@wentorai/research-plugins 1.0.0

package/skills/writing/latex/tikz-diagrams-guide/SKILL.md

@@ -0,0 +1,211 @@
+---
+name: tikz-diagrams-guide
+description: "Create publication-quality scientific diagrams with TikZ in LaTeX"
+metadata:
+  openclaw:
+    emoji: "triangular_ruler"
+    category: "writing"
+    subcategory: "latex"
+    keywords: ["TikZ", "LaTeX diagrams", "scientific figures", "flowcharts", "PGFplots", "vector graphics"]
+    source: "wentor-research-plugins"
+---
+
+# TikZ Diagrams Guide
+
+A skill for creating publication-quality scientific diagrams directly in LaTeX using the TikZ package. Covers basic drawing commands, flowcharts, neural network architectures, data flow diagrams, and integration with PGFplots for camera-ready figures.
+
+## Getting Started with TikZ
+
+### Basic Setup
+
+```latex
+\documentclass{article}
+\usepackage{tikz}
+\usetikzlibrary{arrows.meta, positioning, shapes.geometric, calc, fit}
+
+\begin{document}
+\begin{tikzpicture}
+  % Your drawing commands here
+\end{tikzpicture}
+\end{document}
+```
+
+### Fundamental Drawing Commands
+
+```latex
+% Lines and shapes
+\draw (0,0) -- (3,0) -- (3,2) -- cycle;          % Triangle
+\draw[thick, ->] (0,0) -- (4,0);                  % Arrow
+\draw[dashed, blue] (0,0) circle (1.5);            % Dashed circle
+\filldraw[fill=gray!20, draw=black] (2,1) ellipse (1 and 0.5);
+
+% Nodes (text labels with optional shapes)
+\node[draw, rectangle, minimum width=2cm] (A) at (0,0) {Input};
+\node[draw, circle] (B) at (3,0) {Process};
+\draw[->] (A) -- (B);
+
+% Relative positioning (requires positioning library)
+\node[draw, rectangle] (C) [right=2cm of B] {Output};
+\draw[->] (B) -- (C);
+```
+
+## Common Scientific Diagrams
+
+### Flowcharts
+
+```latex
+\begin{tikzpicture}[
+    block/.style={rectangle, draw, fill=blue!10, text width=5em,
+                  text centered, rounded corners, minimum height=3em},
+    decision/.style={diamond, draw, fill=green!10, text width=4em,
+                     text centered, inner sep=0pt, aspect=2},
+    line/.style={draw, -Stealth}
+]
+  \node[block] (data) {Collect Data};
+  \node[block, below=1cm of data] (clean) {Clean \& Preprocess};
+  \node[decision, below=1cm of clean] (valid) {Valid?};
+  \node[block, below=1cm of valid] (analyze) {Analyze};
+  \node[block, right=2cm of valid] (fix) {Fix Issues};
+
+  \path[line] (data) -- (clean);
+  \path[line] (clean) -- (valid);
+  \path[line] (valid) -- node[right] {Yes} (analyze);
+  \path[line] (valid) -- node[above] {No} (fix);
+  \path[line] (fix) |- (clean);
+\end{tikzpicture}
+```
+
+### Neural Network Architecture
+
+```latex
+\begin{tikzpicture}[
+    neuron/.style={circle, draw, minimum size=0.8cm, fill=orange!20},
+    layer/.style={rectangle, draw, dashed, inner sep=0.3cm}
+]
+  % Input layer
+  \foreach \i in {1,2,3,4} {
+    \node[neuron] (I\i) at (0, -\i*1.2) {};
+  }
+
+  % Hidden layer
+  \foreach \j in {1,2,3} {
+    \node[neuron, fill=blue!20] (H\j) at (3, -\j*1.2 - 0.6) {};
+  }
+
+  % Output layer
+  \foreach \k in {1,2} {
+    \node[neuron, fill=green!20] (O\k) at (6, -\k*1.2 - 1.2) {};
+  }
+
+  % Connections
+  \foreach \i in {1,2,3,4} {
+    \foreach \j in {1,2,3} {
+      \draw[->] (I\i) -- (H\j);
+    }
+  }
+  \foreach \j in {1,2,3} {
+    \foreach \k in {1,2} {
+      \draw[->] (H\j) -- (O\k);
+    }
+  }
+
+  % Labels
+  \node[above=0.5cm of I1] {Input};
+  \node[above=0.5cm of H1] {Hidden};
+  \node[above=0.5cm of O1] {Output};
+\end{tikzpicture}
+```
+
+## Integration with PGFplots
+
+### Combining Diagrams and Plots
+
+```latex
+\usepackage{pgfplots}
+\pgfplotsset{compat=1.18}
+
+\begin{tikzpicture}
+\begin{axis}[
