# agent-research-skills: a set by lingzhi227

The lingzhi227/agent-research-skills repository on GitHub: 31 cards with a description and an install command. They work in Claude Code, Codex, Cursor — 8 platforms in total.

31 cards

- HTML: https://affpapa.org/en/nevibecode/by/lingzhi227/agent-research-skills
- Instructions for agents: https://affpapa.org/en/nevibecode/agents.md

- [excalidraw-skill](https://affpapa.org/en/nevibecode/skills/excalidraw-skill.md) — skill · lingzhi227 · Claude Code, Codex, Cursor +5 · 1600 installs — A skill that connects an agent to a live Excalidraw canvas so it can draw, adjust and export diagrams.
- [literature-review](https://affpapa.org/en/nevibecode/skills/lingzhi227-literature-review.md) — skill · lingzhi227 · Claude Code, Codex, Cursor +5 · 4100 installs — Conducts academic literature reviews by simulating multi-persona expert dialogue.
- [literature-search](https://affpapa.org/en/nevibecode/skills/literature-search.md) — skill · lingzhi227 · Claude Code, Codex, Cursor +5 · 2700 installs — The literature-search skill queries Semantic Scholar, arXiv, and OpenAlex for peer-reviewed and preprint papers, returning structured results with authors, year, citation count, and BibTeX.
- [backward-traceability](https://affpapa.org/en/nevibecode/skills/backward-traceability.md) — skill · lingzhi227 · Claude Code, Codex, Cursor +5 · 2300 installs — backward-traceability connects every numeric value in a research PDF directly to the source code line that produced it.
- [math-reasoning](https://affpapa.org/en/nevibecode/skills/math-reasoning.md) — skill · lingzhi227 · Claude Code, Codex, Cursor +5 · 2300 installs — math-reasoning derives equations, writes proofs, formalizes research problems, and produces publication-ready LaTeX markup for research papers.
- [latex-formatting](https://affpapa.org/en/nevibecode/skills/latex-formatting.md) — skill · lingzhi227 · Claude Code, Codex, Cursor +5 · 2300 installs — latex-formatting sets up conference LaTeX templates, fixes formatting, and runs a pre-submission check.
- [figure-generation](https://affpapa.org/en/nevibecode/skills/figure-generation.md) — skill · lingzhi227 · Claude Code, Codex, Cursor +5 · 2300 installs — figure-generation builds publication-ready scientific plots through query expansion, code execution, and visual verification.
- [citation-management](https://affpapa.org/en/nevibecode/skills/lingzhi227-citation-management.md) — skill · lingzhi227 · Claude Code, Codex, Cursor +5 · 2200 installs — citation-management — a skill that keeps citations in a LaTeX paper in order: harvests missing references via Semantic Scholar, validates cite keys against .bib, and formats the bibliography.
- [data-analysis](https://affpapa.org/en/nevibecode/skills/lingzhi227-data-analysis.md) — skill · lingzhi227 · Claude Code, Codex, Cursor +5 · 2100 installs — data-analysis writes statistical analysis code for a paper: picks a test that fits the data and reports p-values, effect sizes and confidence intervals.
- [deep-research](https://affpapa.org/en/nevibecode/skills/lingzhi227-deep-research.md) — skill · lingzhi227 · Claude Code, Codex, Cursor +5 · 2000 installs — deep-research runs a systematic academic literature review on a topic: finds papers, reads them, builds a database and writes a final report.
- [paper-revision](https://affpapa.org/en/nevibecode/skills/paper-revision.md) — skill · lingzhi227 · Claude Code, Codex, Cursor +5 · 1900 installs — paper-revision is a skill for Claude Code that maps reviewer comments to paper sections and applies targeted edits, marking revised passages with \textcolor{blue}{...}.
- [paper-writing-section](https://affpapa.org/en/nevibecode/skills/paper-writing-section.md) — skill · lingzhi227 · Claude Code, Codex, Cursor +5 · 1900 installs — paper-writing-section — a skill that drafts or reworks a single section of an academic paper, from abstract to conclusion.
- [novelty-assessment](https://affpapa.org/en/nevibecode/skills/novelty-assessment.md) — skill · lingzhi227 · Claude Code, Codex, Cursor +5 · 1900 installs — novelty-assessment runs a research idea through literature search and returns a verdict: novel or not.
- [idea-generation](https://affpapa.org/en/nevibecode/skills/lingzhi227-idea-generation.md) — skill · lingzhi227 · Claude Code, Codex, Cursor +5 · 1900 installs — idea-generation — a skill that generates research ideas, refines them over several rounds and checks novelty against the literature.
- [algorithm-design](https://affpapa.org/en/nevibecode/skills/algorithm-design.md) — skill · lingzhi227 · Claude Code, Codex, Cursor +5 · 1800 installs — algorithm-design is a Claude Code skill that turns a method description or implementation into LaTeX pseudocode and Mermaid diagrams to formalize an algorithm and check its representation against code.
