pennylane-differentiable SKILL.md skillA
pennylane-differentiable 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/pennylane-differentiable@git:20261012.5ce3b3ePins git:20261012.5ce3b3e 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/pennylane-differentiable/SKILL.md- Versions recorded
- 3
- Latest version
- git:20261012.5ce3b3e, committed Oct 12, 2026
- First version recorded
- Sep 27, 2026
- Size
- 3,965 bytes
- Repository stars
- 71
- License
- MIT
使用 Xanadu 的 PennyLane 在本地对用户定义量子线路计算原始态概率、Pauli 期望和指定旋转角的解析梯度。.
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
# PennyLane 可微分量子线路 <!-- BEGIN NATIVE SDK ACCESS --> ## 原生 SDK 路径 本能力同时支持 **PennyLane 的原生公开 API**。用户需要 QNode、自定义电路、算符、测量、设备、梯度、变换与混合优化 时，由 Agent 在固定依赖环境中编写和运行任务代码，不限于下文便捷 Tool 的预设模型。 使用 `node scripts/sdk-access.mjs inspect pennylane-differentiable` 定位环境，按[完整 SDK 工作流](../quantum-sdk-workbench/references/workflow.md)执行。模块导航：`pennylane`；导航不是 API 白名单。 下文关于模型、门集、输入与预算的限制描述便捷 Tool 的合同；原生 SDK 另受上游版本、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 --> 当用户需要用 PennyLane 计算线路期望、验证变分线路导数或与其他 SDK 交叉对照时，Agent 经 Harness 调用 `pennylane_local` 提供的 `differentiate_pennylane_circuit`。本 Skill 指导参数选择与结果解释；计算由 default.qubit + Autograd 完成。 - `numQubits` 与 `gates` 定义全零初态的理想酉线路。支持 H、X、Y、Z、S、T、RX、RY、RZ、CX、CZ、SWAP；双比特门的 targets 为 `[control,target]`（SWAP 为两个交换位），角度单位 rad。 - `observables` 是与量子位数同长的 I/X/Y/Z 字符串，最左字符对应 q0。例如 `ZI` 表示 Z0，`XY` 表示 X0Y1；输出期望保留输入顺序。加权 Hamiltonian 可由调用方按系数组合期望和 Jacobian，勿把 Pauli words 当作系数。 - `trainableGateIndices` 明确选择 gates 数组中需要求导的 RX/RY/RZ；每项是独立参数。可填空数组只做仿真。Jacobian 行对应 observables，列严格对应该索引数组的顺序，不是所有旋转门的隐含顺序。 - `amplitudes[k]` 为 `[real,imag]`，概率向量按 q0 在最左的二进制字典序排列。返回 SDK 原始数值，不裁剪、不归一化；`stateNormSquared` 用来检查数值漂移。这些是精确线路仿真的数值期望，不是 finite-shots 频数。 …
Read the whole file at its exact version.
How to install
mdr add xi-zhao/openquantum/pennylane-differentiable@sha256:f03f545e21cfb18dThe line at the top of this page pins the label git:20261012.5ce3b3e, 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_kyg23yqbxcf4pyxg)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Sep 27, 2026 and Oct 12, 2026, about one every 7 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261012.5ce3b3e latest | 2026-10-12 | 5ce3b3e | 3,965 B | A | view · diff |
| git:20261011.ced251b | 2026-10-11 | ced251b | 3,107 B | A | view · diff |
| git:20260927.3f344ad | 2026-09-27 | 3f344ad | 2,579 B | A | view |
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 (3965 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_kyg23yqbxcf4pyxg GET https://markdownregistry.com/api/v1/resolve?ref=xi-zhao/openquantum/pennylane-differentiable GET https://markdownregistry.com/api/v1/blob/f03f545e21cfb18d31ac9cdae219d304b3cb8e221b96edb3dff9f221bc9fae7f
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.