Quantum-Practices is a DeepSeek Harness tool bundle and cross-agent skill package for quantum algorithm best practices. It provides structured, reviewable guidance for GitHub Copilot, DeepSeek Harness, Claude Code, and other Agent Skills-compatible systems.
As an Agent Skills package, it guides agents through progressive SKILL.md routing before code generation. 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.
✨ 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, credentials, or native code.
Best-Practice Coverage — Primitives, linear systems, cryptography, Hamiltonian simulation, PDE solvers, eigensolvers, gradients, and quantum error correction.
— UnitaryLab (recommended), Qiskit, and PennyLane, with clear selection rules.
dsh-unitarylab-quantum-practices · DSH Hub
Multi-Simulator Support
Run-Ready Setup — Pre-built wheels for Windows, macOS, and Linux; uv-based one-command install.
Education-Friendly — Suitable for concept explanation, circuit design, code review, and hands-on demos.
Install into your project using bunx (recommended) or npx:
# Using Bun (recommended)
bunx skills add https://github.com/unitarylab/quantum-practices
# Using npm / npx
npx skills add https://github.com/unitarylab/quantum-practices
This places the skill under .agents/skills/quantum-practices/ in your workspace — Copilot will discover it automatically.
Or clone manually:
# macOS / Linux
git clone https://github.com/unitarylab/quantum-practices \
.agents/skills/quantum-practices
# Windows (PowerShell)
git clone https://github.com/unitarylab/quantum-practices `
.agents/skills/quantum-practices
The skill itself requires no Python installation. The UnitaryLab simulator is only needed when you intend to run code — setup instructions are inside simulators/unitarylab/SKILL.md.
DeepSeek Harness Plugin
For most users, install Quantum-Practices into the DeepSeek Harness profile you use, then ask your agent to consult Quantum-Practices before answering quantum algorithm questions.
If you use the Web UI:
npx @deepseek-ai/dsh@0.1.0-rc.6 plugin --profile web add \
github:unitarylab/quantum-practices#main
npx @deepseek-ai/dsh@0.1.0-rc.6 --profile headless \
"Use the quantum_practices tool to find the HHL practice guide and explain the required matrix constraints."
After installation, users can ask naturally. The model should call quantum_practices in the background:
Use Quantum-Practices to review HHL before explaining the matrix constraints on A.
Before writing Grover code, check Quantum-Practices and list the common implementation pitfalls.
Use Quantum-Practices to compare quantum phase estimation and the quantum Fourier transform.
Consult Quantum-Practices and recommend a simulator for a variational quantum algorithm.
Check Quantum-Practices and explain how Trotter and QDrift differ for Hamiltonian simulation.
By default, get returns a brief, token-conscious view with the most relevant sections. The model should request detail="full" only when the user needs full implementation notes, complete examples, or debugging context.
Developers can also inspect the tool contract directly:
quantum_practices(action="list")
quantum_practices(action="search", query="HHL linear system")
quantum_practices(action="get", id="algorithms/linear-systems/hhl")
quantum_practices(action="get", query="Explain HHL matrix constraints")
quantum_practices(action="get", query="Implement HHL with a 2x2 example", detail="full")
The DSH plugin never executes algorithms/**/scripts/*.py and never installs or imports Python dependencies.
Build and Verify
npm ci
npm run check
npm pack --dry-run --json
npm run build regenerates src/generated/skill-catalog.ts and compiles the committed lib/ release artifact.
Python Dependencies
requirements.txt is only for optional Python environments used to run examples generated from these skills. It is not part of the DeepSeek Harness plugin install path.
💡 Usage
This skill is automatically invoked by Copilot when you ask about quantum computing topics. The agent reads the relevant SKILL.md files and drills down to the appropriate leaf-level guide before generating any code.
Example prompts:
Prompt
What happens
Implement Grover's algorithm using UnitaryLab
Loads primitives guide — amplitude amplification
Explain the HHL algorithm with a 2×2 example
Loads linear-systems/hhl guide with matrix demo
Simulate 1D heat equation with Schrodingerization
Loads schrodingerization/heat-1d guide
Compare Trotter and QDrift for Hamiltonian simulation
Loads hamiltonian-simulation guide
Run Shor's algorithm on n=15
Loads cryptography/shor guide
License
This repository source is licensed under the MIT License.
The unitarylab wheel files may include proprietary binary components; see
the LICENSE and LICENSE-PROPRIETARY files bundled inside those wheels.
npx @deepseek-ai/dsh@0.1.0-rc.6 --profile headless \
"Use the quantum_practices tool to find the HHL practice guide and explain the required matrix constraints."
