mathrsi-meta-evolve SKILL.md skillA

mathrsi-meta-evolve from lisresearchgroup/math-rsi is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add lisresearchgroup/math-rsi/mathrsi-meta-evolve@git:20261108.cc10760

Pins git:20261108.cc10760 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
lisresearchgroup/math-rsi
Path
base/skills/mathrsi-meta-evolve/SKILL.md
Versions recorded
4
Latest version
git:20261108.cc10760, committed Nov 8, 2026
First version recorded
Nov 2, 2026
Size
23,395 bytes
Repository stars
46
License
MIT

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.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# MathRSI Meta-Evolve

把已有数学研究变成下一版可用的 MathRSI。输入可以是完整研究交接包、某次失败与修正、用户反馈或一组真实调用记录。执行者读取原件、定位现行实现、作出分层判断,修改现有版本,并实际使用修改后的内容。一次运行应交出可审阅的真实变化及依据;只写经验总结或升级计划不算完成已经授权的实现任务。

这是现有 MathRSI 的外层维护 workflow,基于 [EVOLUTION_WORKFLOW](../../../docs/EVOLUTION_WORKFLOW.md) 和 ARIS meta-optimize/meta-apply 演进。它不替代五个解题子工作流,也不自动成为每道题结束后的第六阶段。基础模型不因技能变化而被训练;版本迭代是研究方法、知识、调用与工具的改进。

**先读本技能,再用它组织本次迭代。** 不在技能之外把插件和新版做好,事后补一份“已按 meta 执行”的日志。已经发生的研究可以作为历史证据,不能改写成它由某个尚未存在的 MathRSI 版本完成。

## 执行地图

| 阶段 | 读什么、实际做什么 | 产物怎样进入下一步 |
|---|---|---|
| 恢复与范围 | 用户要求、现用版本、工作树、本轮维护记录;确认可改文件与源项目只读边界 | 延用已有分支与记录,指定唯一协调者 |
| 取证与回收 | 原目标、关键成功/失败/更正链、wiki导航、实际正文/程序/输出;可并行读 | 能支撑具体判断的证据立即回收,不等全库阅读结束 |
| 分类与比较 | 对照现行技能及实际 caller,判断进入 base、插件、单题,或暂不采用 | 每个拟改行为落到现有文件、输入与消费方 |
| 候选实现 | 原位修改现有版本;插件接既有契约,必要知识与资源随仓 | 实际 diff、可调用入口和可用的例子 |
| 针对性讨论 | ARIS research-review 的维护适配,围绕证据、diff和具体疑问 | 修真实问题;误读用原件回应,不等泛泛共识 |
| 实际使用与修正 | 协调者自己按候选内容执行相关任务;子代理承担具体作者/核对 | 实际产物和命令结果决定接纳、收窄或再修 |
| 采用与交接 | 记录版本、已采用变化、保留条件与下一次可复用经验 | 新任务可选择新版;在途研究不被静默切换 |

不要求每轮新增所有类型的变化。一次只修一个已定位的调用错误,可以直接从相关原件和实际接口进入实现。完整项目吸收才需要较宽的研究地图。

## 0. 在当前版本上开始,或从真实断点继续
…

Read the whole file at its exact version.

How to install

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_5yrosrefc5qwr3cr/a723f79d772f38324ae07540f6d88bf74baf358ac018850517697853f8bc80f6.json

Then /plugin install mathrsi-meta-evolve@markdownregistry-5yrosrefc5qwr3cr in Claude Code. It installs git:20261108.cc10760, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add lisresearchgroup/math-rsi/mathrsi-meta-evolve@sha256:a723f79d772f3832

The line at the top of this page pins the label git:20261108.cc10760, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_5yrosrefc5qwr3cr.svg)](https://markdownregistry.com/a/art_5yrosrefc5qwr3cr)

1 badge image fetches in 30 days. What the badge shows.

