Updated today
by lisresearchgroup
math-rsi
MathRSI - A self-improving agent harness for mathematical discovery and proof: shared 5-stage research loop, domain plugins, workspace memory & verifiable proofs(Lean 4, DRAT) for Claude Code and Codex.
63 GitHub stars (63)
+63 in 20 days
| Period | New stars |
|---|---|
| Nov 20 | +16 |
| Nov 21 | +4 |
| Nov 22 | 0 |
- 30 skills (30 skills found in its SKILL.md files)
- 8 forks (8 forks)
- Today last update (Last updated today)
Install
Skills CLI
npx skills add lisresearchgroup/math-rsi
Asks which skills and agents to install. Just one: npx skills add lisresearchgroup/math-rsi --skill alphaxiv — add -g for every project.
Claude Code
git clone https://github.com/lisresearchgroup/math-rsicp -r "math-rsi/base/skills/alphaxiv" ~/.claude/skills/
Copies the alphaxiv skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add lisresearchgroup/math-rsi
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md — showing the first 30 of 78 files.
-
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 URL, or provides a bare arXiv ID for quick understanding - not for broad literature search.
base/skills/ on GitHub (opens in a new tab)alphaxiv/ SKILL.md -
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 data.
base/skills/ on GitHub (opens in a new tab)analyze-results/ SKILL.md -
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 and save papers from arXiv to the local paper library.
base/skills/ on GitHub (opens in a new tab)arxiv/ SKILL.md -
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, while explicit external reviewer overrides remain available. Implements fixes and re-reviews until a policy-approved positive assessment or max rounds is reached.
base/skills/ on GitHub (opens in a new tab)auto-review-loop/ SKILL.md -
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 hallucinated authors, wrong years, fabricated venues, version mismatches, and wrong-context citations. Use when user says "审查引用", "check citations", "citation audit", "verify references", "引用核对", or before submission to ensure bibl…
base/skills/ on GitHub (opens in a new tab)citation-audit/ SKILL.md -
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 while blind to the .bib, and a third extractor emits a mechanical field-by-field delta to catch dropped/re-ordered authors, wrong years, wrong venues, and bad DOIs/arXiv ids. The main agent (never a shard) assigns the MATC…
base/skills/ on GitHub (opens in a new tab)citation-crosscheck/ SKILL.md -
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 literature retrieval.
base/skills/ on GitHub (opens in a new tab)deepxiv/ SKILL.md -
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 databases (arXiv, Semantic Scholar).
base/skills/ on GitHub (opens in a new tab)exa-search/ SKILL.md -
firecrawl-search
Web search and page scraping via Firecrawl, returning full-page markdown. Use when user says "firecrawl search", "firecrawl scrape" or "/firecrawl-search".
base/skills/ on GitHub (opens in a new tab)firecrawl-search/ SKILL.md -
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 theory notes into a paper-ready formula document. Use when the derivation target is not yet fully fixed, the main object still needs to be chosen, or the user needs a coherent derivation package rather than a finished theo…
base/skills/ on GitHub (opens in a new tab)formula-derivation/ SKILL.md -
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 discovery beyond arXiv/Semantic Scholar indexes.
base/skills/ on GitHub (opens in a new tab)gemini-search/ SKILL.md -
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 beyond academic databases (arXiv, Semantic Scholar) with no search API key set up.
base/skills/ on GitHub (opens in a new tab)keenable-search/ SKILL.md -
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 lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff. Use when Lean is requested or a specific proof obligation benefits from formal verification; use proof-writer for ordinary…
base/skills/ on GitHub (opens in a new tab)lean-formalize/ SKILL.md -
mathrsi-assemble
将原题、已证明引理、准确文献进口与计算证据装配成完整数学证明,调用 ARIS proof-writer,检查实际输入与条件引理的连接。用于已有足够结果后形成现用正文;正式审计的新稿可直接写 PROOF.tex,完成或发现缺口后返回原调用方。
base/skills/ on GitHub (opens in a new tab)mathrsi-assemble/ SKILL.md -
mathrsi-handoff
将数学研究的原题、可读证明和真实验证证据整理成可复现交付与恢复入口,按需求调用 ARIS render-html、引用审计或编译,准备独立目录复现材料、最终 wiki 与 NEXT_SESSION。支持准确部分交接,不重开已闭数学或把展示成功当证明。
base/skills/ on GitHub (opens in a new tab)mathrsi-handoff/ SKILL.md -
mathrsi-meta-evolve
Evolve an existing MathRSI version from real mathematical research evidence. Distill successful and failed work into base changes, domain plugins, task-local knowledge or deferred proposals; implement, use and reconcile the actual changes. Use for MathRSI iteration or absorbing a completed research project, not for silently changing a running theorem-solving workflow.
