# auto-claude-code-research-in-sleep: a set by wanshuiyin

The wanshuiyin/auto-claude-code-research-in-sleep repository on GitHub: 83 cards with a description and an install command. They work in Claude Code, Codex, Cursor — 8 platforms in total.

83 cards · page 1 of 3

- HTML: https://affpapa.org/en/nevibecode/by/wanshuiyin/auto-claude-code-research-in-sleep
- Instructions for agents: https://affpapa.org/en/nevibecode/agents.md

- [semantic-scholar](https://affpapa.org/en/nevibecode/skills/semantic-scholar.md) — skill · wanshuiyin · Claude Code, Codex, Cursor +5 · 705 installs — Finds journal and conference papers through the Semantic Scholar API: venue metadata, citation counts and a one-line summary.
- [paper-figure](https://affpapa.org/en/nevibecode/skills/paper-figure.md) — skill · wanshuiyin · Claude Code, Codex, Cursor +5 · 687 installs — A skill that writes the plotting code for a research paper: figures from experiment results plus comparison tables.
- [research-lit](https://affpapa.org/en/nevibecode/skills/research-lit.md) — skill · wanshuiyin · Claude Code, Codex, Cursor +5 · 679 installs — research-lit — a Claude Code skill that finds academic papers, locates related work, and builds short summaries of key ideas.
- [idea-discovery](https://affpapa.org/en/nevibecode/skills/idea-discovery.md) — skill · wanshuiyin · Claude Code, Codex, Cursor +5 · 639 installs — idea-discovery automates the research ideation pipeline from paper surveys to novelty verification, review, and pilot plans.
- [idea-creator](https://affpapa.org/en/nevibecode/skills/idea-creator.md) — skill · wanshuiyin · Claude Code, Codex, Cursor +5 · 635 installs — idea-creator — a skill for Claude Code, Codex, Cursor and other platforms that systematically generates, validates and ranks research ideas from a broad direction.
- [auto-review-loop](https://affpapa.org/en/nevibecode/skills/auto-review-loop.md) — skill · wanshuiyin · Claude Code, Codex, Cursor +5 · 629 installs — auto-review-loop runs an autonomous multi-round research review loop.
- [arxiv](https://affpapa.org/en/nevibecode/skills/wanshuiyin-arxiv.md) — skill · wanshuiyin · Claude Code, Codex, Cursor +5 · 628 installs — Searches arXiv, downloads PDFs into a local folder and writes a short summary.
- [research-pipeline](https://affpapa.org/en/nevibecode/skills/research-pipeline.md) — skill · wanshuiyin · Claude Code, Codex, Cursor +5 · 622 installs — research-pipeline drives autonomous research lifecycles from broad directions and arXiv surveys to code execution and paper reports.
- [research-review](https://affpapa.org/en/nevibecode/skills/research-review.md) — skill · wanshuiyin · Claude Code, Codex, Cursor +5 · 621 installs — research-review is a Claude Code skill that sends research ideas, papers, and experimental results for critical review.
- [paper-writing](https://affpapa.org/en/nevibecode/skills/paper-writing.md) — skill · wanshuiyin · Claude Code, Codex, Cursor +5 · 619 installs — paper-writing runs an automated pipeline that turns research narrative reports into reviewed, compiled LaTeX PDFs for academic venues.
- [pixel-art](https://affpapa.org/en/nevibecode/skills/pixel-art.md) — skill · wanshuiyin · Claude Code, Codex, Cursor +5 · 615 installs — This skill turns a text description into a pixel art SVG for READMEs, docs or slides.
- [grant-proposal](https://affpapa.org/en/nevibecode/skills/wanshuiyin-grant-proposal.md) — skill · wanshuiyin · Claude Code, Codex, Cursor +5 · 614 installs — grant-proposal is a Claude Code skill that turns research ideas and literature into a structured funding proposal.
- [novelty-check](https://affpapa.org/en/nevibecode/skills/novelty-check.md) — skill · wanshuiyin · Claude Code, Codex, Cursor +5 · 613 installs — novelty-check is a Claude Code skill that checks research ideas against arXiv papers and conference proceedings like NeurIPS and ICML before implementation begins.