+    xlabel={Epoch},
+    ylabel={Loss},
+    legend pos=north east,
+    grid=major,
+    width=8cm, height=6cm
+]
+  \addplot[blue, thick, mark=none] table {
+    1  0.95
+    5  0.72
+    10 0.45
+    20 0.22
+    30 0.15
+    50 0.08
+  };
+  \addlegendentry{Training}
+
+  \addplot[red, thick, dashed, mark=none] table {
+    1  0.98
+    5  0.75
+    10 0.52
+    20 0.35
+    30 0.30
+    50 0.28
+  };
+  \addlegendentry{Validation}
+\end{axis}
+\end{tikzpicture}
+```
+
+## Tips for Publication-Quality Figures
+
+### Style Guidelines
+
+```
+1. Font consistency:
+   - Use the same font family as your document body
+   - Minimum 8pt for axis labels and annotations
+   - Match font size to caption text
+
+2. Color considerations:
+   - Use colorblind-friendly palettes (avoid red-green only)
+   - Ensure figures are readable in grayscale
+   - Use patterns or line styles as secondary differentiators
+
+3. Size and resolution:
+   - TikZ produces vector output (PDF) -- always sharp
+   - Set figure width to match column width (single or double)
+   - Use consistent sizing across all figures in the paper
+
+4. Labeling:
+   - Label all axes with units
+   - Use (a), (b), (c) for sub-figures
+   - Place legends inside the plot area when possible
+```
+
+### Exporting Standalone TikZ Figures
+
+```latex
+% standalone.tex -- compile separately, include as PDF
+\documentclass[tikz, border=2mm]{standalone}
+\usetikzlibrary{arrows.meta, positioning}
+\begin{document}
+\begin{tikzpicture}
+  % ... your diagram ...
+\end{tikzpicture}
+\end{document}
+
+% In your main document:
+% \includegraphics{standalone.pdf}
+```
+
+## Useful TikZ Libraries
+
+| Library | Purpose |
+|---------|---------|
+| `positioning` | Relative node placement (right=of, below=of) |
+| `arrows.meta` | Modern arrow tip styles |
+| `shapes.geometric` | Diamond, trapezium, ellipse nodes |
+| `calc` | Coordinate calculations |
+| `fit` | Fit a node around a set of other nodes |
+| `decorations.pathreplacing` | Braces, snakes, zigzag lines |
+| `backgrounds` | Draw behind other elements |
+| `matrix` | Grid-based node layouts |

package/skills/writing/polish/academic-translation-guide/SKILL.md

@@ -0,0 +1,175 @@
+---
+name: academic-translation-guide
+description: "Academic translation, post-editing, and Chinglish correction guide"
+metadata:
+  openclaw:
+    emoji: "globe"
+    category: "writing"
+    subcategory: "polish"
+    keywords: ["academic translation", "machine translation", "post-editing", "Chinglish correction"]
+    source: "wentor-research-plugins"
+---
+
+# Academic Translation Guide
+
+Translate and polish research manuscripts between languages with a focus on academic register, domain-specific terminology, and common pitfalls for Chinese-English academic writing.
+
+## Machine Translation for Academic Texts
+
+### Recommended MT Engines for Academic Use
+
+| Engine | Strengths | Weaknesses | Best For |
+|--------|-----------|------------|----------|
+| DeepL | Excellent European languages, natural output | Limited Asian language pairs | EU language papers |
+| Google Translate | Broadest language coverage | Less polished academic register | Quick drafts, rare languages |
+| ChatGPT / Claude | Context-aware, follows style instructions | May hallucinate terminology | Post-editing, term-aware translation |
+| Tencent TranSmart | Strong Chinese-English technical | Limited other languages | CN-EN STEM papers |
+| Baidu Translate | Strong Chinese-English | Less natural English | CN-EN drafts |
+
+### MT Post-Editing Workflow
+
+1. **Pre-process**: Clean the source text. Remove figure captions, table contents, and equations (translate these separately).
