-present]
+  - Languages: [e.g., English, Chinese]
+  - Document types: [peer-reviewed, preprints, reports, patents]
+  - Disciplines: [e.g., CS, cognitive science, linguistics]
+
+**Exclusion Criteria**:
+  - [Opinion pieces, blog posts without data]
+  - [Studies with n < 30 unless qualitative]
+  - [Duplicate publications of same study]
+
+**Expected Deliverable**: [Literature review / Evidence map / Policy brief / State-of-art report]
+**Depth Target**: [Exhaustive / Representative / Exploratory]
+```
+
+### Phase 2: Multi-Source Collection (30% of effort)
+
+Search systematically across source tiers:
+
+| Tier | Source Type | Examples | Purpose |
+|------|-----------|---------|---------|
+| **1** | Academic databases | Semantic Scholar, PubMed, Scopus, Web of Science | Peer-reviewed primary research |
+| **2** | Preprint servers | arXiv, bioRxiv, SSRN, medRxiv | Cutting-edge, not yet reviewed |
+| **3** | Grey literature | WHO reports, World Bank, NBER working papers | Policy and institutional knowledge |
+| **4** | Patents and standards | Google Patents, USPTO, IEEE standards | Technical implementations |
+| **5** | Data repositories | Zenodo, Figshare, Kaggle, ICPSR | Raw data and reproducibility |
+| **6** | Expert knowledge | Conference talks, interviews, personal communication | Tacit knowledge, emerging trends |
+
+**Search strategy per source**:
+
+```markdown
+For each source:
+1. Construct 3-5 query variants (synonyms, related terms, translated terms)
+2. Apply inclusion/exclusion filters
+3. Record: query string, date, results count, relevant hits
+4. Download and tag all relevant items
+5. Snowball: check references of key papers (backward) and citing papers (forward)
+```
+
+### Phase 3: Source Evaluation (20% of effort)
+
+Rate each source on a standardized evidence hierarchy:
+
+```
+Level 1: Systematic reviews and meta-analyses
+Level 2: Randomized controlled trials / controlled experiments
+Level 3: Cohort studies / quasi-experimental designs
+Level 4: Case-control studies / cross-sectional surveys
+Level 5: Case reports / case series / expert opinion
+Level 6: Anecdotal evidence / grey literature without methodology
+```
+
+**Credibility checklist per source**:
+
+```markdown
+□ Author credentials and affiliation
+□ Publication venue (impact factor, peer-review process)
+□ Methodology transparency (can you replicate it?)
+□ Sample size and representativeness
+□ Conflict of interest disclosure
+□ Recency (is the data still relevant?)
+□ Citation count and reception (supportive vs. critical citations)
+□ Consistency with other sources (does it converge or contradict?)
+```
+
+### Phase 4: Evidence Synthesis (30% of effort)
+
+Organize findings into structured artifacts:
+
+#### Evidence Matrix
+
+| Finding | Source(s) | Evidence Level | Strength | Notes |
+|---------|-----------|---------------|----------|-------|
+| LLMs improve code quality by 20-40% | [A], [B], [C] | Level 2-3 | Strong (convergent) | Effect varies by task complexity |
+| Developers trust AI suggestions less for security-critical code | [D], [E] | Level 4 | Moderate | Small sample sizes |
+| No significant effect on debugging time | [F] | Level 2 | Weak (single study) | Contradicts [A] — needs reconciliation |
+
+#### Contradiction Log
+
+When sources disagree, document systematically:
+
+```markdown
+## Contradiction: Effect of X on Y
+
+**Position A**: X increases Y (Smith 2023, Jones 2024)
+  - Evidence: RCT with n=500, effect size d=0.4
+  - Context: University students, controlled setting
+
+**Position B**: X has no effect on Y (Lee 2024)
+  - Evidence: Field study with n=1200, p=0.34
+  - Context: Industry practitioners, naturalistic setting
+
+**Resolution hypothesis**: The effect is moderated by expertise level.
+  Position A's sample (students) shows the effect;
+  Position B's sample (practitioners) does not.
+  → Need: Study that measures expertise as a moderator.
