platform-diagnostics SKILL.md skillA

platform-diagnostics from xi-zhao/openquantum is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add xi-zhao/openquantum/platform-diagnostics@git:20260924.1dc6767

Pins git:20260924.1dc6767 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/platform-diagnostics/SKILL.md
Versions recorded
3
Latest version
git:20260924.1dc6767, committed Sep 24, 2026
First version recorded
Aug 14, 2026
Size
3,681 bytes
Repository stars
71
License
MIT

审计 OpenQuantum 的 UI、Harness、Skill 和 Model 四层是否真实连通,并生成可验证、可追溯的诊断报告。用于架构验收、联调排障和发布前健康检查。.

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

# OpenQuantum 平台诊断

本能力只诊断四层架构,不实现量子业务功能。默认执行只读检查;除非用户明确授权,不修改配置、
不启动长期后台进程、不写入生产系统。

## 核心对象

诊断对象是一份 `platform-diagnostics` 报告。报告中的每个检查项必须有可复核证据;Capability Validator
根据检查结果推导的是诊断报告聚合状态,不是 Scientific Acceptance,也不能由模型自行宣称。

开始前读取并按 Capability Contract v1 校验 `capability.yaml`。生成报告时读取
`artifacts/diagnostic-report.schema.json`;验收时运行 `validators/validate-report.mjs`。

## 检查流程

先确定本次诊断范围和已有运行证据,只执行与问题相关的检查。未执行项按原 schema 标为
`not_checked` 并写明原因;局部修改不要求自动启动全部探针或外部模型请求。

1. UI:确认 UI 只通过 Harness transport adapter 发出会话命令,不直接调用 Model Provider 或 MCP Server。
2. Harness 配置:运行 `npm run harness:config`,确认组合能展开且默认模型属于 OpenQuantum route。
3. Harness Host:检查 Host 根页面、`session/list` 和 `session/modelCatalog` Harness RPC;未启动时记录 `not_checked`,
   不把静态配置当成运行证据。
4. Skill:通过 Harness `skills/list` 或当前成功加载的 Skill 上下文证明项目 Skill 可发现。
5. Model:只有本次任务要求且已授权外部模型请求时,运行 `npm run models:probe -- --provider openquantum-public`,分别验证目录、文本生成和
   强制函数调用。不要把“接口返回 200”替代工具调用验收。
6. 端到端:仅在任务要求科研链路验收且已授权外部模型请求时,运行 `npm run e2e:quantum-harness -- --provider openquantum-public`,确认
   真实模型在 Harness Session 中产生 QGS `tool/call` / `tool/result`,且 Result Commit 与中央 Acceptance
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add xi-zhao/openquantum/platform-diagnostics@sha256:e0e66fc39d6e7d05

The line at the top of this page pins the label git:20260924.1dc6767, 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_fi7b3imppsl4be4n.svg)](https://markdownregistry.com/a/art_fi7b3imppsl4be4n)

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

Versions

The registry has recorded 3 versions of this file, between Aug 14, 2026 and Sep 24, 2026, about one every 21 days.

versioncommittedcommitsizeaudit
git:20260924.1dc6767 latest2026-09-24 1dc6767 3,681 BA view · diff
git:20260827.79c88b82026-08-27 79c88b8 3,101 BA view · diff
git:20260814.132b3b62026-08-14 132b3b6 2,852 BA view

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 (3681 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

xi-zhao/openquantum · 71 stars · license MIT · pushed 2026-11-05 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_fi7b3imppsl4be4n
GET https://markdownregistry.com/api/v1/resolve?ref=xi-zhao/openquantum/platform-diagnostics
GET https://markdownregistry.com/api/v1/blob/e0e66fc39d6e7d05b5754d1b261d0db57eefa9fcb71c1b976752f05ca818a567