+2. **Translate**: Run through your preferred MT engine.
+3. **Light post-editing (PE)**: Fix factual errors, terminology, and grammar without rewriting.
+4. **Full post-editing**: Rewrite for fluency, cohesion, and academic register.
+5. **Domain review**: Have a subject-matter expert verify technical terminology.
+
+```
+# Example: Light post-editing checklist
+- [ ] Technical terms are correct and consistent
+- [ ] Numbers, units, and chemical formulas are accurate
+- [ ] Negation is preserved (a common MT error)
+- [ ] Subject-verb agreement is correct
+- [ ] Hedging language is appropriate ("may" vs "will")
+- [ ] Citations and references are intact
+```
+
+## Common Chinglish Patterns and Corrections
+
+### Word-Level Issues
+
+| Chinglish | Correction | Explanation |
+|-----------|-----------|-------------|
+| "in recent years" (overuse) | "recently" / omit | Direct translation of "近年来", used excessively |
+| "play an important role" | varies by context | Direct translation of "起着重要作用", often vague |
+| "more and more" | "increasingly" | Direct translation of "越来越" |
+| "discuss about" | "discuss" | "discuss" is transitive in English |
+| "research on" (as verb) | "investigate" / "study" | "Research" used more as noun in English |
+| "the experiment result shows" | "the experimental results show" | Adjective form + plural |
+| "according to" (overuse) | "based on" / rephrase | Direct translation of "根据" |
+
+### Sentence-Level Issues
+
+**Problem: Topic-comment structure (Chinese) vs. Subject-verb-object (English)**
+
+```
+Chinglish: "This method, its advantage is that it can process large datasets."
+Correct:   "The advantage of this method is its ability to process large datasets."
+```
+
+**Problem: Missing articles (a, an, the)**
+
+```
+Chinglish: "We propose method to solve problem."
+Correct:   "We propose a method to solve the problem."
+```
+
+**Problem: Redundant phrasing**
+
+```
+Chinglish: "In this paper, we propose a novel new method..."
+Correct:   "We propose a novel method..."  (or "a new method")
+
+Chinglish: "The purpose of this study is to study..."
+Correct:   "This study investigates..."
+```
+
+**Problem: Overuse of passive voice**
+
+```
+Chinglish: "It was found by us that the results were improved by the new method."
+Correct:   "We found that the new method improved the results."
+```
+
+## Academic Register Conventions
+
+### Formal vs. Informal
+
+| Informal | Formal Academic |
+|----------|----------------|
+| "a lot of" | "numerous" / "substantial" |
+| "get" | "obtain" / "achieve" |
+| "big" | "significant" / "substantial" |
+| "show" | "demonstrate" / "indicate" |
+| "think" | "hypothesize" / "propose" |
+| "look at" | "examine" / "investigate" |
+| "pretty good" | "satisfactory" / "promising" |
+| "kind of" | "somewhat" / "to some extent" |
+
+### Hedging Language
+
+Academic writing requires appropriate hedging to avoid overclaiming:
+
+```
+Too strong: "This proves that X causes Y."
+Hedged:     "These results suggest that X may contribute to Y."
+
+Too strong: "It is certain that..."
+Hedged:     "It appears likely that..." / "The evidence indicates..."
+
+Too strong: "All researchers agree..."
+Hedged:     "There is broad consensus that..." / "Most studies suggest..."
+```
+
+## Translation of Domain-Specific Terms
+
+### Building a Terminology Glossary
+
+For each paper, maintain a bilingual glossary to ensure consistency:
+
+```markdown
+| Chinese Term | English Term | Domain | Notes |
+|-------------|-------------|--------|-------|
+| 深度学习 | deep learning | CS/AI | not "depth learning" |
+| 损失函数 | loss function | ML | not "lost function" |
+| 显著性 | significance | Stats | statistical significance |
+| 显著性 | saliency | CV | visual saliency (different!) |
+| 鲁棒性 | robustness | General | not "robust nature" |
+| 过拟合 | overfitting | ML | not "over-fitting" (no hyphen) |
+| 特征提取 | feature extraction | ML/CV | |
+| 基准测试 | benchmark | CS | not "base test" |
+```
+
+### Using LLMs for Terminology-Aware Translation
+
+```python
+prompt = """Translate the following Chinese academic abstract to English.
