unitarylab/quantum-practices
173Last commit Aug 14, 2026
quantum-practices DSH plugin
Quantum-Practices is a DeepSeek Harness plugin that registers a read-only tool named `quantum_practices`. It allows agents to list, search, and retrieve structured quantum algorithm practice guides from a built-in immutable catalog. The catalog covers 10 categories including primitives, linear systems, cryptography, Hamiltonian simulation, and more, with multi-simulator support (UnitaryLab, Qiskit, PennyLane).
How to install the quantum-practices DSH plugin
dsh plugin --profile web add "/path/to/quantum-practicesCopying does not run this command. Review the repository and version before installing the quantum-practices DSH plugin.
quantum-practices DSH plugin data source
quantum-practices DSH plugin snapshot date: Aug 16, 2026
discovered
What the quantum-practices DSH plugin can do
- Read-only runtime: no network, subprocess, filesystem writes, Python execution, or native code.
- Progressive disclosure: root SKILL.md is lightweight; algorithm and simulator guides load only when needed.
- Multi-simulator support: provides clear selection rules for UnitaryLab (default), Qiskit, and PennyLane.
- Covers 10 algorithm categories with best-practice guides for each.
Where the quantum-practices DSH plugin fits
- Reviewing quantum algorithm implementation details (e.g., HHL matrix constraints) before coding.
- Comparing different algorithms (e.g., Trotter vs QDrift for Hamiltonian simulation) to choose the right approach.
- Recommending a simulator (UnitaryLab, Qiskit, or PennyLane) based on the user's task (learning, noise models, differentiable optimization).
- Checking common implementation pitfalls for algorithms like Grover or QPE before writing code.
Who the quantum-practices DSH plugin is for
- Quantum algorithm developers and researchers who need quick, structured guidance.
- Educators and students in quantum computing looking for educational-friendly practice guides.
quantum-practices DSH plugin limitations
- Does not execute algorithm code; only provides guide text and reference material.
- Does not include a Python runtime or install dependencies; users must set up their own environment to run examples.
- The catalog is immutable at build time and only updated via upstream GitHub syncs (not real-time).
- No network or subprocess access; the tool is entirely read-only.
quantum-practices DSH plugin: from the repository README
Quoted from the unitarylab/quantum-practices README, the upstream source of the quantum-practices DSH plugin. Copyright remains with the original authors.
· <a href="#chinese">中文</a> </p> </div> --- <a name="english"></a> ## English ### What is this? **Quantum-Practices** is a DeepSeek Harness tool bundle for quantum algorithm best practices. It provides structured, reviewable guidance to DeepSeek Harness agents through a read-only model-facing tool. As a DeepSeek Harness plugin, it registers one read-only `quantum_practices` tool for listing, searching, and reading packaged quantum algorithm practice guides from an immutable build-time catalog. Quantum-Practices is based on and adapted from the GitHub project [unitarylab/quantum-skills](https://github.com/unitarylab/quantum-skills). The original project provides the quantum algorithm guide corpus; this repository reworks that foundation into a DeepSeek Harness tool bundle with a generated, read-only practice catalog. --- ### ✨ Key Features - **Progressive Disclosure** — Root `SKILL.md` is lightweight; algorithm and simulator guides load only when needed. - **DeepSeek Harness Tool Bundle** — `quantum_practices` exposes `list`, `search`, and `get` without executing code. - **Read-Only Runtime** — No network, subprocess, filesystem writes, Python execution, c
Read the full READMERepository license: NOASSERTION
quantum-practices DSH plugin questions
How do I install Quantum-Practices into DeepSeek Harness?
You can install it using the CLI: `npx @deepseek-ai/dsh@0.1.0-rc.6 plugin --profile web add github:unitarylab/quantum-practices#main` for the Web UI, or replace `--profile web` with `--profile headless` for the headless CLI. After installation, restart DeepSeek Harness Web if you use the Web UI.
What algorithms are covered by Quantum-Practices?
The plugin covers 10 categories: primitives (Grover, QPE, etc.), linear systems (HHL, LCU, etc.), cryptography (Shor, discrete logarithm), Hamiltonian simulation (Trotter, QDrift, etc.), Schrodingerization, eigensolvers, gradients, quantum machine learning (VQE, QAOA, etc.), state preparation, and quantum error correction (qLDPC, CSS codes). Each category has multiple practice guides.
Can Quantum-Practices execute Python code?
No, it is a read-only tool. It does not execute any code, including Python scripts in the `algorithms/` directory. It only provides guide text and reference material. You need to set up your own Python environment to run examples.
Which simulators does Quantum-Practices support?
It supports three simulators: UnitaryLab (recommended for learning and algorithm demos), Qiskit (for noise models and IBM hardware workflows), and PennyLane (for differentiable hybrid optimization). The plugin provides clear selection rules in the guides.
How do I search for a specific practice guide?
You can use the `quantum_practices` tool with the action `search` and a query string. For example, `quantum_practices(action="search", query="HHL linear system")`. The tool will return matching guides. You can also use `list` to see all available guides.