base/skills/ on GitHub (opens in a new tab)mathrsi-meta-evolve/ SKILL.md -
mathrsi-prepare
数学研究的准备子工作流,实际串联原题初步澄清、广泛文献与反例勘误调查、正式规格定稿及wiki恢复。已有研究按真实断点进入后继阶段,不重复从零调查。
base/skills/ on GitHub (opens in a new tab)mathrsi-prepare/ SKILL.md -
mathrsi-prove
沿选定数学路线实际推进证明、构造和计算义务,调用推导与证明技能、领域程序及独占worker,立即回收核验并接回原题。用于从路线报告产生完整候选证明或精确缺口;换对象或方法交给 mathrsi-route-loop,最终装配验收交给 mathrsi-verify。
base/skills/ on GitHub (opens in a new tab)mathrsi-prove/ SKILL.md -
mathrsi-research
端到端数学研究主工作流,实际串联问题准备与文献、求解路线对抗迭代、证明推进、完整装配验证和可复现交付。组合本仓MathRSI与ARIS技能及领域插件,遇新障碍定向回文献/路线,复用wiki与证据,按需Lean。
base/skills/ on GitHub (opens in a new tab)mathrsi-research/ SKILL.md -
mathrsi-route-loop
执行ARIS auto-review-loop的数学路线适配,准备具体方法,经真实research-review、持续reviewer memory、实际推导或探针、修复复核与逐轮恢复,交付可执行求解路线和未证义务。用于选择或改造证明方法及重判卡住的路线;完整证明验收交给mathrsi-verify。
base/skills/ on GitHub (opens in a new tab)mathrsi-route-loop/ SKILL.md -
mathrsi-specify
整理数学研究的初步问题或恢复既有任务,并在文献调查后定稿原对象、量词、参数、依赖与验收。用于新题起步、原题含糊或已有规格需要对齐;不负责替用户换题或评选求解路线。
base/skills/ on GitHub (opens in a new tab)mathrsi-specify/ SKILL.md -
mathrsi-survey
调查数学问题的异名、等价表述、已有结论与反例勘误,深读关键原文形成可调用的数学进口和准确基线,并持续接回任务wiki。用于新题广搜、换参数或方法后的查漏及文献断点恢复;不以查新分数替代证明或自行更改原目标。
base/skills/ on GitHub (opens in a new tab)mathrsi-survey/ SKILL.md -
mathrsi-verify
对已装配数学证明或明确局部义务执行验证子工作流:按需装配,核覆盖与独立精确复算,调用 ARIS proof-checker 自身修复循环,并在需要时接 Lean。输出准确范围的 VERIFICATION.md;实质数学缺口返回 mathrsi-prove,不用路线评分充当定理验收。
base/skills/ on GitHub (opens in a new tab)mathrsi-verify/ SKILL.md -
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 cross-model jury and human approval at landing. Use when the user says "meta apply", "/meta-apply", "land the staged patches", "应用优化", after a /meta-optimize run.
base/skills/ on GitHub (opens in a new tab)meta-apply/ SKILL.md -
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., 2026). Use when user says "优化技能", "meta optimize", "improve skills", "分析使用记录", or wants to optimize ARIS's own harness components based on accumulated experience.
base/skills/ on GitHub (opens in a new tab)meta-optimize/ SKILL.md -
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 implementing.
base/skills/ on GitHub (opens in a new tab)novelty-check/ SKILL.md -
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 citation graph", or wants comprehensive academic metadata beyond arXiv/Semantic Scholar.
base/skills/ on GitHub (opens in a new tab)openalex/ SKILL.md -
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 confirmation bias. Use when user says "审查论文数据", "check paper claims", "verify numbers", "论文数字核对", or before submission to ensure paper-to-evidence fidelity.
base/skills/ on GitHub (opens in a new tab)paper-claim-audit/ SKILL.md -
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.
base/skills/ on GitHub (opens in a new tab)paper-compile/ SKILL.md -
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 gap with full derivations, re-reviews, and generates an audit report. Use when user says "检查证明", "verify proof", "proof check", "审证明", "check this proof", or wants rigorous mathematical verification of a theory paper.
base/skills/ on GitHub (opens in a new tab)proof-checker/ SKILL.md
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.