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in lisresearchgroup/math-rsi/mathrsi-meta-evolve since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of mathrsi-meta-evolve from somewhere else? Ask it: where did my mathrsi-meta-evolve come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 4 versions of this file, between Nov 2, 2026 and Nov 8, 2026, about one every 2 days.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20261108.cc10760 latest2026-11-08 cc10760 23,395 BA view · diff
git:20261107.7b312fd2026-11-07 7b312fd 22,769 BA view · diff
git:20261104.774d09d2026-11-04 774d09d 22,316 BA view · diff
git:20261102.086d0c62026-11-02 086d0c6 21,964 BA view
Keep it current by itself, install once

Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

Install on GitHub

It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.

Keep it current by itself

Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml

It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.

Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (23395 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

lisresearchgroup/math-rsi · 46 stars · license MIT · pushed 2026-11-18 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_5yrosrefc5qwr3cr
GET https://markdownregistry.com/api/v1/resolve?ref=lisresearchgroup/math-rsi/mathrsi-meta-evolve
GET https://markdownregistry.com/api/v1/blob/a723f79d772f38324ae07540f6d88bf74baf358ac018850517697853f8bc80f6

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from lisresearchgroup/math-rsi

aris-fanout-leaf Claude Code subagent
lisresearchgroup/math-rsi · .claude/agents/aris-fanout-leaf.md
git:20261101.6b49c04 · audit B · 46 stars
AGENTS.md AGENTS.md file
lisresearchgroup/math-rsi · AGENTS.md
git:20261117.1c72df1 · audit A · 46 stars
alphaxiv SKILL.md skill
lisresearchgroup/math-rsi · base/skills/alphaxiv/SKILL.md · Quick single-paper lookup via AlphaXiv LLM-optimized summaries with tiered source fallback. Use when user says "explain…
git:20261101.6b49c04 · audit A · 46 stars
analyze-results SKILL.md skill
lisresearchgroup/math-rsi · base/skills/analyze-results/SKILL.md · Analyze ML experiment results, compute statistics, generate comparison tables and insights. Use when user says "analyze…
git:20261101.6b49c04 · audit A · 46 stars
arxiv SKILL.md skill
lisresearchgroup/math-rsi · base/skills/arxiv/SKILL.md · Search, download, and summarize academic papers from arXiv. Use when user says "search arxiv", "download paper", "fetch…
git:20261101.6b49c04 · audit A · 46 stars
auto-review-loop SKILL.md skill
lisresearchgroup/math-rsi · base/skills/auto-review-loop/SKILL.md · Autonomous multi-round research review loop. In Copilot CLI it defaults to the native complementary rubber-duck…
git:20261101.6b49c04 · audit A · 46 stars
citation-audit SKILL.md skill
lisresearchgroup/math-rsi · base/skills/citation-audit/SKILL.md · Zero-context verification that every bibliographic entry in the paper is real, correctly attributed, and used in a…
git:20261101.6b49c04 · audit A · 46 stars
citation-crosscheck SKILL.md skill
lisresearchgroup/math-rsi · base/skills/citation-crosscheck/SKILL.md · Double-blind bibliographic cross-check: one agent extracts each cited entry verbatim from the local .bib, a second…
git:20261101.6b49c04 · audit A · 46 stars
deepxiv SKILL.md skill
lisresearchgroup/math-rsi · base/skills/deepxiv/SKILL.md · Search and progressively read open-access academic papers through DeepXiv. Use when the user wants layered paper…
git:20261101.6b49c04 · audit A · 46 stars
exa-search SKILL.md skill
lisresearchgroup/math-rsi · base/skills/exa-search/SKILL.md · AI-powered web search via Exa with content extraction. Use when user says "exa search", "web search with content"…
git:20261101.6b49c04 · audit A · 46 stars
firecrawl-search SKILL.md skill
lisresearchgroup/math-rsi · base/skills/firecrawl-search/SKILL.md · Web search and page scraping via Firecrawl, returning full-page markdown. Use when user says "firecrawl search"…
git:20261101.6b49c04 · audit A · 46 stars
formula-derivation SKILL.md skill
lisresearchgroup/math-rsi · base/skills/formula-derivation/SKILL.md · Structures and derives research formulas when the user wants to 推导公式, build a theory line, organize assumptions, turn…
git:20261101.6b49c04 · audit A · 46 stars

Every file in lisresearchgroup/math-rsi

Browse by kind, by grade A, or by owner.