Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add xi-zhao/OpenQuantum --skill pasqal-experimentsgit 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/pasqal-experiments)<a href="https://agentmods.dev/skills/xi-zhao/openquantum/pasqal-experiments"><img src="https://agentmods.dev/badge/skills/xi-zhao/openquantum/pasqal-experiments/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/xi-zhao/openquantum/pasqal-experiments"><img src="https://agentmods.dev/badge/skills/xi-zhao/openquantum/pasqal-experiments.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00073 | $0.01298 |
| Opus 5.5 | $0.00029 | $0.00519 |
| Sonnet 5.5 | $0.00015 | $0.00260 |
| Haiku 4.5 | $0.00007 | $0.00130 |
Grade A, and why
pasqal-experiments 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pasqal 中性原子实验
使用本 Skill 完成从问题到实验数据的七个阶段。工作流复用 Pasqal agent-marketplace 的方法和接口契约， 按 OpenQuantum 的权限与科学证据规则适配。读取工作流、命令与文件合同，按需读取上游方法资料。
环境与执行
- Desktop/源码：
node scripts/sdk-access.mjs inspect pulser-dynamics返回固定 Python 环境和project绝对目录。 尚未准备时，单独执行返回的setup命令。环境保持 Pulser 1.9.1，增加pasqal-cloud==0.24.0。 - 本 Skill 目录与返回的
project是同级目录：<project>/../pasqal-experiments/。 用其scripts/experiment.py --help查看辅助命令。Codex 用本 Skill 的scripts/sdk-access.mjs inspect pulser-dynamics定位插件内环境，继续使用同一相对关系读取本地工作流和脚本；不依赖 GitHub 上尚未发布的文件。 - Agent 通过宿主现有代码 Tool 保存并运行任意原生程序。
pulser、pulser_simulation、pasqal_cloud全部公开 API 可用，包括参数化序列、映射寄存器、各 backend、jobs、batches、workloads 和原生连接。 辅助 CLI 的扫描合同不是 SDK 的能力上限；复杂扫描、校准、优化及非计数结果使用原生 API。 - 辅助 CLI 要求单文件研究模块：两个入口函数、研究常量与辅助函数放在同一序列文件，不从本地模块或动态代码加载。 允许的数值库与环境核对见命令合同。代码、包版本或依赖锁变化后须重新准备和审阅计划； 旧任务仍可恢复、采集或取消。多文件研究项目使用宿主代码 Tool 直接调用原生 SDK。
- 现有
simulate_pulser_rydberg保持其本地便捷合同。Skill 不启动额外 Agent Runtime，也不新增任意代码执行 MCP。
七阶段与交付
| 阶段 | 需要形成的工件 |
|---|---|
| application-to-idea | 方法选择、经典基线、可测观测量、规模与局限的 idea note |
| idea-to-spec | 带单位、来源、几何、扫描、噪声模型、shots 与待决问题的 spec JSON |
| spec-to-sequence | build_sequence(device=None, **params) 与 compute_observable(counts) 的真实 Pulser 程序 |
| validate-emu | 理想本地扫描、解析/小系统对照、序列与原子顺序证据 |
| noise-emulate | 明确来源的噪声扫描；需要时转 Cloud EMU_MPS，保存模型及收敛条件 |
| qpu-submit | 经审阅的序列计划、项目、设备快照、总 shots、云提交收据与恢复记录 |
| harvest-and-analyze | 原始 counts/status、观测量及误差、基线比较、图形和失败/缺失点 |
真实 Cloud EMU 与 QPU 都是外部操作，可能计费。先形成 prepare 计划，说明项目、region、设备、
shots、开放批次及噪声配置，再按用户已有授权与宿主审批执行。--approve-plan 只绑定已审阅内容，
不代替授权。缺失凭据在认证入口配置，不能要求用户把秘密发到聊天。
提交后保留收据。超时、取消本地进程或未知响应不证明远端未提交；用 request tag/批次 ID 恢复， 不能删除收据后重发。关闭批次仍会执行已有 jobs；取消请求不保证停止已经完成或正在执行的 shots。
科学边界
- 不擅自缩小寄存器、改变几何或换设备。缩小后的实验单独保存 spec，并说明有限尺寸和边界条件改变。
- Pulser 时长为 ns、距离为 µm、Rabi/失谐为 rad/µs；MHz 转换是
2*pi*MHz。 - 保存实际
register.qubit_ids，按此顺序解释位串。需要几何顺序的观测量必须在 spec 中声明atom_ids并核对。 - 论文噪声、设备快照噪声和假设噪声分开命名。无噪声参数时不补造校准值；不能丢弃未知噪声字段后仍宣称复现原模型。
- 原始数据先落盘，再计算观测量。保留不完整、失败和不一致，不静默归一化、截断修正值或删除扫描点。
- 辅助分析是 L1 数值事实，
scientificValidation=not_evaluated。bootstrap 与模型一致性不是科学 Acceptance； 需要最终科学验收时另走既有 Validator、Profile、物化和 central Acceptance Builder。
What ships with it
28 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.
