mit einem Klick
paper-skill-latex
paper-skill-latex enthält 6 gesammelte Skills von Fanceir, mit Repository-Berufsabdeckung und Skill-Detailseiten auf SkillsMP.
Skills in diesem Repository
create, revise, validate, and compile latex paper projects, especially ml/ai review papers for arxiv using ieeetran-style structure, verified bibtex citations, plan/issues workflow, and two-column layout hygiene. also use when scanning a codebase to produce paper-ready figure prompts and source for draw.io, excalidraw, and tikz. triggers include requests to write an arxiv review article, scaffold a latex paper, validate citations, compile/qa a paper, generate paper diagrams from a repo, create tikz figures, or produce thesis/research-paper architecture diagrams.
Extract figures-worthy artifacts (architecture, module graph, data pipeline, training/inference loop, model structure, ablation results) from a source codebase and emit ready-to-paste prompts or source for draw.io (mxGraph XML), Excalidraw (scene descriptor / Mermaid fallback), and TikZ (LaTeX source). Use ONLY for paper figures and diagrams — thesis (毕业设计), ML/AI conference/journal paper, arXiv preprint, system-design writeup. Output is prompt / source text only; the skill never renders, compiles, exports, or invokes any image / AI-diagram plugin itself. Pair with `arxiv-paper-writer` when you also need manuscript drafting, citation work, or full paper scaffolding — this skill stays strictly in the figure lane.
Write LaTeX ML/AI review articles for arXiv using the IEEEtran template and verified BibTeX citations.
Use the Claude Code CLI to consult Claude and delegate coding tasks for prototyping, debugging, and code review. Supports multi-turn sessions via SESSION_ID. Optimized for low-token, file/line-based handoff.
Use the Gemini CLI to consult Gemini and delegate coding tasks for prototyping, debugging, and code review. Supports multi-turn sessions via SESSION_ID. Optimized for low-token, file/line-based handoff.
Post-process LaTeX project prose to improve readability through varied sentence and paragraph lengths. Removes filler phrases and unnecessary transitions while preserving all citations and semantic meaning.