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

72%

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

The body is highly actionable and well-structured with clean progressive disclosure to verified reference files, but it loses conciseness to inline version/date specifics and duplicated topic lists, and its hardware workflows omit explicit validation feedback loops for costly operations.

Suggestions

Move time-sensitive version pins and dates (e.g., 'cirq==1.6.1', 'August 2025', Python 3.11+) into a dedicated 'Versioning / old patterns' section so the main Installation and Quick Start flow stays lean and date-agnostic.

Trim or remove the 'Common topics' bullet lists under each reference section, since they duplicate content already covered in the linked reference files; rely on the link plus a one-line summary instead.

Add explicit validation checkpoints and a validate→fix→retry loop to the hardware execution workflow (e.g., validate the circuit against device constraints before submitting, and handle job failures with a retry path), given these are costly and hard to reverse operations.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and avoids explaining concepts Claude already knows, but inline time-sensitive specifics (version pins like 'cirq==1.6.1', 'August 2025', Python 3.11+) sit in the main flow rather than a deprecated/old-patterns section, and the per-section 'Common topics' lists partly duplicate the reference files.	2 / 3
Actionability	Provides complete, executable, copy-paste-ready code (basic and parameterized circuits, variational and hardware-execution templates, noise study) plus exact pinned install commands — concrete rather than abstract.	3 / 3
Workflow Clarity	Steps are clearly listed and sequenced (build → simulate → optimize → run; Best Practices per phase) and a troubleshooting section exists, but the costly/hard-to-reverse hardware workflows lack explicit validation checkpoints and validate→fix→retry feedback loops, capping this dimension at 2.	2 / 3
Progressive Disclosure	Body is a clear overview that links to six real, one-level-deep reference files (building, simulation, transformation, hardware, noise, experiments), each signaled with a markdown link and a short topic preview; content is appropriately split with easy navigation.	3 / 3
	Total	10 / 12 Passed

Description

100%

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

The description is specific, complete, and distinctive: it states concrete capabilities, provides explicit 'Use when' triggers, and disambiguates against the most likely competing skills. It is concise without fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — 'targeting Google Quantum AI hardware', 'designing noise-aware circuits', 'running quantum characterization experiments', 'noise modeling', and 'low-level circuit design' — rather than vague domain language.	3 / 3
Completeness	Explicitly answers what ('Google quantum computing framework') and when via a clear 'Use when...' clause spanning hardware targeting, noise-aware circuits, and characterization experiments.	3 / 3
Trigger Term Quality	Covers natural terms a quantum user would say (Google hardware, noise-aware circuits, characterization, IBM hardware, quantum ML, physics simulations); these are the phrasings users reach for when they need this skill.	3 / 3
Distinctiveness Conflict Risk	Carves a clear Google-hardware niche and explicitly routes away from likely rivals ('For IBM hardware use qiskit; for quantum ML with autodiff use pennylane; for physics simulations use qutip'), minimizing wrong-skill triggering.	3 / 3
	Total	12 / 12 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: 757b63b

Reviewed: about 12 hours 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.