Sandbox
@Calix-L/awesome-latex-skills

LaTeX skills for Claude Code and other agents

This repository packages five LaTeX-focused skills that an agent can load as reusable workflows. They help with compilation errors, paper polish, venue formatting, paper reading, and reconstructing source from PDFs.

173 stars3 forksShellUpdated 4mo ago
Who it's for

Builders who write or review LaTeX papers with agent tools and want repeatable help for common academic workflows.

What it delivers

You can turn a general agent into a LaTeX helper that fixes, rewrites, formats, reads, and reconstructs papers with less re-explaining.

What it does

latex-rescue

Fixes compilation errors, package conflicts, mismatched environments, and common LaTeX typos.

latex-polish

Rewrites academic prose with Chinglish fixes, phrasebank templates, and different intensity levels.

latex-fmt

Reformats papers for venues like NeurIPS, ICML, CVPR, ACL, and others, including anonymization and page checks.

paper-read

Produces skim, read, or deep analyses of papers with structured appraisal items and assumption checks.

pdf2tex

Rebuilds LaTeX source from a compiled PDF using a staged recovery pipeline and glyph mappings.

How to get it

  1. 1One command to install all 5 skills
    git clone https://github.com/Calix-L/awesome-latex-skills.git && \
    cp -r awesome-latex-skills/{latex-rescue,latex-polish,latex-fmt,paper-read,pdf2tex} ~/.claude/skills/
  2. 2One skill only
    cp -r awesome-latex-skills/latex-rescue ~/.claude/skills/
  3. 3Not using Claude Code? Just point your agent to the SKILL.md
    Read awesome-latex-skills/latex-rescue/SKILL.md and follow the workflow.

README

中文文档

awesome-latex-skills

Every researcher knows the feeling.

47 compilation errors at 2 AM. A reviewer who writes "English needs improvement." A CVPR reject that needs to become an ICML submission by Friday.

awesome-latex-skills turns any AI agent into a LaTeX expert — structured workflows, curated knowledge, and guardrails that raw prompts can't replicate.


47 errors → 0  ·  Chinglish → publication-ready  ·  CVPR → NeurIPS  ·  50 pages → structured notes


CI 5 skills 168 tests Stars MIT


10-Second Pitch · Skills · Demos · Workflows · Quick Start · Compatibility


10-Second Pitch

You describe the problem. The skill produces the fix.

  • 47 compilation errors at 2 AMlatex-rescue auto-corrects typos, fixes mismatched environments, resolves package conflicts. 80+ patterns, zero manual edits.
  • "English needs improvement" from Reviewer #2latex-polish fixes 18 categories of Chinglish, applies 100+ academic phrasebank templates, adds proper hedging. 3 intensity levels.
  • CVPR rejected, ICML deadline Fridaylatex-fmt switches \documentclass, removes banned packages, anonymizes, checks page limits. 15 venues covered.
  • 50 papers in your reading listpaper-read produces a 5-bullet skim in 30 seconds, a structured analysis in 5 minutes, or a full critical review in 15.
  • Lost the .tex, only the PDFpdf2tex rebuilds LaTeX from any compiled PDF. 97+ math glyph mappings, table reconstruction, 7-phase pipeline.

No LaTeX expertise required. The skill handles the semicolons.


Skills

:ambulance:latex-rescueFix compilation errors — 80+ auto-fix patterns, package conflicts, Overleaf support
:pencil2:latex-polishPolish academic writing — 18 Chinglish categories, 100+ phrasebank templates, 3 intensity levels
:repeat:latex-fmtReformat between 15 venues — NeurIPS · ICML · CVPR · ACL · ICLR · ECCV · AAAI · TMLR · IEEE · Nature · Science · COLING · KDD · SIGIR · Interspeech
:book:paper-readRead & analyze papers — skim / read / deep, 50+ critical appraisal items, assumption auditing
:wrench:pdf2texRebuild LaTeX from PDF — 7-phase pipeline, 97+ math glyph mappings, table reconstruction
80+ error patterns14 package conflicts18 Chinglish categories100+ phrasebank templates
15 venue rules50+ appraisal items97+ glyph mappings15 reference files

Why skills, not just prompts?

You've tried asking ChatGPT to fix your LaTeX. It guesses. It misses things. It changes your math.

You say...What the raw LLM doesWhat the skill pack does
\beginn{table}"That's an interesting typo"Auto-corrects to \begin{table}
"According to the experiment"Accepts itFlags overuse, suggests alternatives
"Format for NeurIPS"Forgets Broader ImpactFlags missing required section
"Convert this PDF to LaTeX"Produces broken markup7-phase pipeline with verification
\citep{} without natbibSilently ignoresDetects missing package, adds it
"Polish my paper"Rewrites everythingMinimal edits, preserves math & commands

Skills inject hundreds of domain-specific rules that LLMs can't reliably recall from memory. Each skill = structured workflow + reference knowledge + guardrails. Same input, same expert output, every time.


