skills/43-wentorai-research-plugins/skills/writing/polish/academic-writing-refiner/SKILL.md
Checklist-driven academic English polishing and Chinglish correction
npx skillsauth add brycewang-stanford/Awesome-Agent-Skills-for-Empirical-Research academic-writing-refinerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
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.
| 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" |
These are interference patterns common when translating from Chinese thought patterns into English:
Topic-comment structure. Chinese allows "As for X, Y does Z." English prefers "Y does Z to X."
Redundant verbs. Chinese often uses verb-verb compounds that become redundant in English.
Missing determiners. Chinese has no articles, leading to dropped "the/a/an."
Overuse of "respectively."
"With the development of..." This opening is overused to the point of cliche.
Apply this checklist before submitting any manuscript:
While manual review is irreplaceable, these tools serve as a useful second pass:
# 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 | 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) |
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)."
tools
Recommend AND run open-source AI tools, agents, Claude Code / Codex skills, and MCP servers for any stage of a literature review — searching, reading, extracting, synthesizing, screening, citation-checking, and paper writing. Use when the user asks "what tool should I use to..." OR "install/run/use <tool> to ..." for research/lit-review work: automating a survey or related-work section, PDF→Markdown extraction for LLMs (MinerU/marker/docling), PRISMA / systematic review (ASReview), citation-backed Q&A over PDFs (PaperQA2), wiring papers into Claude/Cursor via MCP (arxiv/paper-search/zotero servers), or chatting with a Zotero library. Ships a launcher (scripts/litrun.py) that installs each tool in an isolated venv and runs it. Curated catalog of 70+ vetted projects. 支持中英文(用于「文献综述工具选型」与「一键安装/运行」)。
development
Route empirical-research requests through the Auto-Empirical Research Skills catalog when this whole repository is installed as one skill in Codex, CodeBuddy, Claude Code, or another IDE. Use to choose and load the right vendored AERS skill for causal inference, econometrics, replication, data acquisition, manuscript writing, peer review and referee responses, citation checking, de-AIGC editing, or full empirical-paper workflows without reading the entire repository at once.
documentation
Use when the project collects primary data or runs a field, lab, or survey experiment, before the intervention begins — write the pre-analysis plan, size the sample from a power calculation, and register with the AEA RCT Registry. Apply after the design is chosen in aer-identification and before any outcome data are seen.
tools
Guide economists to authoritative data sources with explicit, confirmed data specifications before retrieval; interfaces with Playwright MCP to navigate portals and extract real data, not articles about data.