wanshuiyin/auto-claude-code-research-in-sleep

1

paper-figure Generate publication-quality figures and tables from experiment results. Use when user says \"画图\", \"作图\", \"gen…

wanshuiyin/auto-claude-code-research-in-sleep

509

2

research-lit Search and analyze research papers, find related work, summarize key ideas. Use when user says "find papers", "relate…

wanshuiyin/auto-claude-code-research-in-sleep

494

3

idea-discovery Workflow 1: Full idea discovery pipeline to go from a broad research direction to validated, pilot-tested ideas. Use …

wanshuiyin/auto-claude-code-research-in-sleep

471

4

idea-creator Generate and rank research ideas given a broad direction. Use when user says "找idea", "brainstorm ideas", "generate …

wanshuiyin/auto-claude-code-research-in-sleep

467

5

arxiv Search, download, and summarize academic papers from arXiv. Use when user says "search arxiv", "download paper", "fet…

wanshuiyin/auto-claude-code-research-in-sleep

460

6

auto-review-loop Autonomous multi-round research review loop.

wanshuiyin/auto-claude-code-research-in-sleep

458

7

research-pipeline Full end-to-end research pipeline: from a broad research direction through idea discovery, experiments, and review al…

wanshuiyin/auto-claude-code-research-in-sleep

453

8

semantic-scholar Search published venue papers (IEEE, ACM, Springer, etc.) via Semantic Scholar API.

wanshuiyin/auto-claude-code-research-in-sleep

452

9

paper-writing Workflow 3: Full paper writing pipeline that goes from a narrative report to a polished, submission-ready PDF. Use wh…

wanshuiyin/auto-claude-code-research-in-sleep

451

10

research-review Get a deep critical review of research from an external reviewer backend (Codex or manual). Use when user says "revie…

wanshuiyin/auto-claude-code-research-in-sleep

449

11

grant-proposal Draft a structured grant proposal from research ideas and literature.

wanshuiyin/auto-claude-code-research-in-sleep

446

12

novelty-check Verify research idea novelty against recent literature. Use when user says "查新", "novelty check", "有没有人做过", "…

wanshuiyin/auto-claude-code-research-in-sleep

438

13

analyze-results Analyze ML experiment results, compute statistics, generate comparison tables and insights. Use when user says "analy…

wanshuiyin/auto-claude-code-research-in-sleep

436

14

auto-paper-improvement-loop Autonomously improve a generated paper via GPT-5.6-Sol xhigh review → implement fixes → recompile, for 2 rounds. Use …

wanshuiyin/auto-claude-code-research-in-sleep

430

15

paper-write Draft LaTeX paper section by section from an outline. Use when user says \"写论文\", \"write paper\", \"draft LaTeX\"…

wanshuiyin/auto-claude-code-research-in-sleep

430

16

pixel-art Generate pixel art SVG illustrations for READMEs, docs, or slides. Use when user says "画像素图", "pixel art", "make …

wanshuiyin/auto-claude-code-research-in-sleep

427

17

experiment-plan Turn a refined research proposal or method idea into a detailed, claim-driven experiment roadmap.

wanshuiyin/auto-claude-code-research-in-sleep

425

18

research-refine Turn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan…

wanshuiyin/auto-claude-code-research-in-sleep

422

19

run-experiment Deploy and run ML experiments on local, remote, Vast.ai, or Modal serverless GPU. Use when user says "run experiment"…

wanshuiyin/auto-claude-code-research-in-sleep

419

20

formula-derivation Structures and derives research formulas when the user wants to 推导?

wanshuiyin/auto-claude-code-research-in-sleep

417

21

monitor-experiment Monitor running experiments, check progress, collect results. Use when user says "check results", "is it done", "moni…

wanshuiyin/auto-claude-code-research-in-sleep

415

22

paper-illustration Generate publication-quality AI illustrations for academic papers using Gemini image generation.

wanshuiyin/auto-claude-code-research-in-sleep

415

23

paper-plan Generate a structured paper outline from review conclusions and experiment results. Use when user says \"写大纲\", \"…

wanshuiyin/auto-claude-code-research-in-sleep

415

24

paper-slides Generate conference presentation slides (beamer LaTeX → PDF + editable PPTX) from a compiled paper, with speaker note…

wanshuiyin/auto-claude-code-research-in-sleep

413

25

proof-writer Writes rigorous mathematical proofs for ML/AI theory. Use when asked to prove a theorem, lemma, proposition, or corol…

wanshuiyin/auto-claude-code-research-in-sleep

405

26

research-refine-pipeline Run an end-to-end workflow that chains `research-refine` and `experiment-plan`.

