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

Agent skills in the GitHub repository wanshuiyin/Auto-claude-code-research-in-sleep, each with its code score out of 100.

ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.

Repository score

71 / 100 B

Skills

87

Verified

11

Average skill score

71

GitHub stars

19,072

License

MIT

Open wanshuiyin/Auto-claude-code-research-in-sleep on GitHub

87 skills in this repository

1. proof-writer

   Writes rigorous mathematical proofs for ML/AI theory. Use when asked to prove a theorem, lemma, proposition, or corollary, fill in missing proof steps, formalize a proof sketch, 补…

   Verified87A
2. 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", "claim drafting", or wants to create patent claims. The core skill of the patent pipel…

   Verified85A
3. paper-compile

   Compile LaTeX paper to PDF, fix errors, and verify output. Use when user says "编译论文", "compile paper", "build PDF", "生成PDF", or wants to compile LaTeX into a submission-ready PDF.

   Verified85A
4. figure-spec

   Generate deterministic publication-quality architecture, workflow, and pipeline diagrams from structured JSON (FigureSpec) into editable SVG. Use when user says "架构图", "workflow 图…

   Verified84B
5. rebuttal

   Workflow 4: Submission rebuttal pipeline. Parses external reviews, enforces coverage and grounding, drafts a safe text-only rebuttal under venue limits, and manages follow-up roun…

   Verified84B
6. integrity-forensics

   Run the Anti-Autoresearch integrity-forensics sweep (span-anchored evidence ledger → GPT auditors propose findings → a rules-only reporter that lists every proposal with what the…

   Verified83B
7. idea-creator

   Generate and rank research ideas given a broad direction. Use when user says "找idea", "brainstorm ideas", "generate research ideas", "what can we work on", or wants to explore a r…

   82B
8. formula-derivation

   Structures and derives research formulas when the user wants to 推导公式, build a theory line, organize assumptions, turn scattered equations into a coherent derivation, or rewrite th…

   Verified81B
9. novelty-check

   Verify research idea novelty against recent literature. Use when user says "查新", "novelty check", "有没有人做过", "check novelty", or wants to verify a research idea is novel before imp…

   Verified81B
10. proof-checker

    Rigorous mathematical proof verification and fixing workflow. Reads a LaTeX proof, identifies gaps via cross-model review (external reviewer backend, ultra reasoning), fixes each…

    81B
11. grant-proposal

    Draft a structured grant proposal from research ideas and literature. Supports KAKENHI (Japan), NSF (US), NSFC (China, including 面上/青年/优青/杰青/海外优青/重点), ERC (EU), DFG (Germany), SNS…

    80B
12. jurisdiction-format

    Compile patent application into jurisdiction-specific filing format. Use when user says "格式转换", "jurisdiction format", "国家格式", "compile patent", or wants formatted patent document…

    Verified80B
13. paper-figure

    Generate publication-quality figures and tables from experiment results. Use when user says "画图", "作图", "generate figures", "paper figures", or needs plots for a paper.

    Verified80B
14. paper-write

    Draft LaTeX paper section by section from an outline. Use when user says "写论文", "write paper", "draft LaTeX", "开始写", or wants to generate LaTeX content from a paper plan.

    80B
15. research-refine

    Turn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative GPT-6-Astra review. Use when the user says "ref…

    80B
16. specification-writing

    Write the full patent specification from claims and invention disclosure. Use when user says "撰写说明书", "write specification", "写说明书", "patent description", or wants to draft the co…

    Verified80B
17. paper-claim-audit

    Zero-context verification that every number, comparison, and scope claim in the paper matches raw result files. Uses a fresh cross-model reviewer with NO prior context to prevent…

    79B
18. writing-systems-papers

    Paragraph-level structural blueprint for 10-12 page systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Provides page allocation, paragraph templates, and writing patt…

    79B
19. paper-slides

    Generate conference presentation slides (beamer LaTeX → PDF + editable PPTX) from a compiled paper, with speaker notes and full talk script. Use when user says "做PPT", "做幻灯片", "ma…

    78B
20. experiment-queue

    SSH job queue for multi-seed/multi-config ML experiments with OOM-aware retry, stale-screen cleanup, and wave-transition race prevention. Use when user says "batch experiments", "…

