qutip
Quantum physics simulation library for open quantum systems. Use when studying master equations, Lindblad dynamics, decoherence, quantum optics, or cavity QED. Best for physics research, open system dynamics, and educational simulations. NOT for circuit-based quantum computing—use qiskit, cirq, or pennylane for quantum algorithms and hardware execution.
85
81%
Does it follow best practices?
Impact
90%
1.40xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong description with excellent trigger terms, clear 'when to use' guidance, and outstanding distinctiveness through explicit negative triggers. Its main weakness is that it describes the domain rather than listing specific concrete actions the skill performs—it reads more like a library description than an action-oriented skill description. Adding specific verbs/actions would elevate the specificity score.
Suggestions
Add concrete action verbs describing what the skill does, e.g., 'Solves master equations, simulates Lindblad evolution, models decoherence channels, computes steady states, and plots Wigner functions.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (quantum physics simulation for open quantum systems) and mentions some specific areas like master equations, Lindblad dynamics, decoherence, quantum optics, and cavity QED, but doesn't list concrete actions the skill performs (e.g., 'solve master equations', 'simulate Lindblad evolution', 'plot Wigner functions'). | 2 / 3 |
Completeness | Clearly answers both 'what' (quantum physics simulation library for open quantum systems) and 'when' (explicit 'Use when' clause listing trigger scenarios, plus 'Best for' and 'NOT for' guidance). The explicit trigger guidance and anti-triggers make this very complete. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms a physics researcher would use: 'master equations', 'Lindblad dynamics', 'decoherence', 'quantum optics', 'cavity QED', 'open quantum systems', 'physics research'. Also includes negative triggers distinguishing from circuit-based quantum computing with specific alternative tool names. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche in open quantum systems simulation, and explicitly differentiates itself from circuit-based quantum computing tools (qiskit, cirq, pennylane). The 'NOT for' clause is an excellent conflict-reduction mechanism. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill with excellent actionability and progressive disclosure. The code examples are complete and executable, and the reference structure is clean and navigable. The main weaknesses are moderate verbosity (three full workflow examples could be condensed or moved to references) and missing validation/convergence-checking steps within the workflows themselves.
Suggestions
Move 1-2 of the Common Workflows examples to a reference file to reduce the main skill's length, keeping only the most representative one (e.g., Jaynes-Cummings as it covers the most concepts).
Add explicit validation checkpoints to workflows, such as checking operator dimensions with `.dims`, verifying Hilbert space convergence by comparing results with different N values, or checking that density matrices remain physical (trace=1, positive semidefinite).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but includes some unnecessary verbosity. The Common Workflows section with three full examples (damped oscillator, entanglement dynamics, Jaynes-Cummings) is extensive and could be trimmed or moved to a reference file. The Quick Start section overlaps with the Core Capabilities section. However, it generally avoids explaining basic quantum mechanics concepts Claude would know. | 2 / 3 |
Actionability | All code examples are fully executable with proper imports, concrete parameter values, and complete workflows from setup to visualization. The solver selection guide provides clear decision criteria. Installation commands are copy-paste ready. | 3 / 3 |
Workflow Clarity | The common workflows are well-sequenced with clear steps (define parameters → build Hamiltonian → set initial state → evolve → visualize), but there are no validation checkpoints. For numerical simulations, there should be explicit verification steps like checking Hilbert space convergence or validating operator dimensions. The tips section mentions convergence checking but doesn't integrate it into the workflows. | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure with a clear overview in the main file and well-signaled one-level-deep references to five specific reference files. Each section ends with a clear pointer to the relevant reference document, and the References section provides a clean index of all supplementary files. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
Total | 10 / 11 Passed | |
- Repository
- K-Dense-AI/claude-scientific-skills
- Commit
b58ad7e
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.