quantum-guide-algorithms

quantum-guide-algorithms is a skill for Claude Code from xi-zhao/OpenQuantum. It costs 31 tokens per session (3,103 once invoked), scanned A, original, MIT.

A directory for open-source workflows covering quantum algorithms and related classical reference methods. It routes a problem to a smaller method guide instead of requiring one large catalogue to be read first.

In plain words
What is it for?
Use it to find workflows for Shor factoring, discrete logarithms, Simon's problem, eigenvalues, excited states, quantum gradients, Hamiltonian decompositions, and other listed algorithms.
Why use it?
It removes the work of finding the right algorithm for a mathematical or quantum-computing task. It also includes checks and limitations for methods such as factoring, eigenvalue solving, gradients, and variational optimization.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to find workflows for Shor factoring, discrete logarithms, Simon's problem, eigenvalues, excited states, quantum gradients, Hamiltonian decompositions, and other listed algorithms.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/xi-zhao/openquantum/quantum-guide-algorithms
Install

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.

Any agent
npx skills add xi-zhao/OpenQuantum --skill quantum-guide-algorithms
Clone the repo
git clone --depth 1 https://github.com/xi-zhao/OpenQuantum

Made for: Claude Code.

Wrote 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.

agentmods badge for quantum-guide-algorithms

README.md
[![agentmods](https://agentmods.dev/badge/skills/xi-zhao/openquantum/quantum-guide-algorithms/github.svg)](https://agentmods.dev/skills/xi-zhao/openquantum/quantum-guide-algorithms)
Your own site
<a href="https://agentmods.dev/skills/xi-zhao/openquantum/quantum-guide-algorithms"><img src="https://agentmods.dev/badge/skills/xi-zhao/openquantum/quantum-guide-algorithms/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.

agentmods 80×15 button for quantum-guide-algorithms

Your own site · 80×15
<a href="https://agentmods.dev/skills/xi-zhao/openquantum/quantum-guide-algorithms"><img src="https://agentmods.dev/badge/skills/xi-zhao/openquantum/quantum-guide-algorithms.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,103 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00031 $0.03103
Opus 5.5 $0.00012 $0.01241
Sonnet 5.5 $0.00006 $0.00621
Haiku 4.5 $0.00003 $0.00310

Measured 4d ago against content hash f5cce09b0eba, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

quantum-guide-algorithms 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.

.agents/skills/quantum-guide-algorithms/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

algorithms

本地开源适配。上游指南 ID:algorithms。

分类导航:保留用户显式调用;自动任务直接选择叶子方法 Skill,或使用 quantum-algorithms 查找。

选择工作流

按用户的数学问题、输入表示、计算规模和需要的输出选择一个叶子 Skill。知识解释可直接使用原理;计算任务加载叶子 Skill,使用其中的开源实现和现有代码执行 Tool。无需为阅读指南启动额外服务。