    77B
21. feishu-notify

    Send notifications to Feishu/Lark. Internal utility used by other skills, or manually via /feishu-notify. Use when user says "发飞书", "notify feishu", or other skills need to send s…

    77B
22. paper-illustration-image2

    Generate publication-quality academic illustrations through a local Codex app-server bridge that uses Codex native image generation. This is a separate experimental alternative to…

    77B
23. render-html

    Render an ARIS Markdown / JSON artifact (IDEA_REPORT, AUTO_REVIEW, KILL_ARGUMENT, PAPER_PLAN, research-wiki state, etc.) into a single-file HTML view designed for human reading. U…

    77B
24. idea-discovery-robot

    Workflow 1 adaptation for robotics and embodied AI. Orchestrates robotics-aware literature survey, idea generation, novelty check, and critical review to go from a broad robotics…

    76B
25. invention-structuring

    Structure a raw invention idea into a formal invention disclosure. Use when user says "构建发明", "structure invention", "发明构建", "invention disclosure", or wants to formalize a rough…

    76B
26. embodiment-description

    Write detailed embodiment descriptions for patent specifications. Use when user says "撰写实施例", "write embodiment", "实施例描述", "detailed description", or wants to describe how to prac…

    75B
27. paper-poster-html

    DEFAULT poster pipeline — build an academic conference poster (ICML/NeurIPS/ICLR/CVPR/...) as a single HTML/CSS file with measurement-driven hard gates, real paper figures, a two-…

    75B
28. research-refine-pipeline

    Run an end-to-end workflow that chains `research-refine` and `experiment-plan`. Use when the user wants a one-shot pipeline from vague research direction to focused final proposal…

    75B
29. slides-polish

    Per-page Codex review + targeted python-pptx / Beamer fixes for academic talk slides. Use AFTER /paper-slides (or any externally generated PPTX/Beamer) when the deck looks 'mostly…

    75B
30. dse-loop

    Autonomous design space exploration loop for computer architecture and EDA. Runs a program, analyzes results, tunes parameters, and iterates until objective is met or timeout. Use…

    74B
31. figure-description

    Process user-provided patent figures and generate formal drawing descriptions. Use when user says "附图处理", "figure description", "附图说明", "drawings description", or wants to describ…

    74B
32. paper-plan

    Generate a structured paper outline from review conclusions and experiment results. Use when user says "写大纲", "paper outline", "plan the paper", "论文规划", or wants to create a paper…

    74B
33. arxiv

    Search, download, and summarize academic papers from arXiv. Use when user says "search arxiv", "download paper", "fetch arxiv", "arxiv search", "get paper pdf", or wants to find a…

    73B
34. citation-crosscheck

    Double-blind bibliographic cross-check: one agent extracts each cited entry verbatim from the local .bib, a second independently re-fetches the same paper's record from the web wh…

    72B
35. experiment-audit

    Audit experiment integrity before claiming results. Uses cross-model review (external reviewer backend) to check for fake ground truth, score normalization fraud, phantom results,…

    72B
36. experiment-plan

    Turn a refined research proposal or method idea into a detailed, claim-driven experiment roadmap. Use after `research-refine`, or when the user asks for a detailed experiment plan…

    72B
37. idea-discovery

    Workflow 1: Full idea discovery pipeline to go from a broad research direction to validated, pilot-tested ideas. Use when user says "找idea全流程", "idea discovery pipeline", "从零开始找方向…

    72B
38. monitor-experiment

    Monitor running experiments, check progress, collect results. Use when user says "check results", "is it done", "monitor", or wants experiment output.

    72B
39. overleaf-sync

    Two-way sync between a local paper directory and an Overleaf project, so ARIS audit/edit workflows stay on the local copy while collaborators edit in the Overleaf web UI. Use when…

    72B
40. patent-novelty-check

    Assess patent novelty and non-obviousness against prior art. Use when user says "专利查新", "patent novelty", "可专利性评估", "patentability check", or wants to evaluate if an invention is…

    72B
41. pixel-art

    Generate pixel art SVG illustrations for READMEs, docs, or slides. Use when user says "画像素图", "pixel art", "make an SVG illustration", "README hero image", or wants a cute visual.