+```
+
+#### Knowledge Map
+
+Visualize the landscape of your findings:
+
+```
+Central Question
+├── Sub-Q1: [Strong evidence — 8 sources, convergent]
+│   ├── Finding 1.1 (Level 2, 3 sources)
+│   ├── Finding 1.2 (Level 3, 2 sources)
+│   └── Finding 1.3 (Level 4, 3 sources)
+├── Sub-Q2: [Mixed evidence — 5 sources, 1 contradiction]
+│   ├── Finding 2.1 (Level 2, 2 sources)
+│   └── Finding 2.2 ⚠️ CONTRADICTED by Finding 2.3
+├── Sub-Q3: [Weak evidence — 2 sources, emerging area]
+│   └── Finding 3.1 (Level 5, 2 sources)
+└── Unexpected: [Theme that emerged during research]
+    └── Finding 4.1 (Level 3, 1 source) → needs further investigation
+```
+
+### Phase 5: Deliverable Production (10% of effort)
+
+Compile findings into the target deliverable format:
+
+**For a Literature Review**:
+1. Organize by themes (not chronologically)
+2. Synthesize across sources (not paper-by-paper summaries)
+3. Identify gaps explicitly ("No studies have examined...")
+4. State implications for your research
+
+**For a State-of-the-Art Report**:
+1. Current landscape with taxonomy
+2. Key advances and timelines
+3. Open problems and active debates
+4. Future directions with evidence basis
+
+**For a Policy Brief**:
+1. Executive summary (1 paragraph)
+2. Evidence summary (1-2 pages)
+3. Policy options with trade-offs
+4. Recommended action with justification
+
+## Iteration Protocol
+
+Deep research is inherently iterative. After Phase 4, reassess:
+
+```
+After synthesis:
+  □ Are all sub-questions adequately answered?
+  □ Are there new sub-questions that emerged?
+  □ Are there critical gaps requiring additional search?
+  □ Are contradictions resolved or at least documented?
+
+If gaps remain:
+  → Return to Phase 2 with refined queries
+  → Maximum 3 iteration cycles before declaring scope complete
+  → Document what remains unknown (future work)
+```
+
+## Quality Indicators
+
+A well-executed in-depth investigation should demonstrate:
+
+- **Breadth**: Multiple source tiers consulted (not just Google Scholar)
+- **Depth**: Key papers read in full, not just abstracts
+- **Rigor**: Evidence levels assessed, contradictions documented
+- **Transparency**: Search strategy reproducible, decisions justified
+- **Currency**: Most recent relevant work included
+- **Balance**: Competing viewpoints represented fairly
+
+## References
+
+- Petticrew, M., & Roberts, H. (2006). *Systematic Reviews in the Social Sciences*. Blackwell.
+- Grant, M. J., & Booth, A. (2009). "A typology of reviews." *Health Information & Libraries Journal*, 26(2), 91-108.
+- Snyder, H. (2019). "Literature review as a research methodology." *Journal of Business Research*, 104, 333-339.

package/skills/research/deep-research/khoj-research-guide/SKILL.md

@@ -0,0 +1,200 @@
+---
+name: khoj-research-guide
+description: "AI second brain for deep research and personal knowledge management"
+metadata:
+  openclaw:
+    emoji: "🧠"
+    category: "research"
+    subcategory: "deep-research"
+    keywords: ["second-brain", "knowledge-management", "document-analysis", "rag", "self-hosted", "research-assistant"]
+    source: "https://github.com/khoj-ai/khoj"
+---
+
+# Khoj Research Guide
+
+## Overview
+
+Khoj is an open-source AI personal research assistant with over 33,000 GitHub stars that acts as a second brain for researchers, students, and knowledge workers. It can search and chat with your personal notes, documents, and the web to help you find information, synthesize knowledge, and conduct deep research. Khoj combines personal knowledge management with AI-powered research capabilities, making it a unique tool for academic researchers who need to work with large collections of papers, notes, and data.
+
+Unlike general-purpose AI assistants, Khoj is designed to work with your own data. It indexes your documents -- including PDFs, markdown files, org-mode notes, plaintext, and images -- and provides an AI interface that can reason over this personal knowledge base alongside web search results. This means you can ask questions that require combining information from your personal research notes with the latest findings from the web.
