Skip to content

brycewang-stanford/Auto-Empirical-Research-Skills / skills/35-bahayonghang-academic-writing-skills/skills/latex-paper-en

latex-paper-en

Verified

English 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.

FileKindSize
SKILL.mdskill md8.5 KB
agents/openai.yamlconfig390 B
evals/evals.jsonconfig7.8 KB
examples/compile-and-bibliography.mdmarkdown551 B
examples/experiment-review.mdmarkdown527 B
examples/figures-and-title.mdmarkdown513 B
examples/grammar-and-logic.mdmarkdown687 B
examples/translation-and-deai.mdmarkdown630 B
references/ABSTRACT_STRUCTURE.mdmarkdown4.9 KB
references/BEST_PRACTICES.mdmarkdown456 B
references/CITATION_STYLES.mdmarkdown4.2 KB
references/CITATION_VERIFICATION.mdmarkdown4.1 KB
references/COMMON_ERRORS.mdmarkdown2.8 KB
references/COMPILATION.mdmarkdown2.0 KB
references/DEAI_GUIDE.mdmarkdown16.8 KB
references/FORBIDDEN_TERMS.mdmarkdown1.6 KB
references/JOURNAL_ABBREVIATIONS.mdmarkdown3.5 KB
references/JOURNAL_ADAPTATION_WORKFLOW.mdmarkdown3.6 KB
references/NUMBER_UNIT_GUIDE.mdmarkdown2.3 KB
references/REVIEWER_PERSPECTIVE.mdmarkdown4.9 KB
references/STYLE_GUIDE.mdmarkdown6.5 KB
references/TABLE_GUIDE.mdmarkdown3.7 KB
references/TERMINOLOGY.mdmarkdown9.9 KB
references/TRANSLATION_GUIDE.mdmarkdown11.4 KB
references/VENUES.mdmarkdown6.4 KB
references/WRITING_PHILOSOPHY.mdmarkdown6.7 KB
references/modules/ABSTRACT.mdmarkdown1.2 KB
references/modules/ADAPT.mdmarkdown1.3 KB
references/modules/BIBLIOGRAPHY.mdmarkdown1.3 KB
references/modules/CAPTION.mdmarkdown2.0 KB
references/modules/COMPILE.mdmarkdown2.8 KB
references/modules/DEAI.mdmarkdown1.0 KB
references/modules/EXPERIMENT.mdmarkdown3.8 KB
references/modules/EXPRESSION.mdmarkdown789 B
references/modules/FORMAT.mdmarkdown440 B
references/modules/GRAMMAR.mdmarkdown980 B
references/modules/LOGIC.mdmarkdown7.6 KB
references/modules/PSEUDOCODE.mdmarkdown1.7 KB
references/modules/SENTENCES.mdmarkdown575 B
references/modules/TABLES.mdmarkdown1.3 KB
references/modules/TITLE.mdmarkdown7.7 KB
references/modules/TRANSLATION.mdmarkdown1.1 KB
references/modules/WORKFLOW.mdmarkdown910 B
scripts/analyze_abstract.pyscript17.3 KB
scripts/analyze_experiment.pyscript18.1 KB
scripts/analyze_grammar.pyscript3.6 KB
scripts/analyze_logic.pyscript18.4 KB
scripts/analyze_sentences.pyscript3.6 KB
scripts/check_figures.pyscript6.4 KB
scripts/check_format.pyscript6.4 KB
scripts/check_pseudocode.pyscript11.2 KB
scripts/check_references.pyscript14.2 KB
scripts/check_tables.pyscript16.3 KB
scripts/compile.pyscript17.4 KB
scripts/deai_batch.pyscript9.9 KB
scripts/deai_check.pyscript16.4 KB
scripts/extract_prose.pyscript2.7 KB
scripts/generate_table.pyscript8.8 KB
scripts/improve_expression.pyscript3.2 KB
scripts/online_bib_verify.pyscript11.9 KB
scripts/optimize_title.pyscript15.4 KB
scripts/parsers.pyscript14.9 KB
scripts/translate_academic.pyscript5.1 KB
scripts/verify_bib.pyscript18.9 KB

scripts/deai_batch.py

View on GitHub
#!/usr/bin/env python3
"""
De-AI Batch Processor for English Academic Papers
Batch processes entire LaTeX/Typst chapters or documents.

