An agentic skills framework & software development methodology that works.
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.
Builders who write or review LaTeX papers with agent tools and want repeatable help for common academic workflows.
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
- 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/ - 2One skill only
cp -r awesome-latex-skills/latex-rescue ~/.claude/skills/
- 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
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
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 AM —
latex-rescueauto-corrects typos, fixes mismatched environments, resolves package conflicts. 80+ patterns, zero manual edits. - "English needs improvement" from Reviewer #2 —
latex-polishfixes 18 categories of Chinglish, applies 100+ academic phrasebank templates, adds proper hedging. 3 intensity levels. - CVPR rejected, ICML deadline Friday —
latex-fmtswitches\documentclass, removes banned packages, anonymizes, checks page limits. 15 venues covered. - 50 papers in your reading list —
paper-readproduces 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 PDF —
pdf2texrebuilds 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-rescue | Fix compilation errors — 80+ auto-fix patterns, package conflicts, Overleaf support |
| :pencil2: | latex-polish | Polish academic writing — 18 Chinglish categories, 100+ phrasebank templates, 3 intensity levels |
| :repeat: | latex-fmt | Reformat between 15 venues — NeurIPS · ICML · CVPR · ACL · ICLR · ECCV · AAAI · TMLR · IEEE · Nature · Science · COLING · KDD · SIGIR · Interspeech |
| :book: | paper-read | Read & analyze papers — skim / read / deep, 50+ critical appraisal items, assumption auditing |
| :wrench: | pdf2tex | Rebuild LaTeX from PDF — 7-phase pipeline, 97+ math glyph mappings, table reconstruction |
| 80+ error patterns | 14 package conflicts | 18 Chinglish categories | 100+ phrasebank templates |
| 15 venue rules | 50+ appraisal items | 97+ glyph mappings | 15 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 does | What the skill pack does |
|---|---|---|
\beginn{table} | "That's an interesting typo" | Auto-corrects to \begin{table} |
| "According to the experiment" | Accepts it | Flags overuse, suggests alternatives |
| "Format for NeurIPS" | Forgets Broader Impact | Flags missing required section |
| "Convert this PDF to LaTeX" | Produces broken markup | 7-phase pipeline with verification |
\citep{} without natbib | Silently ignores | Detects missing package, adds it |
| "Polish my paper" | Rewrites everything | Minimal 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:
| Scenario | What you type | What happens |
|---|---|---|
| Deadline crunch | /latex-rescue | Crash → rescue → compile |
| Review turnaround | /latex-polish → /latex-fmt | Draft → polish → format → submit |
| Rebuttal reformat | /latex-polish → /latex-fmt | CVPR reject → polish → reformat for ICML |
| Lost source | /pdf2tex → /latex-rescue | PDF → reconstruct → fix → compile |
| New paper | /paper-read → /latex-polish → /latex-fmt | Read papers → polish → format for venue |
| Overleaf | /latex-rescue | Paste 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
| Platform | How to use |
|---|---|
| Claude Code | Copy to ~/.claude/skills/, invoke with /latex-rescue |
| ChatGPT / GPT-4 | Paste SKILL.md as custom instruction or system prompt |
| Cursor | Add SKILL.md content to .cursor/rules/ |
| Copilot | Add SKILL.md content to .github/copilot-instructions.md |
| Any LLM | Send 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
- You type
/latex-rescueor say "fix my LaTeX errors" - Agent loads
SKILL.md— now it has a structured workflow + guardrails - It reads
references/for precise domain rules at each phase - Same workflow → same expert output, every time
License
MIT
Files in the repo
- .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 itSign in to join the discussion.
No comments yet. Be the first to say what this is good for.
More skills

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.
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.
Public repository for Agent Skills
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…)

Production-grade engineering skills for AI coding agents.