Demos

:ambulance: latex-rescue — 2 AM, 47 errors, deadline tomorrow

- \textbff{bold}              → Undefined control sequence
+ \textbf{bold}               → auto-fixed

- x_i is important            → Missing $ inserted
+ $x_i$ is important          → auto-fixed

- \begin{figure}...\end{table}
+ \begin{figure}...\end{figure}  → mismatch fixed

:pencil2: latex-polish — Reviewer #2 says "English needs improvement"

- The model can achieves good performance on the dataset.
+ The model achieves strong performance on the benchmark.

- According to the experiment, it makes the accuracy improved by 3.2%.
+ Experiments show that the method improves accuracy by 3.2%.

- Most of methods in this research field can not achieve the same result.
+ Most methods in this field fail to match this result.

:repeat: latex-fmt — Camera-ready reformat, CVPR → NeurIPS

- \documentclass{article}
+ \documentclass{neurips_2025}
- \author{Zhang et al.}
+ \author{Anonymous}
- (no Broader Impact section)
+ ⚠ Broader Impact required by NeurIPS — flagged

:book: paper-read — 50 papers in your reading list, no time

- "This paper proposes a novel transformer-based approach for..."
+ [skim] Object detection · Wang et al., CVPR 2024
+        Novelty: sparse attention for real-time. Verdict: worth deep read.

- (reading every paper front-to-back)
+ [deep] Key eq: sparse attention. Delta: 10x faster.
+        Gap: only tested on COCO. Overclaim: "SOTA" (margin 0.3%).

:wrench: pdf2tex — Lost the .tex, only the PDF survives

- (staring at a compiled PDF, no source files)
+ \documentclass{article}
+ \usepackage{amsmath,amssymb}
+ \section{Introduction}
+ The model achieves $F_1 = 92.3$ on the benchmark.
+ % [UNCERTAIN: math notation — verify subscripts]

Workflows

Skills compose into pipelines for real academic scenarios:

ScenarioWhat you typeWhat happens
Deadline crunch/latex-rescueCrash → rescue → compile
Review turnaround/latex-polish/latex-fmtDraft → polish → format → submit
Rebuttal reformat/latex-polish/latex-fmtCVPR reject → polish → reformat for ICML
Lost source/pdf2tex/latex-rescuePDF → reconstruct → fix → compile
New paper/paper-read/latex-polish/latex-fmtRead papers → polish → format for venue
Overleaf/latex-rescuePaste error log → get fixes

Quick Start

One command to install all 5 skills:

git clone https://github.com/Calix-L/awesome-latex-skills.git && \
cp -r awesome-latex-skills/{latex-rescue,latex-polish,latex-fmt,paper-read,pdf2tex} ~/.claude/skills/

Then just type /latex-rescue, /latex-polish, etc. in Claude Code.

One skill only:

cp -r awesome-latex-skills/latex-rescue ~/.claude/skills/

Not using Claude Code? Just point your agent to the SKILL.md:

Read awesome-latex-skills/latex-rescue/SKILL.md and follow the workflow.

No install needed for latex-polish, latex-fmt, or paper-read. latex-rescue needs LaTeX. pdf2tex needs pip install pymupdf.


Compatibility

PlatformHow to use
Claude CodeCopy to ~/.claude/skills/, invoke with /latex-rescue
ChatGPT / GPT-4Paste SKILL.md as custom instruction or system prompt
CursorAdd SKILL.md content to .cursor/rules/
CopilotAdd SKILL.md content to .github/copilot-instructions.md
Any LLMSend SKILL.md as context, then ask your question

How it works

Each skill is a self-contained directory:

latex-rescue/
├── SKILL.md              # the prompt — role, triggers, workflow, guardrails
├── references/           # domain knowledge the agent reads at each phase
│   ├── error-catalog.md
│   ├── package-conflicts.md
│   └── debug-workflow.md
└── agents/
    └── config.yaml       # auto-activation triggers and platform settings
  1. You type /latex-rescue or say "fix my LaTeX errors"
  2. Agent loads SKILL.md — now it has a structured workflow + guardrails
  3. It reads references/ for precise domain rules at each phase
  4. Same workflow → same expert output, every time

License

MIT

Files in the repo

Repository payload14 top-level entries
  • .github
  • assets
  • latex-fmt
  • latex-polish
  • latex-rescue
  • paper-read
  • pdf2tex
  • tests
  • .gitignore
  • CHANGELOG.md
  • CONTRIBUTING.md
  • LICENSE
  • README_CN.md
  • README.md

Discussion (0)

Ask about usage, or say what you built with it

Sign in to join the discussion.

No comments yet. Be the first to say what this is good for.

More skills

obra/
superpowers

An agentic skills framework & software development methodology that works.

285k
1 add

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.

117k
1 add
Vincentwei1021/
anything2explainer

Topic in, narrated explainer video out. A Claude Code / Codex skill that turns any topic into a black-canvas motion-graphics explainer video with TTS voiceover, subtitles and a chapter progress bar. Chinese or English; every frame drawn in code with Remotion.

666

Open-source AI job search: scan job portals, evaluate listings into a structured A-H report with a global 1-5 score, tailor your CV, track applications — runs locally in your AI coding CLI (Claude Code, Codex, OpenCode, Antigravity…)

71k