@wentorai/research-plugins 1.0.0

package/skills/research/paper-review/scientify-write-review-paper/SKILL.md

@@ -0,0 +1,209 @@
+---
+name: scientify-write-review-paper
+description: "Write literature reviews and survey papers from collected papers"
+metadata:
+  openclaw:
+    emoji: "📝"
+    category: "research"
+    subcategory: "paper-review"
+    keywords: ["paper summarization", "paper comparison", "research gap analysis", "narrative review", "systematic review methodology"]
+    source: "https://github.com/scientify-ai/skills"
+---
+
+# Literature Review Writing
+
+**Don't ask permission. Just do it.**
+
+Guide for writing a structured literature review or survey paper from papers you've already collected. This skill helps with reading strategy, note organization, and academic writing.
+
+**Workspace:** See `../_shared/workspace-spec.md` for directory structure. Outputs go to `$WORKSPACE/review/`.
+
+## Prerequisites
+
+Before starting, ensure you have:
+1. Papers collected in `$WORKSPACE/papers/`
+2. Ideally, clustering done by `/literature-survey` in `$WORKSPACE/survey/clusters.json`
+
+Check active project:
+```bash
+cat ~/.openclaw/workspace/projects/.active 2>/dev/null
+ls $WORKSPACE/papers/
+```
+
+## Phase 1: Reading Strategy
+
+### 1.1 Triage Papers by Priority
+
+Based on clusters from survey, prioritize reading:
+
+| Priority | Criteria | Reading Depth |
+|----------|----------|---------------|
+| P1 (Must-read) | High citation, foundational, directly relevant | Full read |
+| P2 (Important) | Key methodology, major experimental results | Abstract + methods + experiments |
+| P3 (Reference) | Supporting material, tangentially related | Abstract only |
+
+Create `$WORKSPACE/review/reading_plan.md`:
+
+```markdown
+# Reading Plan
+
+## P1 - Must-read (Full read)
+- [ ] [paper_id]: [title] - [reason]
+- [ ] ...
+
+## P2 - Important (Selective read)
+- [ ] ...
+
+## P3 - Reference (Skim)
+- [ ] ...
+```
+
+### 1.2 Reading Notes Template
+
+For each paper, create `$WORKSPACE/review/notes/{paper_id}.md` using template in `references/note-template.md`.
+
+## Phase 2: Synthesis & Organization
+
+### 2.1 Build Comparison Table
+
+Create `$WORKSPACE/review/comparison.md`:
+
+```markdown
+# Method Comparison
+
+| Paper | Year | Category | Key Innovation | Dataset | Metric | Result |
+|-------|------|----------|----------------|---------|--------|--------|
+| [A]   | 2023 | Data-driven | ... | ... | RMSE | 0.05 |
+| [B]   | 2022 | Hybrid | ... | ... | RMSE | 0.08 |
+```
+
+### 2.2 Timeline Analysis
+
+Create `$WORKSPACE/review/timeline.md`:
+
+```markdown
+# Research Timeline
+
+## 2018-2019: Early Exploration
+- [Paper A]: First proposal of method X
+- [Paper B]: Introduction of technique Y
+
+## 2020-2021: Method Maturation
+- [Paper C]: Proposed SOTA method
+- ...
+
+## 2022-2023: New Trends
+- [Paper D]: Began addressing problem Z
+- ...
+
+## Key Milestones
+1. [Year]: [Event/Paper] - [Significance]
+```
+
+### 2.3 Taxonomy Design
+
+Create `$WORKSPACE/review/taxonomy.md`:
+
+```markdown
+# Taxonomy of Approaches
+
+## Dimension 1: Method Type
+- Data-driven
+  - Statistical (e.g., GPR, SVM)
+  - Deep Learning
+    - CNN-based
+    - RNN/LSTM-based
+    - Transformer-based
+  - Hybrid
+- Model-based
+  - Electrochemical
+  - Equivalent Circuit
+
+## Dimension 2: Data Source
+- Laboratory Data
+- Real-world Driving Data
+- Synthetic Data
+
+## Dimension 3: Prediction Horizon
+- Short-term (< 100 cycles)
+- Medium-term (100-500 cycles)
+- Long-term (> 500 cycles)
+```
+
+## Phase 3: Writing Structure
+
+### 3.1 Survey Paper Template
+
+Create `$WORKSPACE/review/draft.md` using template in `references/survey-template.md`.