- [analyze-results](https://affpapa.org/en/nevibecode/skills/analyze-results.md) — skill · wanshuiyin · Claude Code, Codex, Cursor +5 · 609 installs — The analyze-results skill reads JSON and CSV experiment outputs, builds comparison tables and runs the statistics.
- [experiment-plan](https://affpapa.org/en/nevibecode/skills/experiment-plan.md) — skill · wanshuiyin · Claude Code, Codex, Cursor +5 · 604 installs — The experiment-plan skill turns a refined research idea into a claim-driven experiment roadmap with ablations and run order.
- [paper-write](https://affpapa.org/en/nevibecode/skills/paper-write.md) — skill · wanshuiyin · Claude Code, Codex, Cursor +5 · 596 installs — paper-write turns an outline into LaTeX prose one section at a time, with figures and BibTeX wired in.
- [auto-paper-improvement-loop](https://affpapa.org/en/nevibecode/skills/auto-paper-improvement-loop.md) — skill · wanshuiyin · Claude Code, Codex, Cursor +5 · 596 installs — auto-paper-improvement-loop is a Claude Code skill that runs a compiled paper through two rounds of external review, applying fixes, rebuilding the PDF and keeping a log.
- [paper-illustration](https://affpapa.org/en/nevibecode/skills/paper-illustration.md) — skill · wanshuiyin · Claude Code, Codex, Cursor +5 · 589 installs — paper-illustration produces publication-ready research diagrams via Gemini image models, guided by Claude through iterative layout and quality reviews.
- [formula-derivation](https://affpapa.org/en/nevibecode/skills/formula-derivation.md) — skill · wanshuiyin · Claude Code, Codex, Cursor +5 · 589 installs — formula-derivation structures research notes and equations into a derivation package.
- [research-refine](https://affpapa.org/en/nevibecode/skills/research-refine.md) — skill · wanshuiyin · Claude Code, Codex, Cursor +5 · 584 installs — research-refine turns a vague research topic into an implementation-ready method plan through iterative reviewer rounds via Codex MCP, saving checkpoints to disk.
- [paper-plan](https://affpapa.org/en/nevibecode/skills/paper-plan.md) — skill · wanshuiyin · Claude Code, Codex, Cursor +5 · 582 installs — paper-plan turns experiment results and review conclusions into a section-by-section paper outline, with the page budget of the target venue.
- [run-experiment](https://affpapa.org/en/nevibecode/skills/run-experiment.md) — skill · wanshuiyin · Claude Code, Codex, Cursor +5 · 579 installs — The run-experiment skill for Claude Code automates deploying and running ML jobs on local GPUs, SSH servers, Vast.ai, and Modal.
- [paper-slides](https://affpapa.org/en/nevibecode/skills/paper-slides.md) — skill · wanshuiyin · Claude Code, Codex, Cursor +5 · 578 installs — paper-slides turns a compiled research paper into Beamer LaTeX slides and PPTX with speaker notes.
- [proof-writer](https://affpapa.org/en/nevibecode/skills/proof-writer.md) — skill · wanshuiyin · Claude Code, Codex, Cursor +5 · 571 installs — proof-writer drafts mathematically rigorous proofs for ML and AI theory.
- [monitor-experiment](https://affpapa.org/en/nevibecode/skills/monitor-experiment.md) — skill · wanshuiyin · Claude Code, Codex, Cursor +5 · 571 installs — The monitor-experiment skill checks running experiments, gathers logs and JSON results, and compares metrics.
- [patent-novelty-check](https://affpapa.org/en/nevibecode/skills/patent-novelty-check.md) — skill · wanshuiyin · Claude Code, Codex, Cursor +5 · 564 installs — patent-novelty-check evaluates invention novelty and non-obviousness against prior art using legal patent examination standards.
- [ablation-planner](https://affpapa.org/en/nevibecode/skills/ablation-planner.md) — skill · wanshuiyin · Claude Code, Codex, Cursor +5 · 564 installs — ablation-planner designs ablation studies around the questions reviewers will ask: Codex plans the experiments, Claude checks feasibility and runs them.
