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

83%

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

78%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, actionable skill body with strong progressive disclosure into verified reference files and concrete executable templates. The main improvements are trimming mild duplication, completing the placeholder cost function, and adding an explicit validation feedback loop for hardware runs.

Suggestions

Tighten the 'Common topics' bullet lists under each Core Capability section, since they duplicate the contents of the referenced files and add tokens without new information.

Replace the placeholder cost function in the Variational Algorithm Template ('Calculate cost based on state') with a concrete, runnable example so the template is fully copy-paste ready.

Add an explicit validate->fix->retry feedback loop for hardware execution (e.g., simulate -> validate against device constraints -> submit -> store results immediately -> inspect), with hard checkpoints, given that hardware runs are expensive and not easily reversible.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with executable code and tight Quick Start examples, but the opening one-line description of what Cirq is and the enumerated 'Common topics' lists under each capability mildly restate knowledge or duplicate reference content that could be trimmed.	4 / 5
Actionability	Provides copy-paste-ready install commands and concrete executable code across Quick Start and three templates, but the variational algorithm template leaves a placeholder cost function ('Calculate cost based on state') that is a minor gap in fully executable guidance.	4 / 5
Workflow Clarity	Sequences for hardware execution and optimization are clear with validation cues ('test on simulators first', 'validate circuits against device constraints', 'validate correctness after transformation'), but it lacks an explicit validate->fix->retry feedback loop with hard checkpoints for expensive/destructive hardware runs.	4 / 5
Progressive Disclosure	The SKILL.md body is a clear overview that points to six real one-level-deep reference files (building.md, simulation.md, transformation.md, hardware.md, noise.md, experiments.md), each clearly signaled with markdown links and well-organized into discoverable sections.	5 / 5
	Total	17 / 20 Passed

Description

87%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.

A strong, well-targeted description that clearly states what the skill does, when to use it, and when to prefer alternatives. It is specific and distinctive, with only minor room to make the listed capabilities more granular.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('designing noise-aware circuits', 'running quantum characterization experiments', 'noise modeling', 'low-level circuit design'), but the actions are stated at a relatively high level rather than as granular operations, leaving minor coverage gaps short of fully comprehensive.	4 / 5
Completeness	Explicitly answers both 'what' (Google quantum computing framework, best for Google hardware/noise modeling/low-level circuit design) 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	Includes natural phrases users would say ('quantum computing', 'Google Quantum AI hardware', 'noise-aware circuits', 'IBM hardware', 'quantum ML', 'physics simulations') with good coverage, though a few synonyms/variations are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear Google-quantum niche and explicitly routes adjacent needs to other skills ('For IBM hardware use qiskit; for quantum ML with autodiff use pennylane; for physics simulations use qutip'), minimizing conflict risk.	5 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/cirq/SKILL.md
Commit: 9cf7d9a

Reviewed: 3 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.