home / skills / bahayonghang / my-claude-code-settings / latex-paper-en

latex-paper-en skill

safe

/content/skills/academic-skills/latex-paper-en

This skill assists writing and formatting English LaTeX papers across IEEE, ACM, Springer, NeurIPS, and ICML, improving clarity and coherence.

npx playbooks add skill bahayonghang/my-claude-code-settings --skill latex-paper-en

Review the files below or copy the command above to add this skill to your agents.

Files (39)

SKILL.md

6.4 KB

---
name: latex-paper-en
version: 1.2.0
category: academic-writing
tags:
  - latex
  - paper
  - english
  - ieee
  - acm
  - springer
  - neurips
  - icml
  - deep-learning
  - compilation
  - grammar
  - bibliography
description: |
  LaTeX academic paper assistant for English papers (IEEE, ACM, Springer, NeurIPS, ICML).
  Use when writing, reviewing, compiling, or improving English LaTeX academic papers.
  Use when user mentions compile, grammar, bibliography, deai, translate, title, logic,
  reviewer perspective, or any LaTeX paper quality improvement task.
  Domains: Deep Learning, Time Series, Industrial Control.
argument-hint: "[main.tex] [--section <section>] [--module <module>]"
allowed-tools: Read, Glob, Grep, Bash(python *), Bash(pdflatex *), Bash(xelatex *), Bash(latexmk *), Bash(bibtex *), Bash(biber *), Bash(chktex *)
references:
  - resources/references/STYLE_GUIDE.md
  - resources/references/COMMON_ERRORS.md
  - resources/references/VENUES.md
  - resources/references/FORBIDDEN_TERMS.md
  - resources/references/TERMINOLOGY.md
  - resources/references/TRANSLATION_GUIDE.md
  - resources/references/DEAI_GUIDE.md
  - resources/references/WRITING_PHILOSOPHY.md
  - resources/references/REVIEWER_PERSPECTIVE.md
  - resources/references/CITATION_VERIFICATION.md
  - resources/references/COMPILATION.md
  - resources/references/BEST_PRACTICES.md
scripts:
  - scripts/compile.py
  - scripts/check_format.py
  - scripts/check_figures.py
  - scripts/verify_bib.py
  - scripts/analyze_grammar.py
  - scripts/analyze_sentences.py
  - scripts/analyze_logic.py
  - scripts/improve_expression.py
  - scripts/translate_academic.py
  - scripts/optimize_title.py
  - scripts/deai_check.py
  - scripts/deai_batch.py
  - scripts/extract_prose.py
  - scripts/parsers.py
---

# LaTeX Academic Paper Assistant (English)

## Critical Rules

1. NEVER modify `\cite{}`, `\ref{}`, `\label{}`, math environments
2. NEVER fabricate bibliography entries
3. NEVER change domain terminology without confirmation
4. ALWAYS output suggestions in diff-comment format first

## Argument Conventions ($ARGUMENTS)

- Use `$ARGUMENTS` to capture user-provided inputs (main `.tex` path, target section, module choice).
- If `$ARGUMENTS` is missing or ambiguous, ask for: main `.tex` path, target scope, and desired module.
- Treat file paths as literal; do not guess missing paths.

## Execution Guardrails

- Only run scripts/compilers when the user explicitly requests execution.
- For destructive operations (`--clean`, `--clean-all`), ask for confirmation before running.

## Unified Output Protocol (All Modules)

Each suggestion MUST include fixed fields:
- **Severity**: Critical / Major / Minor
- **Priority**: P0 (blocking) / P1 (important) / P2 (nice-to-have)

**Default comment template** (diff-comment style):
```latex
% <MODULE> (Line <N>) [Severity: <Critical|Major|Minor>] [Priority: <P0|P1|P2>]: <Issue summary>
% Original: ...
% Revised:  ...
% Rationale: ...
% ⚠️ [PENDING VERIFICATION]: <if evidence/metric is required>
```

## Failure Handling (Global)

If a tool/script cannot run, respond with a comment block including the reason and a safe next step:
```latex
% ERROR [Severity: Critical] [Priority: P0]: <short error>
% Cause: <missing file/tool or invalid path>
% Action: <install tool / verify file path / re-run command>
```
Common cases:
- **Script not found**: confirm `scripts/` path and working directory
- **LaTeX tool missing**: suggest installing TeX Live/MiKTeX or adding to PATH
- **File not found**: ask user to provide the correct `.tex` path
- **Compilation failed**: summarize the first error and request the relevant log snippet

## Modules (Independent, Pick Any)

| Module | Trigger Keywords | Script | Details |
|--------|-----------------|--------|---------|
| Compile | compile, 编译, build | `python scripts/compile.py main.tex` | [COMPILE.md](resources/modules/COMPILE.md) |
| Format Check | format, chktex, lint | `python scripts/check_format.py main.tex` | [FORMAT.md](resources/modules/FORMAT.md) |
| Grammar | grammar, 语法, proofread | `python scripts/analyze_grammar.py main.tex` | [GRAMMAR.md](resources/modules/GRAMMAR.md) |
| Sentences | long sentence, 长句 | `python scripts/analyze_sentences.py main.tex` | [SENTENCES.md](resources/modules/SENTENCES.md) |
| Expression | academic tone, 学术表达 | `python scripts/improve_expression.py main.tex` | [EXPRESSION.md](resources/modules/EXPRESSION.md) |
| Logic | logic, coherence, methodology | `python scripts/analyze_logic.py main.tex` | [LOGIC.md](resources/modules/LOGIC.md) |
| Translation | translate, 翻译, 中译英 | `python scripts/translate_academic.py "text"` | [TRANSLATION.md](resources/modules/TRANSLATION.md) |
| Bibliography | bib, bibliography | `python scripts/verify_bib.py refs.bib` | [BIBLIOGRAPHY.md](resources/modules/BIBLIOGRAPHY.md) |
| De-AI | deai, 去AI化, humanize | `python scripts/deai_check.py main.tex` | [DEAI.md](resources/modules/DEAI.md) |
| Title | title, 标题 | `python scripts/optimize_title.py main.tex` | [TITLE.md](resources/modules/TITLE.md) |
| Reviewer | reviewer, 审稿, checklist | — | [REVIEWER_PERSPECTIVE.md](resources/references/REVIEWER_PERSPECTIVE.md) |
| Workflow | workflow, full review | — | [WORKFLOW.md](resources/modules/WORKFLOW.md) |

## Best Practices & Venue Rules
Load additional context from:
- [VENUES.md](resources/references/VENUES.md): Specific rules for IEEE, ACM, Springer, NeurIPS, ICML
- [BEST_PRACTICES.md](resources/references/BEST_PRACTICES.md): General workflow recommendations

## References

- [STYLE_GUIDE.md](resources/references/STYLE_GUIDE.md): Academic writing rules
- [COMMON_ERRORS.md](resources/references/COMMON_ERRORS.md): Chinglish patterns
- [VENUES.md](resources/references/VENUES.md): Conference/journal requirements
- [FORBIDDEN_TERMS.md](resources/references/FORBIDDEN_TERMS.md): Protected terminology
- [TERMINOLOGY.md](resources/references/TERMINOLOGY.md): Domain terminology (DL/TS/IC)
- [TRANSLATION_GUIDE.md](resources/references/TRANSLATION_GUIDE.md): Translation guide
- [DEAI_GUIDE.md](resources/references/DEAI_GUIDE.md): De-AI writing guide and patterns
- [WRITING_PHILOSOPHY.md](resources/references/WRITING_PHILOSOPHY.md): Writing philosophy
- [REVIEWER_PERSPECTIVE.md](resources/references/REVIEWER_PERSPECTIVE.md): Reviewer checklist
- [CITATION_VERIFICATION.md](resources/references/CITATION_VERIFICATION.md): Citation verification
- [COMPILATION.md](resources/references/COMPILATION.md): Compilation recipes

Overview

This skill is a LaTeX academic paper assistant for English papers, tailored to IEEE, ACM, Springer, NeurIPS, and ICML formats in Deep Learning, Time Series, and Industrial Control domains. It provides modular actions: compilation, format checks, grammar and style polishing, logical and methodological review, Chinese→English translation with domain-aware terminology, bibliography validation, and de-AI editing. All suggestions are returned as diff-style LaTeX comments with severity and priority metadata.

How this skill works

You invoke a module by a trigger word (e.g., "compile", "grammar", "translate") and provide $ARGUMENTS: main .tex path, target scope, and module choice. The skill analyzes the specified scope and outputs suggested edits in a strict diff-comment format, preserves citations/math/labels, and never fabricates bibliography entries. Execution of scripts or compilers is performed only when explicitly requested, and destructive operations prompt confirmation.

When to use it

When you need a reliable build using latexmk or a specific LaTeX recipe (xelatex/pdflatex/biber/bibtex).
Before submission to ensure formatting, linting, and journal/conference style compliance.
To proofread and polish English grammar, article usage, and academic tone in manuscript sections.
To check long sentences (>50 words) and simplify them into clear core + subordinate structure.
To strengthen logical flow, justify methodology choices, and ensure reproducibility details.
When translating Chinese technical text to English with domain-aware terminology confirmation.

Best practices

Always provide $ARGUMENTS: main .tex path, the exact section or line range, and the desired module.
Do not request automatic execution of compilation or cleaning without explicit consent; confirm before destructive flags (--clean, --clean-all).
Preserve all \cite{}, \ref{}, \label{}, and math environments; request confirmation before changing domain terminology.
Use the default latexmk recipe for full builds; request specific recipes only for custom workflows.
Supply bibliography files when asking for citation checks; never add or invent bibliographic entries.

Example use cases

Run the Compile module to produce a PDF with latexmk and capture the first compilation errors.
Use Grammar Analysis on the Methods section to fix article usage, tense, and subject-verb agreement with inline diff comments.
Apply Long Sentence Analysis to Results to decompose sentences with >50 words and suggest concise rewrites.
Invoke Logical Coherence & Methodological Depth to add transitions, justify design choices, and checklist reproducibility items.
Translate a Chinese paragraph about attention mechanisms into English, confirming domain-specific terms before finalizing.

FAQ

Will the tool change my \cite{} or math environments?

No. It never modifies \cite{}, \ref{}, \label{}, or math environments; suggestions are provided as non-destructive diff-style comments.

Can you run a full compilation automatically?

Yes, but only when you explicitly request it. Destructive options require confirmation and missing tools trigger a clear error block with next steps.