- [paper-compile](https://affpapa.org/en/nevibecode/skills/paper-compile.md) — skill · wanshuiyin · Claude Code, Codex, Cursor +5 · 563 installs — paper-compile automates LaTeX paper compilation into PDF using latexmk, diagnoses build errors from logs, and verifies venue page limits.
- [result-to-claim](https://affpapa.org/en/nevibecode/skills/result-to-claim.md) — skill · wanshuiyin · Claude Code, Codex, Cursor +5 · 562 installs — The result-to-claim skill reads your experiment results and decides which claims they back, which they don't, and what evidence is missing.
- [patent-pipeline](https://affpapa.org/en/nevibecode/skills/patent-pipeline.md) — skill · wanshuiyin · Claude Code, Codex, Cursor +5 · 560 installs — patent-pipeline turns invention descriptions into formal patent filings for CNIPA, USPTO, and EPO.
- [rebuttal](https://affpapa.org/en/nevibecode/skills/rebuttal.md) — skill · wanshuiyin · Claude Code, Codex, Cursor +5 · 557 installs — Turns raw peer reviews into a checked, length-limited rebuttal draft and keeps the follow-up threads in order.
- [research-refine-pipeline](https://affpapa.org/en/nevibecode/skills/research-refine-pipeline.md) — skill · wanshuiyin · Claude Code, Codex, Cursor +5 · 557 installs — research-refine-pipeline is a Claude Code skill that turns a rough research direction into a refined method and experiment plan.
- [idea-discovery-robot](https://affpapa.org/en/nevibecode/skills/idea-discovery-robot.md) — skill · wanshuiyin · Claude Code, Codex, Cursor +5 · 555 installs — idea-discovery-robot turns a broad robotics direction into a handful of testable ideas: survey, generation, novelty check, critique.
- [experiment-bridge](https://affpapa.org/en/nevibecode/skills/experiment-bridge.md) — skill · wanshuiyin · Claude Code, Codex, Cursor +5 · 555 installs — experiment-bridge is a Claude Code skill that turns an experiment plan into code, runs it on a GPU, and collects first results for auto-review.
- [citation-audit](https://affpapa.org/en/nevibecode/skills/citation-audit.md) — skill · wanshuiyin · Claude Code, Codex, Cursor +5 · 554 installs — citation-audit is a skill that checks a paper's bibliography before submission, verifying that each work exists, its details match, and the source supports the claim.
- [paper-poster](https://affpapa.org/en/nevibecode/skills/paper-poster.md) — skill · wanshuiyin · Claude Code, Codex, Cursor +5 · 552 installs — This deprecated skill redirects requests to /paper-poster-html.
- [auto-review-loop-llm](https://affpapa.org/en/nevibecode/skills/auto-review-loop-llm.md) — skill · wanshuiyin · Claude Code, Codex, Cursor +5 · 550 installs — auto-review-loop-llm runs your work through review, fixes and another review until an outside model scores it high enough.
- [patent-review](https://affpapa.org/en/nevibecode/skills/patent-review.md) — skill · wanshuiyin · Claude Code, Codex, Cursor +5 · 548 installs — The patent-review skill sends a patent application through an external examiner-style review, then checks revisions against the findings.
- [prior-art-search](https://affpapa.org/en/nevibecode/skills/wanshuiyin-prior-art-search.md) — skill · wanshuiyin · Claude Code, Codex, Cursor +5 · 547 installs — prior-art-search searches patent registries and academic literature to evaluate an invention's novelty.
- [auto-review-loop-minimax](https://affpapa.org/en/nevibecode/skills/auto-review-loop-minimax.md) — skill · wanshuiyin · Claude Code, Codex, Cursor +5 · 543 installs — auto-review-loop-minimax runs an autonomous research review-and-fix loop using the MiniMax API.

Next: https://affpapa.org/en/nevibecode/by/wanshuiyin/auto-claude-code-research-in-sleep.md?page=2

## 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