+Requirements:
+1. Use formal academic register
+2. Maintain these specific translations:
+   - 注意力机制 -> attention mechanism
+   - 自监督学习 -> self-supervised learning
+   - 下游任务 -> downstream task
+3. Do not add information not present in the original
+4. Preserve all citation markers like [1], [2]
+
+Chinese text:
+{source_text}
+"""
+```
+
+## Quality Assurance Checklist
+
+After translating and editing, verify:
+
+- [ ] All technical terms are correct and consistent throughout
+- [ ] Article usage (a/an/the) is correct
+- [ ] Subject-verb agreement is correct
+- [ ] Tense usage follows disciplinary conventions
+- [ ] Hedging language is appropriate
+- [ ] No Chinglish patterns remain
+- [ ] Numbers, units, and equations are accurate
+- [ ] References and citation markers are intact
+- [ ] Abstract length meets journal requirements
+- [ ] Register is consistently formal
+- [ ] No direct translations of Chinese idioms or four-character phrases

package/skills/writing/polish/academic-writing-refiner/SKILL.md

@@ -0,0 +1,143 @@
+---
+name: academic-writing-refiner
+description: "Checklist-driven academic English polishing and Chinglish correction"
+metadata:
+  openclaw:
+    emoji: "🔍"
+    category: "writing"
+    subcategory: "polish"
+    keywords: ["academic English grammar check", "readability improvement", "academic writing style", "Chinglish correction"]
+    source: "https://github.com/SYSUSELab/academic-writing-guide"
+---
+
+# Academic Writing Refiner
+
+## Overview
+
+Academic papers are judged not only on their scientific merit but also on the quality of their English. Grammatical errors, awkward phrasing, and non-native patterns (commonly called "Chinglish" when originating from Chinese-English interference) can distract reviewers and undermine credibility.
+
+This skill provides a systematic checklist for identifying and correcting common academic English issues. It draws from the academic-writing-guide repository (327+ stars) maintained by SYSUSELab, which catalogs frequent mistakes observed in student and researcher manuscripts across STEM disciplines.
+
+The approach is checklist-driven: rather than relying solely on automated tools, researchers learn to recognize error patterns and self-edit effectively. This skill is especially useful for non-native English speakers preparing manuscripts for international journals and conferences.
+
+## Common Error Categories
+
+### Grammar and Syntax Errors
+
+| Error Type | Example (Wrong) | Correction |
+|-----------|-----------------|------------|
+| Article misuse | "We propose a novel the method" | "We propose a novel method" |
+| Subject-verb disagreement | "The results shows that..." | "The results show that..." |
+| Tense inconsistency | "We train the model and evaluated it" | "We trained the model and evaluated it" |
+| Dangling modifier | "Using gradient descent, the loss decreased" | "Using gradient descent, we decreased the loss" |
+| Run-on sentence | "The model converges fast it achieves high accuracy" | "The model converges fast and achieves high accuracy" |
+
+### Chinglish Patterns
+
+These are interference patterns common when translating from Chinese thought patterns into English:
+
+1. **Topic-comment structure.** Chinese allows "As for X, Y does Z." English prefers "Y does Z to X."
+   - Wrong: "As for the dataset, we use ImageNet."
+   - Better: "We use ImageNet as our dataset."
+
+2. **Redundant verbs.** Chinese often uses verb-verb compounds that become redundant in English.
+   - Wrong: "We can be able to achieve..."
+   - Better: "We can achieve..."
+
+3. **Missing determiners.** Chinese has no articles, leading to dropped "the/a/an."
+   - Wrong: "Model achieves state-of-art result."
+   - Better: "The model achieves a state-of-the-art result."
+
+4. **Overuse of "respectively."**
+   - Wrong: "The accuracy and F1 are 95% and 0.93 respectively."