- examples/rabi_sequence.py 788 B runs code
- examples/rabi_spec.json 457 B
- LICENSE.upstream 11 KB
- NOTICE.md 1.9 KB
- references/execution.md 6.6 KB
- references/workflow.md 6.1 KB
- scripts/cloud.py 3.8 KB runs code
- scripts/experiment.py 7.3 KB runs code
- scripts/workflow.py 35 KB runs code
- test/workflow_test.py 32 KB runs code
- upstream-manifest.json 2.4 KB
- upstream/examples/literature_z2_reproduction/literature_z2_reproduction_sequence.py 16 KB runs code
- upstream/examples/literature_z2_reproduction/literature_z2_reproduction_spec.json 4.0 KB
- upstream/examples/literature_z2_reproduction/README.md 7.6 KB
- upstream/examples/square_lattice_eom_quench/README.md 4.4 KB
- upstream/examples/square_lattice_eom_quench/square_lattice_eom_quench_sequence.py 5.9 KB runs code
- upstream/examples/square_lattice_eom_quench/square_lattice_eom_quench_spec.json 2.8 KB
- upstream/examples/triangular_lattice_phases/README.md 7.3 KB
- upstream/examples/triangular_lattice_phases/triangular_lattice_phases_sequence.py 13 KB runs code
- upstream/examples/triangular_lattice_phases/triangular_lattice_phases_spec.json 3.3 KB
- upstream/skills/application-to-idea/references/emulation-ladder.md 4.5 KB
- upstream/skills/application-to-idea/references/handoff-template.md 4.6 KB
- upstream/skills/application-to-idea/references/method-catalog.md 9.8 KB
- upstream/skills/application-to-idea/references/pasqal-stack.md 8.0 KB
- upstream/skills/application-to-idea/references/pulser-primitives.md 5.2 KB
- upstream/skills/application-to-idea/references/selection-rubric.md 3.9 KB
- upstream/skills/application-to-idea/references/sources.md 2.4 KB
- upstream/skills/application-to-idea/support/validate_idea_note.py 5.1 KB runs code
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.
- 4d ago First seen · 57 lines · 73 tokens per session scan A 04435df9f043
pasqal-experiments is a skill published in the GitHub repository xi-zhao/OpenQuantum (75 stars, last pushed yesterday), licensed MIT. It adds 73 tokens to every session and 1,298 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-13.
Other skills, from other repositories
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.
rhylthyme
Schedule multi-step procedures that a person carries out against a clock, with parallel tracks, shared equipment and steps that end when the person says so. Use when turning a lab protocol, recipe, event run sheet or workout into a timed plan; when several procedures must share one instrument (one centrifuge, one…
memory-search-mcp
Long-term memory and context retrieval for AI agents. Semantic search across conversation history with care-weighted relevance.
gc-minimal-zine-poster-v0-3
Generate or analyze poetic paper-texture minimal zine posters with large negative space, a small editorial collage or focal element, experimental typography, and one clear color accent. Use when the user gives a theme, sentence, article, mood, object, photo, content brief, reference images, or an image folder and…
ask-sonner
Guide to Sonner, the React toast library — install and wire up the Toaster, pick the right toast() call, promise and loading toasts, updating, dismissing and persisting toasts, styling, theming and icons, positioning and multiple toasters. Use when working with Sonner or troubleshooting it — toasts that don't appear…
kill-ai-slop
Find and remove AI slop — the generic, machine-default visual and copy tics of vibe-coded products — from a web project. Use when the user asks to "kill AI slop", "de-slop", "remove the AI look", "make this not look AI-generated", or clean up a landing page / UI / docs that feels templated. Detects and fixes the…