brycewang-stanford/Auto-Empirical-Research-Skills / skills/35-bahayonghang-academic-writing-skills/skills/latex-paper-en
latex-paper-en
VerifiedEnglish LaTeX academic paper assistant for existing `.tex` projects. Use this skill whenever the user wants to compile, lint, audit, or improve an English LaTeX conference or journal paper such as IEEE, ACM, Springer, NeurIPS, or ICML submissions. Trigger even when the user only mentions one paper issue, such as bibliography errors, grammar cleanup, sentence splitting, logic review, expression polishing, translation, title optimization, figure checks, pseudocode review, algorithm block cleanup, de-AI editing, experiment-section review, table structure validation, three-line table generation, abstract structure diagnosis, or journal adaptation. Also trigger for "proofread my paper", "fix my LaTeX", "prepare for submission", "check my manuscript", "improve my writing", "three-line table", "booktabs", "check abstract", "reformat for another journal", "换投", `algorithm2e`, `algorithmicx`, `algpseudocodex`, `Require/Ensure`, or "Algorithm 1" when the user has a .tex file.
scripts/translate_academic.py
View on GitHub#!/usr/bin/env python3
"""
Chinese -> English academic translation helper (MVP).
This script is terminology-driven and provides:
1) terminology confirmation table
2) draft translation
3) ambiguity notes requiring manual confirmation
It preserves LaTeX commands and math segments verbatim while translating
the surrounding visible prose.
"""
import argparse
import re
import sys
from pathlib import Path
TERMINOLOGY = {
"deep-learning": {
"注意力机制": "attention mechanism",
"损失函数": "loss function",
"神经网络": "neural network",
"时间序列预测": "time series forecasting",
"模型": "model",
},
"time-series": {
"时间序列": "time series",
"预测": "forecasting",
"滑动窗口": "sliding window",
"趋势": "trend",
"季节性": "seasonality",
},
"industrial-control": {
"故障检测": "fault detection",
"工业控制": "industrial control",
"控制系统": "control system",
"实时": "real-time",
"鲁棒性": "robustness",
},
}
AMBIGUOUS_TERMS = {
"控制": ["control", "controller", "regulation"],
"性能": ["performance", "efficiency"],
"优化": ["optimization", "improvement"],
}
COMMON_PATTERNS = {
"本文提出": "We propose",
"实验结果表明": "Experimental results demonstrate that",
"与...相比": "Compared with ...",
"在...中": "in ...",
}
PROTECTED_RE = re.compile(
r"(\\[a-zA-Z]+\*?(?:\[[^\]]*\])?(?:\{[^{}]*\})?|"
r"\$[^$]*\$|"
r"\\begin\{[^}]+\}.*?\\end\{[^}]+\})",
re.DOTALL,
)
def _load_source(input_arg: str) -> str:
path = Path(input_arg)
if path.exists() and path.is_file():
return path.read_text(encoding="utf-8", errors="ignore")
return input_arg
def _build_term_table(text: str, domain: str) -> list[tuple[str, str, str]]:
table: list[tuple[str, str, str]] = []
domain_terms = TERMINOLOGY.get(domain, {})
for zh, en in domain_terms.items():
if zh in text:
table.append((zh, en, domain))
return table
def _mask_protected(text: str) -> tuple[str, dict[str, str]]:
masked = text
replacements: dict[str, str] = {}
for idx, match in enumerate(PROTECTED_RE.finditer(text)):
placeholder = f"@@LATEX_{idx}@@"
replacements[placeholder] = match.group(0)
masked = masked.replace(match.group(0), placeholder, 1)
return masked, replacements
def _restore_protected(text: str, replacements: dict[str, str]) -> str:
restored = text
for placeholder, original in replacements.items():
restored = restored.replace(placeholder, original)
return restored
def _draft_translate(text: str, domain: str) -> tuple[str, list[str]]:
translated, replacements = _mask_protected(text)
notes: list[str] = []
for zh, en in TERMINOLOGY.get(domain, {}).items():
if zh in translated:
translated = translated.replace(zh, en)
for zh, en in COMMON_PATTERNS.items():
if zh in translated:
translated = translated.replace(zh, en)
for term, options in AMBIGUOUS_TERMS.items():
if term in translated:
notes.append(f"Ambiguous term '{term}' -> choose one: {', '.join(options)}")
# Minimal sentence formatting
translated = translated.replace("。", ". ").replace(",", ", ")
translated = " ".join(translated.split())
translated = _restore_protected(translated, replacements)
return translated, notes
def translate(input_arg: str, domain: str) -> str:
text = _load_source(input_arg)
table = _build_term_table(text, domain)
draft, notes = _draft_translate(text, domain)
lines: list[str] = []
lines.append("### Terminology Confirmation")
lines.append("| 中文 | English | Domain |")
lines.append("|------|---------|--------|")
if table:
for zh, en, dom in table:
lines.append(f"| {zh} | {en} | {dom} |")
else:
lines.append("| (none detected) | - | - |")
lines.append("\n### Translation Draft")
lines.append(f"% ORIGINAL: {text}")
lines.append(f"% TRANSLATION: {draft}")
lines.append("\n### Notes")
if notes:
for note in notes:
lines.append(f"- ⚠️ [PENDING CONFIRMATION] {note}")
else:
lines.append("- No high-risk ambiguous terms detected by rule set.")
return "\n".join(lines)
def main() -> int:
cli = argparse.ArgumentParser(description="Terminology-driven academic translation helper")
cli.add_argument("input", help="Chinese text or a file path containing Chinese text")
cli.add_argument(
"--domain",
choices=["deep-learning", "time-series", "industrial-control"],
default="deep-learning",
help="Domain terminology set",
)
cli.add_argument("--output", help="Output file path")
args = cli.parse_args()
result = translate(args.input, args.domain)
if args.output:
Path(args.output).write_text(result, encoding="utf-8")
print(f"[SUCCESS] Translation report written to: {args.output}")
else:
print(result)
return 0
if __name__ == "__main__":
sys.exit(main())
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |