- Home
- Skills
- Bahayonghang
- My Claude Code Settings
- Latex Paper En
latex-paper-en_skill
- Python
10
GitHub Stars
2
Bundled Files
2 months ago
Catalog Refreshed
4 months ago
First Indexed
Readme & install
Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.
Installation
Preview and clipboard use veilstrat where the catalogue uses aiagentskills.
npx veilstrat add skill bahayonghang/my-claude-code-settings --skill latex-paper-en- README.md6.0 KB
- SKILL.md6.4 KB
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
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.