CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./backend/cli/skills/quantum/cirq/SKILL.md
SKILL.md
Quality
Evals
Security

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 library skill: lean inline content, mostly executable examples, validation guidance embedded in best practices, and exemplary progressive disclosure with six real one-level-deep reference files. The residual gaps are small — a few non-standalone code snippets and placeholders, and validation advice that is scattered rather than sequenced.

DimensionReasoningScore

Conciseness

The body is efficient — it assumes Claude's competence, explains no quantum-computing basics, and keeps code examples tight with inline comments. Minor trims are possible (the 'Common topics' bullet lists partially duplicate reference-file content, and 'Additional Resources' adds link padding), so it matches anchor 4 rather than the perfectly lean anchor 5.

4 / 5

Actionability

Mostly executable guidance: the quick-start circuit, parameter sweep, and the variational/noise templates are concrete runnable code, and Common Issues gives specific fixes. Minor gaps remain — the parameterized example reuses q0/simulator defined only in a prior code block, the hardware template contains a '# Setup workspace...' placeholder with an undefined variable, and the noise study relies on an undefined circuit — fitting anchor 4, not fully copy-paste-ready anchor 5.

4 / 5

Workflow Clarity

Validation checkpoints are present and spread appropriately ('Always test on simulators first', 'Validate circuits against device constraints before execution', 'Validate correctness after transformation'), and the Common Issues section provides error-recovery guidance, but the steps live in scattered best-practice bullets rather than one explicitly numbered sequence — matching anchor 4 with minor sequencing gaps rather than anchor 5's explicit validate-fix-retry loops.

4 / 5

Progressive Disclosure

A clear overview structure: quick-start content stays inline while six detail areas are delegated via well-signaled markdown links (references/building.md, simulation.md, transformation.md, hardware.md, noise.md, experiments.md), each of which exists as a substantial one-level-deep file with no further nesting, and the per-reference topic lists aid navigation — a direct match to anchor 5.

5 / 5

Total

17

/

20

Passed

Description

73%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 description with explicit trigger guidance and excellent distinctiveness via competitor redirects. Its main weakness is that the 'what' is a domain label rather than a list of concrete capabilities (design, simulate, and run quantum circuits), which leaves specificity and completeness just below top marks.

Suggestions

Replace or augment the category label 'Google quantum computing framework' with the skill's concrete actions, e.g. 'Design, simulate, and run quantum circuits on Google Quantum AI hardware...' to raise specificity and completeness.

Add common natural trigger variations users would say, such as 'quantum circuits', 'Sycamore processors', or 'OpenQASM', to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

The description names the domain ('Google quantum computing framework') and 2-3 concrete activities (targeting Google Quantum AI hardware, designing noise-aware circuits, running quantum characterization experiments), but these appear as use-cases rather than a list of the skill's own actions; the core capabilities (designing, simulating, running quantum circuits) are never stated as actions, matching anchor 3 rather than 4.

3 / 5

Completeness

Both parts are present: an explicit 'Use when...' clause with concrete triggers ('targeting Google Quantum AI hardware, designing noise-aware circuits, or running quantum characterization experiments') plus 'Best for' scoping. However, the 'what' is only a one-phrase category label ('Google quantum computing framework') rather than a concrete statement of what the skill does, falling short of anchor 5's fully explicit what-and-when.

4 / 5

Trigger Term Quality

Good natural keyword coverage ('Google Quantum AI hardware', 'noise modeling', 'quantum characterization experiments', 'low-level circuit design', plus qiskit/pennylane/qutip redirects), but common variations like 'quantum circuits' generally, 'Sycamore', or 'OpenQASM' are missing, so it fits anchor 4 rather than 5.

4 / 5

Distinctiveness Conflict Risk

A clear niche (Google quantum hardware, noise modeling, low-level circuit design) is reinforced by explicit redirects ('For IBM hardware use qiskit; for quantum ML with autodiff use pennylane; for physics simulations use qutip'), giving minimal conflict risk with other quantum-framework skills — a direct match to anchor 5.

5 / 5

Total

16

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

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

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.