Usage:
    uv run python -B deai_batch.py main.tex --chapter chapter3/introduction.tex
    uv run python -B deai_batch.py main.tex --all-sections
    uv run python -B deai_batch.py main.tex --section introduction --output polished/
"""

import argparse
import re
import sys
from pathlib import Path

# Import local parsers
try:
    from parsers import get_parser
except ImportError:
    sys.path.append(str(Path(__file__).parent))
    from parsers import get_parser


class DeAIBatchProcessor:
    """Batch process files for de-AI editing."""

    def __init__(self, file_path: Path):
        self.file_path = file_path
        self.content = file_path.read_text(encoding="utf-8", errors="ignore")
        self.lines = self.content.split("\n")
        self.parser = get_parser(file_path)
        self.section_ranges = self.parser.split_sections(self.content)
        self.comment_prefix = self.parser.get_comment_prefix()

    def analyze_section(self, section_name: str) -> dict:
        """Analyze a section for AI traces."""
        if section_name not in self.section_ranges:
            return {
                "section": section_name,
                "found": False,
                "lines": 0,
                "traces": [],
            }

        start, end = self.section_ranges[section_name]
        traces = []

        # Get lines for this section
        # Convert 1-based lines to 0-based index
        section_lines = self.lines[start - 1 : end]
        line_num = start

        for line in section_lines:
            stripped = line.strip()
            if not stripped or stripped.startswith(self.comment_prefix):
                line_num += 1
                continue

            visible = self.parser.extract_visible_text(stripped)
            ai_patterns = self._check_ai_patterns(visible)

            if ai_patterns:
                traces.append(
                    {
                        "line": line_num,
                        "original": stripped,
                        "visible": visible,
                        "patterns": ai_patterns,
                    }
                )

            line_num += 1

        return {
            "section": section_name,
            "found": True,
            "lines": end - start + 1,
            "traces": traces,
        }

    def _check_ai_patterns(self, text: str) -> list[str]:
        """Check text for AI writing patterns."""
        patterns = []

        # Empty phrases
        empty_phrases = [
            r"significant (?:improvement|performance|gain)",
            r"comprehensive (?:analysis|study)",
            r"effective (?:solution|method)",
            r"important (?:contribution|role)",
            r"robust performance",
            r"novel approach",
            r"state-of-the-art",
        ]

        # Over-confident
        over_confident = [
            r"\bobviously\b",
            r"\bclearly\b",
            r"\bcertainly\b",
            r"\bundoubtedly\b",
        ]

        # Vague quantifiers
        vague_quantifiers = [
            r"\bmany studies\b",
            r"\bnumerous experiments\b",
            r"\bvarious methods\b",
            r"\bseveral approaches\b",
        ]

        # Template expressions
        template_exprs = [
            r"\bin recent years\b",
            r"\bmore and more\b",
            r"\bplays? an important role\b",
            r"\bwith the (?:rapid )?development of\b",
        ]

        all_checks = [
            ("empty_phrase", empty_phrases),
            ("over_confident", over_confident),
            ("vague_quantifier", vague_quantifiers),
            ("template_expr", template_exprs),
        ]

        for category, pattern_list in all_checks:
            for pattern in pattern_list:
                if re.search(pattern, text, re.IGNORECASE):
                    patterns.append(f"{category}: {pattern}")

        return patterns

    def generate_batch_report(self, analyses: dict[str, dict]) -> str:
        """Generate batch processing report."""
        report = []
        report.append("=" * 70)
        report.append("DE-AI BATCH PROCESSING REPORT")
        report.append("=" * 70)
        report.append(f"Source file: {self.file_path}")
        report.append("")

        total_traces = 0
        total_lines = 0

        for section_name, analysis in analyses.items():
            if not analysis["found"]:
                continue

            trace_count = len(analysis["traces"])
            total_traces += trace_count
            total_lines += analysis["lines"]

            density = (trace_count / analysis["lines"] * 100) if analysis["lines"] > 0 else 0

            report.append(f"\n{'─' * 70}")
            report.append(f"SECTION: {section_name.upper()}")
            report.append(f"{'─' * 70}")
            report.append(f"Lines: {analysis['lines']}")
            report.append(f"AI traces detected: {trace_count}")
            report.append(f"Density: {density:.1f}%")

            if trace_count > 0:
                report.append("\nTraces (first 5):")
                for i, trace in enumerate(analysis["traces"][:5], 1):
                    report.append(f"\n  [{i}] Line {trace['line']}")
                    report.append(f"      Patterns: {', '.join(trace['patterns'])}")
                    report.append(f"      Visible: {trace['visible'][:100]}")