+
+Khoj supports both cloud-hosted and fully self-hosted deployments. The self-hosted option is particularly attractive for researchers working with sensitive data, unpublished manuscripts, or proprietary datasets that cannot be sent to third-party services. It supports multiple LLM backends including OpenAI, Anthropic, and local models via Ollama.
+
+## Installation and Setup
+
+### Self-Hosted Deployment (Recommended for Researchers)
+
+```bash
+# Using Docker (recommended)
+docker run -d \
+  --name khoj \
+  -p 42110:42110 \
+  -v ~/.khoj:/root/.khoj \
+  ghcr.io/khoj-ai/khoj:latest
+
+# Or using pip
+pip install khoj
+
+# Start the server
+khoj --host 0.0.0.0 --port 42110
+```
+
+### Configuration
+
+After starting Khoj, configure it through the web interface at `http://localhost:42110/config`:
+
+1. **Content sources**: Point Khoj to your document directories
+2. **LLM configuration**: Set up your preferred language model backend
+3. **Search settings**: Configure web search and document search parameters
+
+```bash
+# Set environment variables for LLM access
+export OPENAI_API_KEY=$OPENAI_API_KEY
+# Or for local models
+export OLLAMA_HOST=http://localhost:11434
+```
+
+### Client Integrations
+
+Khoj provides clients for multiple platforms to integrate into your existing workflow:
+
+- **Web interface**: Full-featured browser UI at `http://localhost:42110`
+- **Obsidian plugin**: Search and chat from within Obsidian
+- **Emacs package**: Native integration for Emacs/org-mode users
+- **Desktop app**: Cross-platform Electron app
+- **WhatsApp/Telegram**: Chat with Khoj via messaging apps
+
+```bash
+# Install the Obsidian plugin
+# In Obsidian: Settings > Community Plugins > Search "Khoj"
+# Configure server URL: http://localhost:42110
+```
+
+## Core Research Features
+
+### Document Indexing and Search
+
+Khoj indexes your research documents and makes them searchable using semantic search:
+
+```python
+# Supported document types
+# - PDF files (research papers, textbooks)
+# - Markdown files (notes, drafts)
+# - Org-mode files (structured notes)
+# - Plaintext files (data, logs)
+# - Images (diagrams, figures)
+# - GitHub repositories (code, documentation)
+# - Notion pages (collaborative notes)
+
+# Configure content sources via the web UI or API
+import requests
+
+# Add a document directory
+requests.post("http://localhost:42110/api/config/data/source", json={
+    "type": "folder",
+    "path": "/path/to/research/papers",
+    "file_types": ["pdf", "md"],
+    "recursive": True,
+})
+```
+
+### Deep Research Mode
+
+Khoj includes a dedicated research mode that goes beyond simple question-answering. It iteratively searches, reads, and synthesizes information from both your personal knowledge base and the web:
+
+```python
+# Trigger deep research via the API
+response = requests.post("http://localhost:42110/api/chat", json={
+    "q": "Synthesize the key findings from my notes on transformer "
+         "efficiency and relate them to recent papers on sparse attention",
+    "research_mode": True,
+    "max_iterations": 8,
+})
+
+# The response includes:
+# - Synthesized answer drawing from personal notes and web sources
+# - Citations to specific documents and web pages
+# - Follow-up questions for further exploration
+```
+
+### Conversational Research
+
+Chat with Khoj about your research, and it will draw on your indexed documents:
+
+```
+User: What are the main arguments in the papers I've saved about
+      few-shot learning?
+
+Khoj: Based on your indexed papers, I found 7 documents related to
+      few-shot learning. The main arguments include:
+      1. [From paper_x.pdf] Meta-learning approaches...
+      2. [From notes/ml-review.md] Prototypical networks...
+      ...
+```
+
+### Automated Research Agents
+
+Khoj supports automated agents that can perform scheduled research tasks:
+
+```python
+# Create a research agent that monitors new papers
+requests.post("http://localhost:42110/api/agents", json={
+    "name": "paper-monitor",
+    "schedule": "daily",
+    "task": "Search for new papers on 'graph neural networks for "
+            "molecular property prediction' published in the last "
+            "24 hours and summarize the key findings",
+    "notify": True,
+})
+```
+
+## Advanced Research Workflows
+
+### Literature Review Pipeline
+
+Use Khoj to build a structured literature review:
+
+1. **Collect**: Index your downloaded papers and notes in Khoj
+2. **Explore**: Ask broad questions to understand the landscape
+3. **Synthesize**: Request comparative analyses across papers
+4. **Identify gaps**: Ask Khoj to find areas where your collection lacks coverage
+5. **Expand**: Use web search to find additional papers on identified gaps
+
+### Knowledge Graph Building
+
+Khoj maintains connections between your documents, allowing you to discover relationships:
+
+```
+User: What connections exist between my notes on attention mechanisms
+      and my notes on computational efficiency?
+
+Khoj: I found several connections:
+      - 3 papers discuss efficient attention variants
+      - Your notes from 2024-03 mention linear attention
+      - The survey paper you saved covers both topics in Section 4
+```
+
+### Multi-Modal Research
+
+Khoj can index and reason about images alongside text, which is useful for researchers working with figures, diagrams, and visual data:
+
+- Index experiment result plots and ask questions about trends
+- Upload architecture diagrams and ask for explanations
+- Search for specific visual patterns across your document collection
+
+## Privacy and Data Sovereignty
+
+For researchers handling sensitive or unpublished data, Khoj offers strong privacy guarantees in self-hosted mode:
+
+- All data stays on your local machine or institutional server
+- No telemetry or data sharing with third parties
+- Compatible with fully local LLMs via Ollama (no external API calls)
+- Encrypted storage for indexed documents
+- Fine-grained access controls for multi-user deployments
+
+## References
+
+- Repository: https://github.com/khoj-ai/khoj
+- Documentation: https://docs.khoj.dev/
+- Obsidian plugin: https://github.com/khoj-ai/khoj/tree/master/src/interface/obsidian
+- Self-hosting guide: https://docs.khoj.dev/get-started/setup/

package/skills/research/deep-research/kosmos-scientist-guide/SKILL.md

@@ -0,0 +1,185 @@
+---
+name: kosmos-scientist-guide
+description: "Claude Code-driven autonomous AI Scientist for discovery"
+metadata:
+  openclaw:
+    emoji: "🔭"
+    category: "research"
+    subcategory: "deep-research"
+    keywords: ["AI Scientist", "autonomous discovery", "Claude Code", "research automation", "scientific method", "experiment"]
+    source: "https://github.com/jimmc414/Kosmos"
+---
+
+# Kosmos AI Scientist Guide
+
+## Overview
+
+Kosmos is a Claude Code-driven AI Scientist framework that automates the scientific discovery process — from hypothesis generation through literature review, experiment design, code implementation, result analysis, and paper writing. It uses Claude Code as the execution engine with structured prompts that guide it through the full scientific method. Designed for ML/AI researchers automating experiment pipelines.
+
+## Scientific Pipeline
+
+```
+Research Question
+      ↓
+  Literature Review (search + synthesize)
+      ↓
+  Hypothesis Generation (testable predictions)
+      ↓
+  Experiment Design (variables, controls, metrics)
+      ↓
+  Implementation (code, data pipeline)
+      ↓
+  Execution (run experiments)
+      ↓
+  Analysis (statistics, visualization)
+      ↓
+  Interpretation (findings, limitations)
+      ↓
+  Paper Draft (LaTeX manuscript)
+```
+
+## Project Configuration
+
+```markdown
+# CLAUDE.md for Kosmos AI Scientist
+
+## Research Protocol
+You are an AI Scientist conducting rigorous research.
+Follow the scientific method strictly:
+
+1. **Literature Review**: Search for related work before
+   proposing anything new. Use Semantic Scholar API.
+2. **Hypothesis**: State falsifiable hypotheses clearly.
+3. **Experiment Design**: Define independent/dependent
+   variables, controls, evaluation metrics.
+4. **Implementation**: Write clean, reproducible code.
