rcmps-field-theory SKILL.md skillA
rcmps-field-theory from xi-zhao/openquantum is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add xi-zhao/openquantum/rcmps-field-theory@git:20261105.ad8d419Pins git:20261105.ad8d419 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- xi-zhao/openquantum
- Path
.agents/skills/rcmps-field-theory/SKILL.md- Versions recorded
- 1
- Latest version
- git:20261105.ad8d419, committed Nov 5, 2026
- Size
- 3,819 bytes
- Repository stars
- 71
- License
- MIT
使用 RcmpsCore.jl 的公开 Julia API 研究 1+1 维单标量玻色场的连续 RCMPS、变分基态、正常序观测量与同真空切空间激发，区分传递 gap、Hamiltonian 能隙和数值收敛。.
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
# 连续相对论场论 <!-- BEGIN NATIVE SDK ACCESS --> ## 原生 SDK 路径 本能力使用 **RcmpsCore.jl 的原生公开 API**。用户需要 连续相对论标量场、RCMPS 优化、正常序观测量与同真空激发 时，由 Agent 在固定依赖环境中编写和运行任务代码。 使用 `node scripts/sdk-access.mjs inspect rcmps-field-theory` 定位环境，按[完整 SDK 工作流](../quantum-sdk-workbench/references/workflow.md)执行。模块导航：`RcmpsCore`、`JSON3`；导航不是 API 白名单。 单标量玻色场、无限体积、ComplexF64；正常序参考质量为 1，耦合为 g :phi^4:。传递 gap 不等于 Hamiltonian 能隙；保留背景优化、数值控制和失败诊断。 本入口复用宿主文件与代码工具，没有新增通用执行 Tool。原生 SDK 受上游版本、可选依赖、宿主资源与用户授权约束。已禁用或被拒绝的动作不能借代码路径绕过。执行状态和科研验收分别报告。 <!-- END NATIVE SDK ACCESS --> 适用于直接在连续空间、平移不变热力学极限研究 1+1 维标量场。格点 MPS/MPO、有限系统或非相对论模型优先使用已有 TeNPy、quimb、MPS 工作流或适用的上游实现；不把本入口当通用场论模拟器。 ## 方法与边界 1. 明确模型、单位和正常序：CPU SDK 支持 phi4、sinh-Gordon、sine-Gordon 和修改质量的 phi4 等公开接口；参考质量为 1，phi4 系数为 `g :phi^4:`，没有 `1/4!`。小算例不限制公开 API 或用户选择的 bond dimension。 2. `State` 使用 ComplexF64 和左规范 `Q=-iK-R†R/2`。通过构造器或 retraction 更新矩阵与稳态，评估期间不直接改共享状态。唯一稳态、trace、Hermiticity、positivity 和物理残差分别核对。 3. 显式设置 `state.model_param.name` 和 `coupling`；一次 `fg_phi4` 不会替优化器设置模型。修改质量时向能量、优化及 `ExcitationModel` 显式传同一 `massmod`，换算能量单位后再判断色散。 …
Read the whole file at its exact version.
How to install
mdr add xi-zhao/openquantum/rcmps-field-theory@sha256:89f2f769f0e0e29aThe line at the top of this page pins the label git:20261105.ad8d419, 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.
[](https://markdownregistry.com/a/art_ischenpszshkfnes)
0 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Nov 5, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (3819 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
xi-zhao/openquantum · 71 stars · license MIT · pushed 2026-11-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ischenpszshkfnes GET https://markdownregistry.com/api/v1/resolve?ref=xi-zhao/openquantum/rcmps-field-theory GET https://markdownregistry.com/api/v1/blob/89f2f769f0e0e29a9bf0a91b60b6717220e6137de2fcaab1ee25c9bffb60292d
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.