rohitg00/auto-claude-code-research-in-sleep

1

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

rohitg00/auto-claude-code-research-in-sleep

2

2

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

rohitg00/auto-claude-code-research-in-sleep

2

3

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

rohitg00/auto-claude-code-research-in-sleep

1

4

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

rohitg00/auto-claude-code-research-in-sleep

1

5

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

rohitg00/auto-claude-code-research-in-sleep

1

6

auto-paper-improvement-loop Autonomously improve a generated paper via GPT-5.4 xhigh review → implement fixes → recompile, for 2 rounds. Use when…

rohitg00/auto-claude-code-research-in-sleep

1

7

auto-review-loop Autonomous multi-round research review loop. Repeatedly reviews via Codex MCP, implements fixes, and re-reviews until…

rohitg00/auto-claude-code-research-in-sleep

1

8

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

rohitg00/auto-claude-code-research-in-sleep

1

9

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

rohitg00/auto-claude-code-research-in-sleep

1

10

comm-lit-review Communications-domain literature review and related-work search with database-aware source control. Use when the task…

rohitg00/auto-claude-code-research-in-sleep

1

11

comm-lit-review-claude-single Communications-domain literature review with Claude-style knowledge-base-first retrieval. Use when the task is about …

rohitg00/auto-claude-code-research-in-sleep

1

12

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

rohitg00/auto-claude-code-research-in-sleep

1

13

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

rohitg00/auto-claude-code-research-in-sleep

1

14

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

rohitg00/auto-claude-code-research-in-sleep

1

15

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

rohitg00/auto-claude-code-research-in-sleep

1

16

formula-derivation Structures and derives research formulas when the user wants to 推导公式, build a theory line, organize assumptions, …

rohitg00/auto-claude-code-research-in-sleep

1

17

grant-proposal Draft a structured grant proposal from research ideas and literature. Supports KAKENHI (Japan), NSF (US), NSFC (China…

rohitg00/auto-claude-code-research-in-sleep

1

18

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

rohitg00/auto-claude-code-research-in-sleep

1

19

idea-discovery Workflow 1: Full idea discovery pipeline. Orchestrates research-lit → idea-creator → novelty-check → research-review …

rohitg00/auto-claude-code-research-in-sleep

1

20

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

rohitg00/auto-claude-code-research-in-sleep

1

21

mermaid-diagram Generate Mermaid diagrams from user requirements. Saves .mmd and .md files to figures/ directory with syntax verifica…

rohitg00/auto-claude-code-research-in-sleep

1

22

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

rohitg00/auto-claude-code-research-in-sleep

1

23

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

rohitg00/auto-claude-code-research-in-sleep

1

24

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

rohitg00/auto-claude-code-research-in-sleep

1

25

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

rohitg00/auto-claude-code-research-in-sleep

1

26

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

rohitg00/auto-claude-code-research-in-sleep

1

27

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

rohitg00/auto-claude-code-research-in-sleep

1

28

paper-poster Generate a conference poster (article + tcbposter LaTeX → A0/A1 PDF + editable PPTX + SVG) from a compiled paper.

rohitg00/auto-claude-code-research-in-sleep

1

29

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

rohitg00/auto-claude-code-research-in-sleep

1

30

paper-writing Workflow 3: Full paper writing pipeline. Orchestrates paper-plan → paper-figure → paper-write → paper-compile → auto-…

rohitg00/auto-claude-code-research-in-sleep

1

31

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

rohitg00/auto-claude-code-research-in-sleep

1

32

rebuttal Workflow 4: Submission rebuttal pipeline.

rohitg00/auto-claude-code-research-in-sleep

1

33

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

rohitg00/auto-claude-code-research-in-sleep

1

34

research-pipeline Full research pipeline: Workflow 1 (idea discovery) → implementation → Workflow 2 (auto review loop). Goes from a bro…

rohitg00/auto-claude-code-research-in-sleep

1

35

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

rohitg00/auto-claude-code-research-in-sleep

1

36

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

rohitg00/auto-claude-code-research-in-sleep

1

37

research-review Get a deep critical review of research from GPT via Codex MCP. Use when user says "review my research", "help me revi…

rohitg00/auto-claude-code-research-in-sleep

1

38

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

rohitg00/auto-claude-code-research-in-sleep

1

39

run-experiment Deploy and run ML experiments on local or remote GPU servers. Use when user says "run experiment", "deploy to server"…

rohitg00/auto-claude-code-research-in-sleep

1

40

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

rohitg00/auto-claude-code-research-in-sleep

1

41

system-profile Profile a target (script, process, GPU, memory, interconnect) using external tools and code instrumentation. Produces…

rohitg00/auto-claude-code-research-in-sleep

1

42

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

rohitg00/auto-claude-code-research-in-sleep

1

43

vast-gpu Rent, manage, and destroy GPU instances on vast.ai. Use when user says \"rent gpu\", \"vast.ai\", \"rent a server\", …

rohitg00/auto-claude-code-research-in-sleep

1