+   Set random seeds. Log all hyperparameters.
+5. **Analysis**: Run statistical tests. Report confidence
+   intervals, not just point estimates.
+6. **Honesty**: Report negative results. Acknowledge
+   limitations. Never fabricate data.
+
+## Tools Available
+- Python 3.11+ with PyTorch, NumPy, SciPy
+- LaTeX (pdflatex + bibtex)
+- Semantic Scholar API for literature
+- W&B for experiment tracking (optional)
+```
+
+## Workflow Stages
+
+### Stage 1: Literature Review
+
+```python
+# Kosmos automates literature search
+# The AI Scientist searches, reads, and synthesizes
+
+# Guided prompt pattern:
+"""
+Search for papers on: [TOPIC]
+
+1. Find 20+ relevant papers from last 3 years
+2. Read abstracts and identify key methods
+3. Create a summary table:
+   | Paper | Method | Dataset | Key Result |
+4. Identify gaps in current research
+5. Propose novel directions based on gaps
+"""
+```
+
+### Stage 2: Experiment Design
+
+```python
+# Structured experiment specification
+experiment_spec = {
+    "hypothesis": "Sparse attention patterns learned via "
+                  "Gumbel-Softmax outperform fixed patterns "
+                  "on long-sequence tasks",
+    "independent_vars": ["attention_pattern_type"],
+    "dependent_vars": ["accuracy", "throughput", "memory"],
+    "controls": {
+        "model_size": "same parameter count",
+        "training_data": "same dataset and splits",
+        "hyperparams": "same learning rate schedule",
+    },
+    "datasets": ["Long Range Arena", "PG-19"],
+    "baselines": ["full_attention", "local_window",
+                   "linformer", "performer"],
+    "metrics": {
+        "primary": "accuracy",
+        "secondary": ["wall_clock_time", "peak_memory"],
+    },
+    "statistical_tests": ["paired_t_test", "bootstrap_ci"],
+    "seed_runs": 5,
+}
+```
+
+### Stage 3: Implementation and Execution
+
+```python
+# The AI Scientist writes and runs experiment code
+
+# Pattern: iterative implementation with testing
+"""
+Implement the experiment:
+1. Write model code with unit tests
+2. Write training loop with logging
+3. Run small-scale validation (1 epoch, subset)
+4. Verify metrics are computed correctly
+5. Run full experiments (all seeds, all baselines)
+6. Save results to results/ directory
+"""
+
+# Results structure
+# results/
+# ├── config.json         # Full hyperparameters
+# ├── metrics.csv         # All run metrics
+# ├── figures/            # Generated plots
+# └── checkpoints/        # Model checkpoints
+```
+
+### Stage 4: Analysis and Paper
+
+```python
+# Automated analysis and writing
+"""
+Analyze results and write paper:
+1. Compute mean ± std across seeds
+2. Run statistical significance tests
+3. Generate publication-quality figures
+4. Write LaTeX paper with:
+   - Introduction (motivation + contributions)
+   - Related Work (from literature review)
+   - Method (formal description)
+   - Experiments (setup + results + analysis)
+   - Conclusion (summary + limitations + future)
+5. Verify all citations are real (Semantic Scholar)
+"""
+```
+
+## Safety and Ethics
+
+```markdown
+### Guardrails
+- Never fabricate or manipulate experimental data
+- Report all results including negative ones
+- Acknowledge limitations explicitly
+- Verify all citations against real databases
+- Include compute cost and environmental impact
+- Flag when results are inconclusive
+- Human review required before submission
+```
+
+## Use Cases
+
+1. **ML experiments**: Automated hypothesis → experiment → paper
+2. **Ablation studies**: Systematic component analysis
+3. **Baseline comparison**: Reproduce and compare methods
+4. **Research acceleration**: Draft experiments faster
+5. **Teaching**: Demonstrate scientific method with AI
+
+## References
+
+- [Kosmos GitHub](https://github.com/jimmc414/Kosmos)
+- [The AI Scientist](https://arxiv.org/abs/2408.06292)
+- [Claude Code](https://docs.anthropic.com/en/docs/claude-code)