  • quantum-discrete-log:可逆 g^a y^b oracle、循环群 Fourier 采样与同余恢复;不把已知对数写进 oracle。
  • quantum-shor:可逆模乘 oracle、QPE/连分数和因子验证;密集 oracle 的教学规模模拟,失败明确返回需换基数或精度。
  • quantum-simon:二对一 XOR oracle、Hadamard 采样和 GF(2) 零空间恢复;样本不足时不编造 secret。
  • quantum-numpy-minimum-eigensolver:NumPy 最小本征对,明确标记经典算法并报告残差。
  • quantum-numpy-eigensolver:NumPy Hermitian 稠密本征求解,明确标记经典算法并报告特征残差。
  • quantum-vqd:通过逐态重叠惩罚求激发态(VQD),报告能量与态间重叠;惩罚和 ansatz 会影响收敛。
  • quantum-finite-difference:Qiskit FiniteDiffEstimatorGradient,中心差分与显式 epsilon。
  • quantum-linear-combination:Qiskit LinCombEstimatorGradient,实际生成线性组合导数电路。
  • quantum-parameter-shift:Qiskit ParamShiftEstimatorGradient,RY 参数移位规则。
  • quantum-qfi:Qiskit QFI/ReverseQGT,纯态量子 Fisher 信息;不将其等同于任意测量的经典 Fisher 信息。
  • quantum-reverse:Qiskit ReverseEstimatorGradient,反向态矢量导数。
  • quantum-spsa:Qiskit SPSAEstimatorGradient,显式 epsilon、批量与随机种子;单次估计有统计误差。
  • quantum-cartan:实对称 Hamiltonian 的 SO(N) 谱 Cartan 分解;采用 SciPy Schur 替换未开放的 Cartan-Lax 优化器,不宣称复刻其优化轨迹。
  • quantum-qdrift:使用 Qiskit 的显式量子电路,保留输入、方法参数、实际概率或态矢量;模拟器全态读取不代表硬件可高效读取。
  • quantum-hamiltonian-qsp:偶/奇 QSP 多项式通过 LCU 合成 exp(-iHt);稠密 block encoding 与后选择,次数控制截断误差。
  • quantum-taylor:截断 Taylor 级数展开为 Pauli LCU,实际执行 PREPARE/SELECT/unprepare 并报告后选择概率;无量子加速主张。
  • quantum-trotter:使用 Qiskit 的显式量子电路,保留输入、方法参数、实际概率或态矢量;模拟器全态读取不代表硬件可高效读取。
  • quantum-aqc:正定 Hermitian 系统的绝热线性求解路径、条件数相关 schedule 与分片幺正演化;增加 total_time 和 steps 检查绝热与离散误差。
  • quantum-hhl:Hermitian 非奇异 A、QPE、有符号倒数旋转、反 QPE 与后选择;完整解向量来自模拟器,受相位位数和条件数影响。
  • quantum-lcu:使用 Qiskit 的显式量子电路,保留输入、方法参数、实际概率或态矢量;模拟器全态读取不代表硬件可高效读取。
  • quantum-qsvt-qlsa:Hermitian 非奇异矩阵,PennyLane QSVT 和受控 U/U† 后选择;有界奇次几何倒数多项式,输出实际残差,不承诺输入 epsilon 自动满足。
  • quantum-qft:使用 Qiskit 的显式量子电路,保留输入、方法参数、实际概率或态矢量;模拟器全态读取不代表硬件可高效读取。
  • quantum-qsp:QSP/QSVT 相位综合计算 cos(t x) 的有界偶次多项式;报告截断误差和 block 缩放。
  • quantum-vqls:Qiskit 参数电路与全局归一化残差 cost 的变分线性求解;报告数值残差与优化终止原因。
  • quantum-amplitude-amplification:使用 Qiskit 的显式量子电路,保留输入、方法参数、实际概率或态矢量;模拟器全态读取不代表硬件可高效读取。
  • quantum-amplitude-estimation:使用 Qiskit 的显式量子电路,保留输入、方法参数、实际概率或态矢量;模拟器全态读取不代表硬件可高效读取。
  • quantum-grover:使用 Qiskit 的显式量子电路,保留输入、方法参数、实际概率或态矢量;模拟器全态读取不代表硬件可高效读取。
  • quantum-hadamard-test:使用 Qiskit 的显式量子电路,保留输入、方法参数、实际概率或态矢量;模拟器全态读取不代表硬件可高效读取。
  • quantum-hadamard-transform:使用 Qiskit 的显式量子电路,保留输入、方法参数、实际概率或态矢量;模拟器全态读取不代表硬件可高效读取。
  • quantum-qpe:使用 Qiskit 的显式量子电路,保留输入、方法参数、实际概率或态矢量;模拟器全态读取不代表硬件可高效读取。
  • quantum-molecular-dmrg:PySCF 活性空间积分、Jordan-Wigner MPO 与 quimb 双站点 DMRG。使用开源态制备替换闭源 CVD;当前示例的稠密 Hamiltonian 预处理需要 O(4^n) 存储。
  • quantum-qldpc:HGP CSS 校验矩阵、GF(2) 秩、交换关系和 syndrome;码距未计算。解码任务继续使用 ldpc-decoding Skill。
  • quantum-cvqnn:两模有限 Fock 空间的位移、压缩、旋转、Kerr 和分束器层;SciPy 有限差分优化替换 Torch autograd,需增加 cutoff 检查截断。