- [survey-generation](https://affpapa.org/en/nevibecode/skills/survey-generation.md) — skill · lingzhi227 · Claude Code, Codex, Cursor +5 · 1800 installs — survey-generation walks an agent through paper collection, outlining, writing and citation checking, then hands back a LaTeX survey with a .bib file.
- [research-planning](https://affpapa.org/en/nevibecode/skills/research-planning.md) — skill · lingzhi227 · Claude Code, Codex, Cursor +5 · 1800 installs — research-planning is a Claude Code skill that builds research plans with methodology, dependencies, paper structure and UML diagrams.
- [github-research](https://affpapa.org/en/nevibecode/skills/github-research.md) — skill · lingzhi227 · Claude Code, Codex, Cursor +5 · 1800 installs — github-research finds open-source repositories matching research topics, inspects their codebases, and produces an integration blueprint.
- [experiment-design](https://affpapa.org/en/nevibecode/skills/experiment-design.md) — skill · lingzhi227 · Claude Code, Codex, Cursor +5 · 1800 installs — experiment-design is a Claude Code skill that turns research ideas into staged experiments with baselines, datasets, metrics, and ablations.
- [experiment-code](https://affpapa.org/en/nevibecode/skills/experiment-code.md) — skill · lingzhi227 · Claude Code, Codex, Cursor +5 · 1700 installs — Writes and iterates on ML experiment code for a research paper: training, evaluation, debugging, plots.
- [paper-to-code](https://affpapa.org/en/nevibecode/skills/paper-to-code.md) — skill · lingzhi227 · Claude Code, Codex, Cursor +5 · 1700 installs — paper-to-code turns an ML research paper into a runnable code repository.
- [atomic-decomposition](https://affpapa.org/en/nevibecode/skills/atomic-decomposition.md) — skill · lingzhi227 · Claude Code, Codex, Cursor +5 · 1700 installs — atomic-decomposition splits a research idea into atomic concepts, then finds the math formula in papers and the matching code for each one.
- [paper-compilation](https://affpapa.org/en/nevibecode/skills/paper-compilation.md) — skill · lingzhi227 · Claude Code, Codex, Cursor +5 · 1700 installs — paper-compilation compiles a LaTeX paper to PDF, catches build errors and checks citations and references.
- [slide-generation](https://affpapa.org/en/nevibecode/skills/slide-generation.md) — skill · lingzhi227 · Claude Code, Codex, Cursor +5 · 1700 installs — slide-generation turns a completed LaTeX paper into Beamer presentation slides or a poster.
- [self-review](https://affpapa.org/en/nevibecode/skills/self-review.md) — skill · lingzhi227 · Claude Code, Codex, Cursor +5 · 1700 installs — The self-review skill reviews an academic paper with the NeurIPS form, three reviewer roles, and score aggregation.
- [table-generation](https://affpapa.org/en/nevibecode/skills/table-generation.md) — skill · lingzhi227 · Claude Code, Codex, Cursor +5 · 1700 installs — table-generation — a skill for Claude Code, Codex, Cursor and other platforms that converts JSON and CSV into publication-ready LaTeX tables with best-result highlighting, multirow layouts and captions.
- [related-work-writing](https://affpapa.org/en/nevibecode/skills/related-work-writing.md) — skill · lingzhi227 · Claude Code, Codex, Cursor +5 · 1700 installs — related-work-writing drafts publication-ready Related Work sections by grouping literature thematically and contrasting previous approaches with your method.
- [rebuttal-writing](https://affpapa.org/en/nevibecode/skills/rebuttal-writing.md) — skill · lingzhi227 · Claude Code, Codex, Cursor +5 · 1700 installs — rebuttal-writing turns reviewer comments on a paper into a structured, point-by-point rebuttal backed by evidence from the manuscript.
- [code-debugging](https://affpapa.org/en/nevibecode/skills/code-debugging.md) — skill · lingzhi227 · Claude Code, Codex, Cursor +5 · 1700 installs — code-debugging is a Claude Code skill that structures debugging for ML experiments and research code.
- [symbolic-equation](https://affpapa.org/en/nevibecode/skills/symbolic-equation.md) — skill · lingzhi227 · Claude Code, Codex, Cursor +5 · 1600 installs — symbolic-equation discovers scientific equations from numerical datasets using LLM-guided evolutionary search.
- [paper-assembly](https://affpapa.org/en/nevibecode/skills/paper-assembly.md) — skill · lingzhi227 · Claude Code, Codex, Cursor +5 · 1600 installs — paper-assembly runs a research-paper workflow from literature and experiments through LaTeX, PDF compilation, and review, with checkpoints for resuming work.

## Narrow this list
Parameters: `?platform=<claude-code|codex|cursor|copilot|gemini-cli|windsurf|…>`, `&topic=<…>`, `&sort=installs|stars|new|updated` — values in https://affpapa.org/en/nevibecode/agents.md

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
