Borrowing it
Nothing to install: this file belongs to xi-zhao/OpenQuantum. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/xi-zhao/OpenQuantum/main/.agents/skills/qmclaw-workbench/SKILL.mdgit clone --depth 1 https://github.com/xi-zhao/OpenQuantumWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/xi-zhao/openquantum/qmclaw-workbench)<a href="https://agentmods.dev/skills/xi-zhao/openquantum/qmclaw-workbench"><img src="https://agentmods.dev/badge/skills/xi-zhao/openquantum/qmclaw-workbench.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00126 | $0.00967 |
| Opus 5 | $0.00063 | $0.00483 |
| Sonnet 5 | $0.00025 | $0.00193 |
| Haiku 4.5 | $0.00013 | $0.00097 |
Grade A, and why
qmclaw-workbench scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually 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。
工作流
- 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。 - 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。
- 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。 - 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：
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：运行一个有界、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
- Tool 成功只代表 OpenQuantum 的本地 QMClaw 模拟合同执行完成。
- summary 中的共振频率、T1、T2*、π 脉冲幅度或 RB 衰减参数都是模拟真值/工程摘要，不是实验拟合结论。
- Tool 内部只检查返回数据的有限值、形状和资源边界，不产生独立 Scientific Validator observations。
- 不把上游 Skill 中的统一 T1、XEB、SNR 或 fidelity 阈值当成跨设备科学标准。
- 没有真实 Dataset、设备版本、来源链、Validator observations 和 Acceptance Profile 时，不得宣称调校或科学验收通过。
- 用户要求真实硬件、自动参数写回或实验室部署时，明确说明当前
hardwareExecutionEnabled=false；这些动作需要单独的 LabRAD Adapter、设备白名单、参数 envelope、Harness 审批和回滚证据。
输出格式
回答至少包含：
- 实验类型、量子比特、points/shots 和 seed；
- 使用的 SI 参数与主要模拟摘要；
sourceKind=simulation；scientificValidation=not_evaluated；- 如果用户目标是真实调校，列出仍缺少的硬件 Dataset、设备配置和审批步骤。
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago Changed · -2 lines 1a871810be70
- 4d ago First seen · 67 lines · 126 tokens per session scan A 1387898e70fe
qmclaw-workbench is a skill published in the GitHub repository xi-zhao/OpenQuantum (48 stars, last pushed today), licensed MIT. It adds 126 tokens to every session and 967 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
i4h-catheter-navigation
Overview of workflows/catheternavigation/ (fluorosim DRR, XPBD physics, vasculature digital twin). Use when the user asks what the catheter navigation workflow is, what's supported, or where to start.
i4h-catheter-navigation-viewport
Launch the interactive Slang fluoroscopy viewport with XPBD catheter physics. Use when asked to open the viewport, teleop a catheter, or demo fluoro navigation.
academic-research
Search academic papers, scholarly articles, and research publications through SandBase. Use when asked for literature review, academic citations, scholarly research, paper discovery, or scientific evidence gathering.
alexandria
Reach for this when a research question needs cited sources across academic papers, public domain books, legal records, government archives, security advisories, news, or developer documentation. Alexandria is an MCP server backed by 152 public digital libraries; use it whenever an answer should point at real…
memory-search-mcp
Long-term memory and context retrieval for AI agents. Semantic search across conversation history with care-weighted relevance.
pin-and-lock
Entering digits on native (non-IME) PIN pads, and setting/clearing a secure lock screen required by AndroidKeyStore / Keystore-backed crypto flows. Use when a task needs to unlock a device, enter a PIN, or set/clear a device lock.