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

86%

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

86%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-architected reference skill: executable quick-start and template code, clean progressive disclosure to six real reference files, and practical best-practices/troubleshooting sections. The weakest areas are mild verbosity in the per-reference topic lists and the absence of an explicit validation feedback loop for expensive hardware/batch operations.

Suggestions

Trim or collapse the "Common topics" bullet lists under each Core Capabilities section, since they duplicate the contents of the referenced files — keep the link and a one-line scope summary instead.

Add an explicit validate→fix→retry checkpoint sequence to the Hardware Execution Template (e.g. validate against device.metadata.nx_graph, fix and re-validate, only then submit) to turn the implicit best-practice advice into an actionable loop.

For the Noise Study Template, add a sanity-check step (e.g. confirm the p=0.0 result matches the noiseless simulator output) before trusting the swept results.

Dimension	Reasoning	Score
Conciseness	Mostly efficient — the body is dominated by executable code and structured lists with no padding of basic concepts Claude already knows — but the per-reference "Common topics" bullet lists lightly duplicate content already in the referenced files and could be trimmed.	4 / 5
Actionability	Multiple copy-paste-ready, fully executable examples (basic circuit, parameterized sweep, variational/hardware/noise templates) cover the common cases, matching the 5 anchor for concrete runnable guidance.	5 / 5
Workflow Clarity	Clear organization (install → quick start → capabilities → patterns → best practices → issues) with validation guidance present in best practices ("test on simulators first", "validate circuits against device constraints", "validate correctness after transformation"), but there is no explicit validate→fix→retry checkpoint sequence for hardware execution or batch noise studies.	4 / 5
Progressive Disclosure	SKILL.md is a concise overview that points via clearly-signaled markdown links to six one-level-deep reference files (building.md, simulation.md, transformation.md, hardware.md, noise.md, experiments.md), all of which exist, giving easy navigation matching the 5 anchor.	5 / 5
	Total	18 / 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-structured description that clearly states what the skill is for, when to use it, and how it differs from adjacent quantum frameworks. The only mild gap is specificity — it leans on use-case triggers rather than enumerating concrete capabilities.

Dimension	Reasoning	Score
Specificity	Names the domain ("Google quantum computing framework") plus several concrete actions — targeting Google Quantum AI hardware, designing noise-aware circuits, running quantum characterization experiments, noise modeling, low-level circuit design — but stops short of a comprehensive capability enumeration like the 5 anchor.	4 / 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, matching the 5 anchor pattern.	5 / 5
Trigger Term Quality	Good coverage of natural terms a quantum user would say ("Google Quantum AI hardware", "noise-aware circuits", "quantum characterization experiments", "noise modeling"); a few common synonyms (e.g. "quantum circuits", "qubits", "Sycamore") are missing, so it falls just below the comprehensive 5 anchor.	4 / 5
Distinctiveness Conflict Risk	Explicit routing ("For IBM hardware use qiskit; for quantum ML with autodiff use pennylane; for physics simulations use qutip") carves out a clear niche against sibling quantum skills with minimal conflict risk.	5 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/quantum/cirq/SKILL.md
Commit: 1d182e9

Reviewed: 1 day 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.