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 xi-zhao/openquantum

fixture-capability SKILL.md skill
xi-zhao/openquantum · .agents/skill-contracts/test/fixtures/capabilities/fixture-capability/SKILL.md · Contract fixture used only by the OpenQuantum Skill Contract tests.
git:20260814.132b3b6 · audit B · 71 stars
alicebob-cat-circuits SKILL.md skill
xi-zhao/openquantum · .agents/skills/alicebob-cat-circuits/SKILL.md · 用 Alice & Bob 的真实本地 Qiskit provider 构建物理或逻辑猫量子位噪声电路模型,返回调度转译后的采样和明确模型参数。
git:20261012.5ce3b3e · audit A · 71 stars
aqt-workbench SKILL.md skill
xi-zhao/openquantum · .agents/skills/aqt-workbench/SKILL.md · 官方离子阱后端本地编译与仿真,以及用户鉴权后的设备查询。
git:20261012.5ce3b3e · audit A · 71 stars
arc-rydberg SKILL.md skill
xi-zhao/openquantum · .agents/skills/arc-rydberg/SKILL.md · 使用 ARC Rydberg 的原生公开 API 完成原子、能级、跃迁矩阵元、寿命、Stark 图与相互作用,支持用户自定义模型、程序与结果文件。
git:20261013.efe0949 · audit A · 71 stars
bloqade-analog SKILL.md skill
xi-zhao/openquantum · .agents/skills/bloqade-analog/SKILL.md · 用 QuEra Bloqade Analog 在本地模拟二维 Rydberg 原子阵列的全局时变脉冲,返回逐原子占据、末态振幅、位串概率和明确单位。
git:20261012.5ce3b3e · audit A · 71 stars
braket-simulation SKILL.md skill
xi-zhao/openquantum · .agents/skills/braket-simulation/SKILL.md · 使用 Amazon Braket LocalSimulator 在本地计算结构化量子电路的精确数值振幅与概率。
git:20261012.5ce3b3e · audit A · 71 stars
catalyst-compilation SKILL.md skill
xi-zhao/openquantum · .agents/skills/catalyst-compilation/SKILL.md · 使用 PennyLane Catalyst 的原生公开 API 完成qjit、混合程序、QNode、控制流、编译配置与梯度,支持用户自定义模型、程序与结果文件。
git:20261013.efe0949 · audit A · 71 stars
chromobius-decoding SKILL.md skill
xi-zhao/openquantum · .agents/skills/chromobius-decoding/SKILL.md · 使用 Chromobius 的原生公开 API 对带颜色和基标注的 Stim detector error model 解码,比较预测与实际逻辑 observable 翻转;用于色码解码、样本分析和可复核小规模实验。
git:20261026.f44a0b2 · audit A · 71 stars
classiq-synthesis SKILL.md skill
xi-zhao/openquantum · .agents/skills/classiq-synthesis/SKILL.md · 使用 Classiq 官方 SDK 构建结构化 Qmod 模型,或通过用户自行配置的凭据调用远程综合;区分模型准备、云端综合和量子执行。
git:20261012.5ce3b3e · audit A · 71 stars
clifft-sampling SKILL.md skill
xi-zhao/openquantum · .agents/skills/clifft-sampling/SKILL.md · 用固定 Clifft 对 Clifford+T 电路做带噪采样或 Stim 格式的纠错记录采样,按活跃宽度控制成本,可选最终测量密度矩阵参考。
git:20261012.5ce3b3e · audit A · 71 stars
compact-optimization SKILL.md skill
xi-zhao/openquantum · .agents/skills/compact-optimization/SKILL.md · 用固定 Compact 执行线路优化与独立等价对照,解释输入语义、独立数值对照、成本与科学边界。
git:20261012.5ce3b3e · audit A · 71 stars
cqlib-kernel SKILL.md skill
xi-zhao/openquantum · .agents/skills/cqlib-kernel/SKILL.md · 用固定 cqlib-qml 执行角度编码核与 QSVM,解释输入语义、独立数值对照、成本与科学边界。
git:20261012.5ce3b3e · audit A · 71 stars

Every file in xi-zhao/openquantum

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