latex
Produces compilable LaTeX for researchers in numerical optimisation and applied mathematics. Use for theorems, proofs, convergence analysis, algorithms, tables, TikZ figures, derivations, literature reviews, or structured academic documents, and for requests such as "write up", "typeset", "format in LaTeX", "produce a .tex file", or "give me the LaTeX for". Covers numerical optimisation, nonlinear equations, deep learning theory, and numerical analysis; inverse problems, EIT, and PINNs are supported through an optional reference file. Three modes: (1) DOCUMENT MODE, a full standalone article; (2) SNIPPET MODE, body-only fragments; (3) BEAMER MODE, complete Beamer slides, used for "slides", "presentation", "beamer", "talk", "seminar", "slide deck". Also use when the user supplies a website URL and wants LaTeX output, e.g. "turn this link into LaTeX", "make slides from this page", or "convert this article to a report"; the page is fetched and routed to the correct mode.
Install
git clone https://github.com/hameefy/claude-latex-skill ~/.claude/skills/latexFrom README
LaTeX Skill This skill governs the production of LaTeX output for researchers in numerical optimisation and applied mathematics: unconstrained and constrained optimisation, nonlinear equations, conjugate gradient and quasi-Newton methods, stochastic optimisation, deep learning theory, and numerical analysis. All output must satisfy the mathematical standards of journals such as SIAM Journal on Optimization, Mathematical Programming, Optimization Methods and Software, and Mathematics of Computation. Inverse problems, electrical impedance tomography (EIT), regularisation theory, and PINNs are covered by the optional file references/inverse-problems.md (notation, macros, and reference entries). Read it only when the request concerns those areas. If the file is not installed, proceed with the rules in this file. --- Step 0. Detect and Ingest Web Content (URL Input) Run this step FIRST, before Step 1, whenever the user provides a URL or web link.