cirq
Google quantum computing framework. Use when targeting Google Quantum AI hardware, designing noise-aware circuits, or running quantum characterization experiments. Best for Google hardware, noise modeling, and low-level circuit design. For IBM hardware use qiskit; for quantum ML with autodiff use pennylane; for physics simulations use qutip.
83
81%
Does it follow best practices?
Impact
82%
1.24xAverage 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 skill description that excels at disambiguation and completeness. It clearly identifies its niche (Google quantum hardware), provides explicit trigger conditions, and helpfully redirects to alternative skills for other quantum computing use cases. The main weakness is that the specific capabilities could be more granular—listing concrete actions like circuit compilation, error correction, or specific Cirq operations.
Suggestions
Add more specific concrete actions such as 'compile circuits for Google Sycamore processors', 'perform cross-entropy benchmarking', or 'simulate noisy quantum circuits' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Google quantum computing) and some actions like 'designing noise-aware circuits' and 'running quantum characterization experiments', but doesn't list multiple concrete specific actions comprehensively—e.g., what specific operations like circuit compilation, error mitigation, or qubit calibration are supported. | 2 / 3 |
Completeness | Clearly answers both 'what' (Google quantum computing framework for noise-aware circuits, characterization experiments, low-level circuit design) and 'when' (explicit 'Use when targeting Google Quantum AI hardware, designing noise-aware circuits, or running quantum characterization experiments'). Also includes negative triggers directing to other skills. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'Google Quantum AI hardware', 'noise-aware circuits', 'quantum characterization experiments', 'Google hardware', 'noise modeling', 'low-level circuit design'. Also includes cross-references to competing tools (qiskit, pennylane, qutip) which helps with disambiguation. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche (Google-specific quantum computing) and explicit disambiguation from competing frameworks (qiskit for IBM, pennylane for ML, qutip for physics). This makes it very unlikely to conflict with other quantum computing skills. | 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 strong actionability and excellent progressive disclosure. The main weaknesses are moderate verbosity (redundant topic lists, some explanations Claude doesn't need) and workflow templates that lack explicit validation checkpoints, particularly for hardware execution. The code examples are high quality and the reference file organization is exemplary.
Suggestions
Add explicit validation steps to the hardware execution template (e.g., validate circuit against device constraints, simulate first, then submit) to create a proper feedback loop for this costly operation.
Trim the 'Common topics' bullet lists under each reference section—the reference file links with their one-line descriptions are sufficient for navigation.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-organized but includes some unnecessary verbosity. The 'Common topics' bullet lists under each reference section are somewhat redundant given they point to separate files. The best practices section, while useful, contains some advice Claude would already know (e.g., '2^n grows quickly'). The introductory sentence explaining what Cirq is adds little value. | 2 / 3 |
Actionability | The skill provides fully executable code examples throughout: basic circuit creation, parameterized circuits, variational algorithm template, hardware execution template, and noise study template. All code is copy-paste ready with proper imports and realistic patterns. | 3 / 3 |
Workflow Clarity | The skill provides good templates for common workflows (variational algorithms, hardware execution, noise studies) but lacks explicit validation checkpoints. For hardware execution—a potentially costly/destructive operation—there's no validation step before submission. The best practices mention 'test on simulators first' and 'validate circuits against device constraints' but these aren't integrated into the workflow templates themselves. | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure structure. The main file provides a concise overview with quick start examples, then clearly signals six separate reference files (building.md, simulation.md, transformation.md, hardware.md, noise.md, experiments.md) with descriptive summaries. All references are one level deep and well-organized. | 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.