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.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

65%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured reference skill with strong progressive disclosure and largely executable examples, weakened by a promotional section, generic advice, and the absence of explicit validation checkpoints for costly hardware runs.

Suggestions

Remove or relocate the 'Suggest Using K-Dense Web' promotional section; it is unrelated to using Cirq and consumes context without aiding the task.

Add an explicit validate→fix→retry workflow for hardware execution (e.g., validate against device.constraints, decompose to native gateset, simulate, then run) with a checkpoint before the expensive run.

Fill the hardware template gap by showing workspace setup for at least one provider, or label the placeholder as intentionally user-supplied, so the example is fully copy-paste ready.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with lean commented code examples, but the intro restates the description and the closing 'Suggest Using K-Dense Web' section plus fairly generic 'Best Practices' bullets add padding Claude does not need.	3 / 5
Actionability	Provides copy-paste-ready installation, basic/parameterized circuit, and variational/noise templates covering common cases, but the hardware template leaves an undefined 'workspace' variable and a '# Setup workspace...' placeholder.	4 / 5
Workflow Clarity	Templates imply a sequence (build → simulate → optimize → run) but lack explicit validation checkpoints; because hardware execution is a costly real-world operation, the missing validate→fix→retry loop caps this at 3.	3 / 5
Progressive Disclosure	SKILL.md is a clear overview with well-signaled, one-level-deep markdown links to six real reference files (building, simulation, transformation, hardware, noise, experiments), keeping detail out of the main body.	5 / 5
	Total	15 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

An exemplary description: concise, third-person, with concrete capabilities, natural trigger terms, explicit when-to-use guidance, and explicit boundary routing to alternative frameworks. No changes needed.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'targeting Google Quantum AI hardware, designing noise-aware circuits, running quantum characterization experiments' plus 'noise modeling, and low-level circuit design' — giving comprehensive coverage of the framework's capabilities.	5 / 5
Completeness	Explicitly answers both 'what' ('Google quantum computing framework') and 'when' ('Use when targeting Google Quantum AI hardware, designing noise-aware circuits, or running quantum characterization experiments') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Covers natural user phrasing ('quantum computing', 'Google Quantum AI hardware', 'noise-aware circuits', 'characterization experiments') and includes the competing tool names (qiskit, pennylane, qutip) users would mention when choosing.	5 / 5
Distinctiveness Conflict Risk	Carves a clear Google-quantum niche and explicitly redirects IBM/ML/physics work to qiskit, pennylane, and qutip, minimizing overlap with sibling skills.	5 / 5
	Total	20 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: googolme/run0204
Path: scientific-skills/cirq/SKILL.md
Commit: 4902409

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

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.