    72B
42. auto-review-loop-llm

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

    71B
43. auto-review-loop-minimax

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

    71B
44. experiment-bridge

    Workflow 1.5: Bridge between idea discovery and auto review. Reads EXPERIMENT_PLAN.md, implements experiment code, deploys to GPU, collects initial results. Use when user says "实现…

    71B
45. research-lit

    Search and analyze research papers, find related work, summarize key ideas. Use when user says "find papers", "related work", "literature review", "what does this paper say", or n…

    71B
46. research-wiki

    Persistent research knowledge base that accumulates papers, ideas, experiments, claims, and their relationships across the entire research lifecycle. Inspired by Karpathy's LLM Wi…

    71B
47. gemini-search

    Search research papers via Gemini for broad literature discovery. Use when user says "gemini search", "gemini papers", "search with gemini", or wants AI-powered literature discove…

    70B
48. paper-writing

    Workflow 3: Full paper writing pipeline that goes from a narrative report to a polished, submission-ready PDF. Use when user says "写论文全流程", "write paper pipeline", "从报告到PDF", "pap…

    70B
49. patent-pipeline

    Full patent drafting pipeline from invention description to jurisdiction-formatted filing documents. Supports CN (CNIPA), US (USPTO), EP (EPO). Supports invention patents and util…

    70B
50. prior-art-search

    Search patent databases and academic literature for prior art relevant to an invention. Use when user says "现有技术检索", "prior art search", "专利检索", "check patents", or wants to find…

    70B
51. research-implement-feature

    Build a working artifact from a plain "implement X for me" request: a running end-to-end spine first, then one feature per rung, with every under-determined decision written to an…

    70B
52. proof-orchestrator

    Manage a stateful, run-directory-based proof project: continuation across runs, run-local source bookkeeping, manual GPT Pro handoff packages when a local attempt stalls, and an o…

    68C
53. run-experiment

    Deploy and run ML experiments on local, remote, Vast.ai, or Modal serverless GPU. Use when user says "run experiment", "deploy to server", "跑实验", or needs to launch training jobs.

    68C
54. vast-gpu

    Rent, manage, and destroy GPU instances on vast.ai. Use when user says "rent gpu", "vast.ai", "rent a server", "cloud gpu", or needs on-demand GPU without owning hardware.

    68C
55. web-debug-search

    Search GitHub, Stack Exchange, Chinese technical communities, official documentation, and general developer web sources for software errors, compatibility problems, API usage ques…

    68C
56. interview-cheatsheet

    Generate a long-form Chinese interview-prep cheat sheet on a specific ML/LLM topic — formulas with derivations, from-scratch PyTorch code, comparison tables, and 25 高频面试题 (L1 必会 /…

    67C
57. kill-argument

    Two-thread adversarial review: a fresh reviewer constructs the strongest 200-word rejection memo, then a second fresh reviewer defends the paper point-by-point and surfaces still-…

    67C
58. lean-formalize

    Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemm…

    67C
59. mermaid-diagram

    Generate Mermaid diagrams from user requirements. Supports flowcharts, sequence diagrams, class diagrams, ER diagrams, Gantt charts, and 18 more diagram types.

    67C
60. meta-apply

    Privileged applier that LANDS meta-optimize / corpus-audit patches the user approved — the ONLY skill permitted to mutate the skill corpus from a self-modification proposal, with…

    67C
61. paper-talk

    End-to-end conference talk pipeline: paper → slide outline → Beamer + PPTX → per-page polish → assurance checks (claim / citation / anonymity) → final export and report. Default-g…

    67C
62. result-to-claim

    Use when experiments complete to judge what claims the results support, what they don't, and what evidence is still missing. Codex MCP evaluates results against intended claims an…

    67C
63. serverless-modal

    Run GPU workloads on Modal — training, fine-tuning, inference, batch processing. Zero-config serverless: no SSH, no Docker, auto scale-to-zero. Use when user says "modal run", "mo…

    67C
64. training-check

    Periodically check WandB metrics during training to catch problems early (NaN, loss divergence, idle GPUs). Avoids wasting GPU hours on broken runs. Use when training is running a…

    67C
65. wiki-enrich

    Fill in the per-paper TODO sections of research-wiki/papers/<slug>.md pages that literature-ingest skills leave as bare scaffolds. Use when user says 'enrich wiki', 'fill paper TO…