  • quantum-fermi-hubbard-vqe:开放边界 Hubbard 链,Jordan-Wigner 与全 Fock 空间 VQE;粒子数是测量值,未强制固定粒子数扇区。
  • quantum-ising:开放边界二维矩形 Ising 网格,quimb MPS 与二阶 Strang 演化;报告键维数及截断参数,不分配完整态矢量。
  • quantum-qaoa:无权 MaxCut 的交替 cost/mixer 电路与参数优化;输出平均 cut 和最高概率位串。
  • quantum-qcbm:参数电路 Born 分布拟合目标概率,KL 目标与 total variation 对照。
  • quantum-vqc:RY 特征编码与参数电路二分类;输出训练集指标,不能当作泛化效果。
  • quantum-vqe:实 Pauli Hamiltonian、RY/RZ/CX ansatz 和 SciPy 优化;能量、优化记录及保留的参数可复查。
  • quantum-advection:周期边界、常速一维平流,中心差分和显式薛定谔化电路;不接受并静默回退所谓 block 模式。
  • quantum-heat-1d:齐次一维热方程,周期或零 Dirichlet 边界;显式辅助 Fourier 寄存器的幺正薛定谔化电路、截面恢复和离散热方程参照。
  • quantum-heat-2d:齐次二维方形网格热方程,周期或零 Dirichlet 边界;显式薛定谔化电路。空间与辅助网格误差需要分别收敛。
  • quantum-glued-trees:随机交替叶环连接的双树连续时间邻接矩阵量子行走;稠密编译和出口概率,不宣称搜索加速。
  • quantum-hidden-shift:偶数位二次 bent 函数的 shifted/dual 相位 oracle;其他函数族需要另写任务代码。
  • quantum-mottonen:PennyLane Möttönen 均匀受控旋转态制备;输入正规化后保留复相位。
  • quantum-mps:SVD 分解、可选键截断、显式右规范化与 PennyLane MPSPrep;报告实际制备保真度及辅助位清零概率。
  • quantum-multiplexer:Qiskit StatePreparation/Isometry 的均匀受控门合成;保留复振幅、输出位序与保真度。
  • quantum-pauli:PennyLane ArbitraryStatePreparation 的 Pauli 旋转优化;报告保真度及优化状态,迭代结束不自动代表达到目标误差。
  • quantum-superposition:PennyLane Superposition 的计算基叠加与辅助位清零;系数可为复数。

Read the full file on GitHub · 77 lines

Changes

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.

  1. 4d ago Changed · +4 lines f5cce09b0eba
  2. 22d ago First seen · 73 lines · 31 tokens per session scan A 45ab572a4ea6

Subscribe to this mod's changes

quantum-guide-algorithms is a skill published in the GitHub repository xi-zhao/OpenQuantum (75 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 3,103 once invoked, about $0.0001 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 2026-09-25.

Related

Other skills, from other repositories

code-review

Reviews a supplied code path or diff for correctness, security, maintainability, and style without executing or modifying it.

sandbaseai/sandbase-harness · 25 tokens

memory-search-mcp

Long-term memory and context retrieval for AI agents. Semantic search across conversation history with care-weighted relevance.

CSOAI-ORG/memory-search-mcp · 0 tokens

animate

Build an animation from scratch, making the decisions in the order that determines whether it feels right — should it animate at all, what purpose, which tool, which properties, which curve and duration, how it interrupts, how it exits. Writes the implementation. Use when asked to animate something, add motion, make a…

stvlynn/dsh.fish · 96 tokens

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…

stvlynn/dsh.fish · 100 tokens

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…

stvlynn/dsh.fish · 97 tokens

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…

stvlynn/dsh.fish · 249 tokens