wanshuiyin/auto-claude-code-research-in-sleep

403

27

paper-compile Compile LaTeX paper to PDF, fix errors, and verify output. Use when user says \"编译论文\", \"compile paper\", \"buil…

wanshuiyin/auto-claude-code-research-in-sleep

402

28

ablation-planner Use when main results pass result-to-claim (claim_supported=yes or partial) and ablation studies are needed for paper…

wanshuiyin/auto-claude-code-research-in-sleep

399

29

experiment-bridge Workflow 1.5: Bridge between idea discovery and auto review.

wanshuiyin/auto-claude-code-research-in-sleep

399

30

mermaid-diagram Generate Mermaid diagrams from user requirements. Supports flowcharts, sequence diagrams, class diagrams, ER diagrams…

wanshuiyin/auto-claude-code-research-in-sleep

399

31

result-to-claim Use when experiments complete to judge what claims the results support, what they don't, and what evidence is still m…

wanshuiyin/auto-claude-code-research-in-sleep

398

32

paper-poster DEPRECATED — superseded by /paper-poster-html. Kept only as a redirect for muscle memory; do not use for new posters.

wanshuiyin/auto-claude-code-research-in-sleep

397

33

auto-review-loop-llm Autonomous research review loop using any OpenAI-compatible LLM API. Configure via llm-chat MCP server or environment…

wanshuiyin/auto-claude-code-research-in-sleep

394

34

idea-discovery-robot Workflow 1 adaptation for robotics and embodied AI.

wanshuiyin/auto-claude-code-research-in-sleep

394

35

rebuttal Workflow 4: Submission rebuttal pipeline.

wanshuiyin/auto-claude-code-research-in-sleep

394

36

auto-review-loop-minimax Autonomous multi-round research review loop using MiniMax API. Use when you want to use MiniMax instead of Codex MCP …

wanshuiyin/auto-claude-code-research-in-sleep

390

37

dse-loop Autonomous design space exploration loop for computer architecture and EDA.

wanshuiyin/auto-claude-code-research-in-sleep

389

38

patent-pipeline Full patent drafting pipeline from invention description to jurisdiction-formatted filing documents.

wanshuiyin/auto-claude-code-research-in-sleep

389

39

feishu-notify Send notifications to Feishu/Lark. Internal utility used by other skills, or manually via /feishu-notify. Use when us…

wanshuiyin/auto-claude-code-research-in-sleep

387

40

patent-novelty-check Assess patent novelty and non-obviousness against prior art. Use when user says \"专利查新\", \"patent novelty\", \"…

wanshuiyin/auto-claude-code-research-in-sleep

383

41

training-check Periodically check WandB metrics during training to catch problems early (NaN, loss divergence, idle GPUs). Avoids wa…

wanshuiyin/auto-claude-code-research-in-sleep

379

42

patent-review Get an external patent examiner review of a patent application. Use when user says \"专利审查\", \"patent review\", \…

wanshuiyin/auto-claude-code-research-in-sleep

378

43

system-profile Profile a target (script, process, GPU, memory, interconnect) for performance analysis. Use when user says \"profile\…

wanshuiyin/auto-claude-code-research-in-sleep

370

44

claims-drafting Draft patent claims for an invention. Use when user says \"撰写权利要求\", \"draft claims\", \"写权利要求书\", \"clai…

wanshuiyin/auto-claude-code-research-in-sleep

368

45

research-wiki Persistent research knowledge base that accumulates papers, ideas, experiments, claims, and their relationships acros…

wanshuiyin/auto-claude-code-research-in-sleep

368

46

prior-art-search Search patent databases and academic literature for prior art relevant to an invention. Use when user says \"现有技术…

wanshuiyin/auto-claude-code-research-in-sleep

367

47

deepxiv Search and progressively read open-access academic papers through DeepXiv. Use when the user wants layered paper acce…

wanshuiyin/auto-claude-code-research-in-sleep

365

48

citation-audit Zero-context verification that every bibliographic entry in the paper is real, correctly attributed, and used in a co…

wanshuiyin/auto-claude-code-research-in-sleep

364

49

proof-checker Rigorous mathematical proof verification and fixing workflow.

wanshuiyin/auto-claude-code-research-in-sleep

364

50

serverless-modal Run GPU workloads on Modal — training, fine-tuning, inference, batch processing.

wanshuiyin/auto-claude-code-research-in-sleep

359