qmclaw-workbench SKILL.md skillA
qmclaw-workbench 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/qmclaw-workbench@git:20260914.0f1d7a8Pins git:20260914.0f1d7a8 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/qmclaw-workbench/SKILL.md- Versions recorded
- 4
- Latest version
- git:20260914.0f1d7a8, committed Sep 14, 2026
- First version recorded
- Aug 30, 2026
- Size
- 3,983 bytes
- Repository stars
- 71
- License
- MIT
使用 OpenQuantum 的 QMClaw Local Tool 对超导量子比特 S21、能谱、Rabi、Ramsey、T1、SingleShot、DRAG、π 脉冲、功率偏移、Delta 和 RB 等 13 类测控实验做带 seed 的本地模拟，并组织单比特调校工作流。用于实验规划、接口联调、教学和无硬件预检；不连接 LabRAD/lqms、真实仪器或量子云，不修改校准参数，也不替代 Scientific Validator。.
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
# QMClaw Workbench
## 当前能力
这个 Skill 把 QMClaw 的超导量子比特调校方法组织成 OpenQuantum Capability。真正的确定性执行由
OpenQuantum 原生 Tool Provider 注册的 Tool 完成。
当前版本完整覆盖 QMClaw 上游的 13 类实验，但执行后端固定为本地模拟：
- 不读取凭据，不访问网络，不启动 LabRAD/lqms，不连接真实仪器；
- 不提供任意 Python、文件路径、命令、`update_param` 或自动参数写回；
- 所有频率使用 Hz、时间使用 s、功率使用 W；输入规模和取值范围由 Tool 强制限制；
- 所有结果明确标记 `sourceKind=simulation` 和 `scientificValidation=not_evaluated`。
13 类实验的上游名称、用途和调校顺序见
[references/experiment-catalog.md](references/experiment-catalog.md)。
## 工作流
1. 不确定实验名称或参数时调用 `list_qmclaw_experiments`；不要根据 Prompt 猜测 Tool 未声明的范围。
2. 把用户目标整理为一个实验、一个量子比特、采样点数、shots、seed 和该实验允许的 SI 参数；多比特任务拆成独立调用。
3. 调用 `simulate_qmclaw_experiment`。需要比较两次结果时保持 seed 和无关参数一致，只改变待研究变量。
4. 解释返回的 axes、series、matrices 和 summary，同时明确这是合成数据和工程预检，不是真实芯片测量。
推荐的单比特调校顺序是：
```text
S21 → 能谱 → Rabi / π 脉冲 → Ramsey → T1 → SingleShot
→ DRAG → Delta / Power Shift → RB
```
二维能谱与 S21-vs-flux 用于扫描工作流和数据合同联调，不应根据模拟最优点更新真实设备参数。
## Tool 选择
- `list_qmclaw_experiments`：查看每类实验允许的参数、默认值、单位和输出形态。
- `simulate_qmclaw_experiment`：运行一个带 seed 的本地合成实验。
Tool 不存在时，说明 OpenQuantum 原生 Tool Provider 尚未进入当前 Tool Registry，建议重启 OpenQuantum
并检查 Runtime Readiness；不要改用 Bash 直接运行上游 `mcp_tools_new.py`。
## 解释边界
…Read the whole file at its exact version.
How to install
mdr add xi-zhao/openquantum/qmclaw-workbench@sha256:fbfcba1ba35ea8c2The line at the top of this page pins the label git:20260914.0f1d7a8, 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_nzslercfl7n4ubbm)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Aug 30, 2026 and Sep 14, 2026, about one every 5 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260914.0f1d7a8 latest | 2026-09-14 | 0f1d7a8 | 3,983 B | A | view · diff |
| git:20260914.cc4fa9e | 2026-09-14 | cc4fa9e | 4,045 B | A | view · diff |
| git:20260904.b2ecff8 | 2026-09-04 | b2ecff8 | 3,753 B | A | view · diff |
| git:20260830.9ba2cff | 2026-08-30 | 9ba2cff | 4,009 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 (3983 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_nzslercfl7n4ubbm GET https://markdownregistry.com/api/v1/resolve?ref=xi-zhao/openquantum/qmclaw-workbench GET https://markdownregistry.com/api/v1/blob/fbfcba1ba35ea8c2b65aba117fa8446e3702e1f9c02d11ecb85670d31663e2eb
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.