+   - Better: "The accuracy is 95% and the F1 score is 0.93."
+
+5. **"With the development of..."** This opening is overused to the point of cliche.
+   - Better: Lead with the specific problem or finding.
+
+## Self-Editing Checklist
+
+Apply this checklist before submitting any manuscript:
+
+### Pass 1: Structure and Flow
+
+- [ ] Each paragraph has a clear topic sentence.
+- [ ] Transitions connect paragraphs logically (however, therefore, in contrast).
+- [ ] No paragraph exceeds 200 words.
+- [ ] Figures and tables are referenced in order.
+
+### Pass 2: Grammar and Mechanics
+
+- [ ] All verbs agree with their subjects.
+- [ ] Tense is consistent within each section (past for Methods/Results, present for general truths).
+- [ ] Every acronym is defined on first use.
+- [ ] No comma splices or run-on sentences.
+- [ ] Articles (a, an, the) are used correctly.
+
+### Pass 3: Style and Conciseness
+
+- [ ] Remove "very," "really," "quite," "basically" unless essential.
+- [ ] Replace "in order to" with "to."
+- [ ] Replace "a large number of" with "many" or give the exact count.
+- [ ] Convert passive voice to active where possible.
+- [ ] Eliminate "it is well known that" and similar filler phrases.
+
+### Pass 4: Technical Accuracy
+
+- [ ] All numbers have units.
+- [ ] Table column headers are unambiguous.
+- [ ] Equations are numbered and referenced.
+- [ ] Statistical claims include confidence intervals or p-values.
+
+## Automated Polishing Tools
+
+While manual review is irreplaceable, these tools serve as a useful second pass:
+
+```bash
+# LanguageTool CLI for grammar checking
+java -jar languagetool-commandline.jar -l en-US paper.tex
+
+# Writefull for academic-specific suggestions (VS Code extension)
+# Install from VS Code marketplace: "Writefull for LaTeX"
+
+# textlint for rule-based prose linting
+npm install -g textlint textlint-rule-no-dead-link textlint-rule-write-good
+textlint paper.md
+```
+
+### Tool Comparison
+
+| Tool | Type | Academic Focus | Free Tier |
+|------|------|---------------|-----------|
+| Grammarly | Cloud | General + academic | Yes (limited) |
+| Writefull | Plugin | High (trained on papers) | Yes |
+| LanguageTool | Local/Cloud | General | Yes (full) |
+| textlint | CLI | Configurable rules | Yes (open source) |
+| Trinka | Cloud | High (academic-specific) | Yes (limited) |
+
+## Sentence-Level Revision Examples
+
+### Before and After
+
+**Before:** "In recent years, with the rapid development of deep learning, more and more researchers have paid attention to the problem of image classification, which is a very important task in computer vision."
+
+**After:** "Image classification is a fundamental task in computer vision. Recent advances in deep learning have renewed interest in this problem, with convolutional and transformer architectures achieving human-level accuracy on standard benchmarks."
+
+**Before:** "We can observe from Table 1 that our method can achieve better performance than baseline methods in terms of all evaluation metrics."
+
+**After:** "Our method outperforms all baselines across every metric (Table 1)."
+
+## Best Practices
+
+- **Read published papers in your target venue.** Absorb the register and conventions of journals like Nature, IEEE TPAMI, or ACL.
+- **Have a native speaker review critical sections.** At minimum, ask someone to read the Abstract and Introduction.
+- **Use consistent terminology.** If you call it "feature extraction" in Section 2, do not switch to "representation learning" in Section 4 unless you define the distinction.
+- **Limit sentences to 25 words on average.** Long sentences are harder to parse, especially for non-native readers.
+- **Revise in separate passes.** Do not try to fix grammar, structure, and style simultaneously.
+
+## References
+
+- [academic-writing-guide](https://github.com/SYSUSELab/academic-writing-guide) -- Writing checklist and tutorials (327+ stars)
+- [Common Errors in Technical Writing](https://www.cs.columbia.edu/~hgs/etc/writing-bugs.html) -- Henning Schulzrinne, Columbia University
+- [Writefull](https://writefull.com/) -- AI writing assistant trained on published papers
+- [LanguageTool](https://languagetool.org/) -- Open-source grammar checker