        report.append("\n" + "=" * 70)
        report.append("SUMMARY")
        report.append("=" * 70)
        report.append(f"Total lines analyzed: {total_lines}")
        report.append(f"Total AI traces: {total_traces}")
        overall_density = (total_traces / total_lines * 100) if total_lines > 0 else 0
        report.append(f"Overall density: {overall_density:.1f}%")

        return "\n".join(report)

    def process_section_file(self, chapter_file: Path, output_dir: Path) -> bool:
        """Process a single chapter file."""
        if not chapter_file.exists():
            print(f"[ERROR] Chapter file not found: {chapter_file}")
            return False

        # Determine parser for the chapter file specifically
        chapter_parser = get_parser(chapter_file)
        comment_prefix = chapter_parser.get_comment_prefix()

        content = chapter_file.read_text(encoding="utf-8")
        lines = content.split("\n")

        processed_lines = []
        modifications = []

        for i, line in enumerate(lines, 1):
            stripped = line.strip()

            if not stripped or stripped.startswith(comment_prefix):
                processed_lines.append(line)
                continue

            visible = chapter_parser.extract_visible_text(stripped)
            patterns = self._check_ai_patterns(visible)

            if patterns:
                comment = f"{comment_prefix} DE-AI: Line {i} - {', '.join(patterns)}"
                processed_lines.append(comment)
                processed_lines.append(line)
                modifications.append(
                    {
                        "line": i,
                        "patterns": patterns,
                        "original": stripped,
                    }
                )
            else:
                processed_lines.append(line)

        output_file = output_dir / chapter_file.name
        output_file.write_text("\n".join(processed_lines), encoding="utf-8")

        print(f"[SUCCESS] Processed: {chapter_file.name}")
        print(f"         Output: {output_file}")
        print(f"         Modifications: {len(modifications)}")

        return True


def main():
    parser = argparse.ArgumentParser(
        description="Batch process LaTeX/Typst documents for de-AI editing"
    )

    parser.add_argument("file", type=Path, help="Main file (.tex or .typ)")
    parser.add_argument("--chapter", type=Path, help="Process specific chapter file")
    parser.add_argument("--all-sections", action="store_true", help="Analyze all sections")
    parser.add_argument("--section", type=str, help="Analyze specific section")
    parser.add_argument("--output", type=Path, help="Output directory for processed files")
    parser.add_argument("--report", type=Path, help="Save report to file")

    args = parser.parse_args()

    if not args.file.exists():
        print(f"[ERROR] File not found: {args.file}", file=sys.stderr)
        sys.exit(1)

    processor = DeAIBatchProcessor(args.file)

    if args.all_sections:
        analyses = {}
        for section_name in processor.section_ranges:
            analyses[section_name] = processor.analyze_section(section_name)

        report = processor.generate_batch_report(analyses)

        if args.report:
            args.report.write_text(report, encoding="utf-8")
            print(f"[SUCCESS] Report saved to: {args.report}")
        else:
            print(report)

    elif args.chapter:
        if not args.output:
            print("[ERROR] --output required when processing chapter file")
            sys.exit(1)

        args.output.mkdir(parents=True, exist_ok=True)
        success = processor.process_section_file(args.chapter, args.output)
        sys.exit(0 if success else 1)

    elif args.section:
        analysis = processor.analyze_section(args.section.lower())

        if not analysis["found"]:
            print(f"[WARNING] Section not found: {args.section}")
            sys.exit(1)

        print(f"\nSection: {args.section}")
        print(f"Lines: {analysis['lines']}")
        print(f"AI traces: {len(analysis['traces'])}\n")

        for trace in analysis["traces"][:10]:
            print(f"Line {trace['line']}:")
            print(f"  Patterns: {', '.join(trace['patterns'])}")
            print(f"  Text: {trace['visible'][:100]}")
            print()

    else:
        print(f"[INFO] Available sections in {args.file.name}:")
        for section_name in processor.section_ranges:
            start, end = processor.section_ranges[section_name]
            print(f"  - {section_name}: lines {start}-{end}")


if __name__ == "__main__":
    main()
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: 472kUpdated Claude CodeCodexVerifiedInstall
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: 472kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 196kUpdated Claude CodeCodexVerifiedInstall