+
+Key sections: Abstract -> Introduction -> Background -> Taxonomy -> Comparison -> Datasets -> Future Directions -> Conclusion
+
+### 3.2 Thesis Literature Review Template
+
+For a thesis chapter:
+```markdown
+# Chapter 2: Literature Review
+## 2.1 Introduction
+## 2.2 [Topic Area 1]
+## 2.3 [Topic Area 2]
+## 2.4 Summary and Research Gaps
+```
+
+## Phase 4: Writing Tips
+
+### Citation Density Guidelines
+
+| Section | Citation Density |
+|---------|------------------|
+| Abstract | 0 citations |
+| Introduction | 10-20 citations |
+| Background | 5-10 citations |
+| Main Survey | 50-100+ citations |
+| Conclusion | 2-5 citations |
+
+### Transition Phrases
+
+**Introducing similar work:**
+- "Similarly, [Author] proposed..."
+- "Following this direction, ..."
+- "Building upon [X], [Author] extended..."
+
+**Introducing contrasting work:**
+- "In contrast, [Author] argued..."
+- "However, [Author] took a different approach..."
+- "Unlike previous methods, ..."
+
+**Summarizing:**
+- "In summary, existing methods can be categorized into..."
+- "The key insight from these works is..."
+
+### Common Mistakes to Avoid
+
+1. **List-style writing** - Don't just say "A did X, B did Y, C did Z"
+2. **Lack of comparison** - Analyze relationships and differences between methods
+3. **Tense confusion** - Use present tense for methods, past tense for results
+4. **Over-citing** - Not every sentence needs a citation
+5. **Missing important work** - Ensure coverage of foundational works in the field
+
+## Output Files
+
+```
+$WORKSPACE/review/
+├── reading_plan.md       # Reading plan
+├── notes/                # Reading notes
+│   ├── {paper_id}.md
+│   └── ...
+├── comparison.md         # Comparison table
+├── timeline.md           # Timeline analysis
+├── taxonomy.md           # Taxonomy
+├── draft.md              # Review draft
+└── bibliography.bib      # References
+```
+
+## Commands
+
+- "Help me write a review" -> Full workflow from reading to writing
+- "Generate reading plan" -> Create reading_plan.md
+- "Compare these papers" -> Generate comparison.md
+- "Write review draft" -> Generate draft.md
+- "Polish this section" -> Polish specific section

package/skills/tools/code-exec/jupyter-notebook-guide/SKILL.md

@@ -0,0 +1,178 @@
+---
+name: jupyter-notebook-guide
+description: "Best practices for computational research notebooks with reproducible workflows"
+metadata:
+  openclaw:
+    emoji: "notebook"
+    category: "tools"
+    subcategory: "code-exec"
+    keywords: ["sandbox execution", "code runner", "Jupyter notebook", "computational notebook", "reproducible research"]
+    source: "wentor"
+---
+
+# Jupyter Notebook Guide
+
+A skill for using Jupyter notebooks effectively in research contexts. Covers notebook organization, reproducibility best practices, collaboration workflows, and integration with research computing infrastructure.
+
+## Notebook Organization
+
+### Recommended Structure
+
+Every research notebook should follow a consistent structure:
+
+```
+01_data_collection.ipynb     # Data acquisition and initial storage
+02_data_cleaning.ipynb       # Preprocessing, validation, transformations
+03_exploratory_analysis.ipynb # EDA, descriptive statistics, initial plots
+04_modeling.ipynb             # Model training, evaluation, selection
+05_results_visualization.ipynb # Publication-quality figures
+06_supplementary.ipynb       # Additional analyses, robustness checks
+```
+
+### Cell Organization Within a Notebook
+
+```python
+# === CELL 1: Header and metadata ===
+"""
+# Analysis: Effect of Treatment on Outcome Variable
+Author: [Name]
+Date: 2026-03-09
+Data: experiment_results_v2.csv
+Dependencies: pandas>=2.0, scipy>=1.11, matplotlib>=3.8
+"""
+
+# === CELL 2: Imports and configuration ===
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+from scipy import stats
+
+# Reproducibility
+np.random.seed(42)
+pd.set_option('display.max_columns', 50)
+plt.rcParams.update({
+    'figure.figsize': (10, 6),
+    'figure.dpi': 150,
+    'font.size': 12,
+    'axes.titlesize': 14,
+    'savefig.dpi': 300,
+    'savefig.bbox': 'tight'
+})
+
+# === CELL 3: Data loading ===
+DATA_PATH = '../data/raw/experiment_results_v2.csv'
+df = pd.read_csv(DATA_PATH)
+print(f"Loaded {len(df)} rows, {len(df.columns)} columns")
+df.head()
+```
+
+## Reproducibility Best Practices
+
+### Environment Management
+
+Always pin your dependencies:
+
+```bash
+# Create environment from scratch
+conda create -n research python=3.11
+conda activate research
+
+# Install and pin
+pip install pandas==2.1.4 scipy==1.11.4 matplotlib==3.8.2 jupyterlab==4.0.9
+
+# Export for reproducibility
+pip freeze > requirements.txt
+
+# Or use conda
+conda env export --no-builds > environment.yml
+```
+
+### Kernel and Execution Order
+
+```python
+# Add this cell at the top of every notebook to catch execution order issues
+import IPython
+print(f"Python: {IPython.sys.version}")
+print(f"IPython: {IPython.__version__}")
+print(f"Working directory: {os.getcwd()}")
+
+# Run all cells from top to bottom before sharing
+# Menu: Kernel -> Restart & Run All
+# This verifies the notebook executes cleanly in order
+```
+
+### Parameterized Notebooks
+
+Use `papermill` for parameterized execution:
+
+```python
+# Parameters cell (tag with "parameters" in cell metadata)
+input_file = "data/experiment_001.csv"
+alpha = 0.05
+n_bootstrap = 1000
+output_dir = "results/experiment_001"
+```
+
+```bash
+# Execute with different parameters
+papermill 04_modeling.ipynb output/run_001.ipynb \
+  -p input_file "data/experiment_001.csv" \
+  -p alpha 0.01 \
+  -p n_bootstrap 5000
+
+# Batch execution
+for i in $(seq 1 10); do
+  papermill 04_modeling.ipynb "output/run_${i}.ipynb" \
+    -p input_file "data/experiment_${i}.csv"
+done
+```
+
+## JupyterLab Extensions for Research
+
+| Extension | Purpose | Install |
+|-----------|---------|---------|
+| jupyterlab-git | Version control integration | `pip install jupyterlab-git` |
+| jupyterlab-lsp | Code intelligence (autocomplete) | `pip install jupyterlab-lsp` |
+| nbdime | Notebook diffing and merging | `pip install nbdime` |
+| jupytext | Pair notebooks with .py scripts | `pip install jupytext` |
+| jupyter-book | Convert notebooks to publications | `pip install jupyter-book` |
+
+## Version Control for Notebooks
+
+Jupyter notebooks contain output cells, which create noisy diffs. Solutions:
+
+```bash
+# Option 1: Strip outputs before committing
+pip install nbstripout
+nbstripout --install  # adds git filter
+
+# Option 2: Use jupytext to maintain .py mirrors
+jupytext --set-formats ipynb,py:percent notebook.ipynb
+# Now edit the .py file and sync: jupytext --sync notebook.ipynb
+
+# Option 3: Use nbdime for meaningful diffs
+nbdime config-git --enable --global
+git diff notebook.ipynb  # now shows structured diff
+```
+
+## Remote Computing Integration
+
+### Connecting to HPC Clusters
+
+```bash
+# SSH tunnel to remote Jupyter server
+ssh -N -L 8888:localhost:8888 user@cluster.university.edu
+
+# On the cluster:
+jupyter lab --no-browser --port=8888
+
+# Then open http://localhost:8888 in your local browser
+```
+
+### Google Colab Integration
+
+For quick sharing and GPU access, export notebooks to Colab format. Add a Colab badge to your repository README for one-click access. Remember that Colab environments are ephemeral -- always save results to Google Drive or download locally.
+
+## Converting to Publications
+
+Use `jupyter-book` or `nbconvert` to transform notebooks into LaTeX, HTML, or PDF outputs suitable for supplementary materials in journal submissions. Always run the full notebook from a clean kernel before conversion to ensure all outputs are current and reproducible.