    66C
66. analyze-results

    Analyze ML experiment results, compute statistics, generate comparison tables and insights. Use when user says "analyze results", "compare", or needs to interpret experimental dat…

    65C
67. auto-paper-improvement-loop

    Autonomously improve a generated paper via GPT-6-Astra xhigh review → implement fixes → recompile, for 2 rounds. Use when user says "改论文", "improve paper", "论文润色循环", "auto improve…

    65C
68. firecrawl-search

    Web search and page scraping via Firecrawl, returning full-page markdown. Use when user says "firecrawl search", "firecrawl scrape" or "/firecrawl-search".

    65C
69. meta-optimize

    Analyze ARIS usage logs and propose optimizations to SKILL.md files, reviewer prompts, and workflow defaults. Outer-loop harness optimization inspired by Meta-Harness (Lee et al.,…

    65C
70. openalex

    Search academic papers via OpenAlex API for open citation data, institutional affiliations, and funding information. Use when user says "openalex search", "search openalex", "open…

    65C
71. research-pipeline

    Full end-to-end research pipeline: from a broad research direction through idea discovery, experiments, and review all the way to a polished paper PDF. Use when user says "全流程", "…

    65C
72. system-profile

    Profile a target (script, process, GPU, memory, interconnect) for performance analysis. Use when user says "profile", "benchmark", "bottleneck", or wants performance analysis.

    65C
73. paper-illustration

    Generate publication-quality AI illustrations for academic papers using Gemini image generation. Creates architecture diagrams, method illustrations with Claude-supervised iterati…

    64C
74. semantic-scholar

    Search published venue papers (IEEE, ACM, Springer, etc.) via Semantic Scholar API. Complements /arxiv (preprints) with citation counts, venue metadata, and TLDR. Use when user sa…

    64C
75. alphaxiv

    Quick single-paper lookup via AlphaXiv LLM-optimized summaries with tiered source fallback. Use when user says "explain this paper", "summarize paper", pastes an arXiv/AlphaXiv UR…

    63C
76. citation-audit

    Zero-context verification that every bibliographic entry in the paper is real, correctly attributed, and used in a context the cited paper actually supports — catching hallucinate…

    63C
77. exa-search

    AI-powered web search via Exa with content extraction. Use when user says "exa search", "web search with content", "find similar pages", or needs broad web results beyond academic…

    63C
78. resubmit-pipeline

    Workflow 5: orchestrate a text-only resubmit of a polished paper to a different venue under hard constraints (no new experiments, no bib edits, no framework changes, never overwri…

    63C
79. comm-lit-review

    Communications-domain literature review with Claude-style knowledge-base-first retrieval. Use when the task is about communications, wireless, networking, satellite/NTN, Wi-Fi, ce…

    62C
80. research-review

    Get a deep critical review of research from a selected reviewer (Codex by default, Gemini, Grok, Claude Code, or manual). Use when user says "review my research", "help me review"…

    62C
81. patent-review

    Get an external patent examiner review of a patent application. Use when user says "专利审查", "patent review", "审查意见", "examiner review", or wants critical feedback on patent claims…

    61C
82. deepxiv

    Search and progressively read open-access academic papers through DeepXiv. Use when the user wants layered paper access, section-level reading, trending papers, or DeepXiv-backed…

    60C
83. auto-review-loop

    Autonomous multi-round research review loop. In Copilot CLI it defaults to the native complementary rubber-duck subagent with host-event model evidence; elsewhere it uses Codex, w…

    56C
84. keenable-search

    Keyless web search and page fetch via Keenable. Use when user says "keenable search", "web search without an API key", "fetch this page as markdown", or needs broad web results be…

    56C
85. qzcli

    Manage GPU compute jobs on the Qizhi (启智) platform using qzcli — a kubectl-style CLI tool. Use when user says "qzcli", "启智平台", "submit job", "stop job", "查计算组", "avail", "list job…

    54D
86. ablation-planner

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

    52D
87. paper-poster

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

    50D

Scores come from a snapshot of 300 public GitHub repositories taken on 12 November 2026. Every score is the result of fixed checks run by code; no AI is involved. How scoring works.