CtrlK
BlogDocsLog inGet started
Tessl Logo

cirq

Cirq is Google Quantum AI's open-source framework for designing, simulating, and running quantum circuits on quantum computers and simulators.

52

Quality

59%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/cirq/SKILL.md

The canonical home for this skill is cirq in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

57%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.

The body is a well-organized reference overview with concrete executable examples and clear pointers to per-topic guides, scoring well on actionability. Its main weaknesses are the missing reference files (broken progressive disclosure), the absence of explicit validation/feedback-loop workflows, and some redundant "Common topics" padding.

Suggestions

Ship the six referenced files (building.md, simulation.md, transformation.md, hardware.md, noise.md, experiments.md) or remove the dangling references so navigation is not broken.

Trim the "Common topics" bullet lists under each capability; a one-line summary plus the reference link is enough once the files exist.

Add at least one explicit validate→fix→retry workflow for hardware execution (e.g. validate against device constraints, run on simulator, then submit, with error-recovery steps) to lift workflow clarity above 3.

DimensionReasoningScore

Conciseness

The body is mostly efficient with executable code and no over-explanation of concepts Claude already knows, but the per-capability "Common topics" bullet lists largely restate what lives in the reference files and could be tightened, keeping it just below the efficient anchor.

3 / 5

Actionability

It provides concrete, runnable code (basic circuit, parameterized sweep) and explicit install commands, plus reusable templates; minor gaps such as the "Setup workspace..." placeholder in the Azure template and the incomplete cost function keep it from fully copy-paste ready.

4 / 5

Workflow Clarity

Best Practices and Common Issues give useful guidance and the hardware section hints at checkpoints ("test on simulators first", "store expensive results immediately"), but there is no explicit multi-step workflow with validate→fix→retry feedback loops, so checkpoints are only implicit.

3 / 5

Progressive Disclosure

The structure is well-signaled with one-level-deep references (references/building.md, simulation.md, etc.), but none of the six referenced files actually exist in the bundle, so the navigation is broken and a reader following a link lands nowhere.

3 / 5

Total

13

/

20

Passed

Description

61%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.

The description is a clear, third-person statement of what Cirq is and does, but it functions as a tagline rather than trigger guidance: it lacks any "Use when..." clause that would tell Claude when to invoke the skill. Specificity and keyword coverage are reasonable, but the missing when-cap caps the score.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user asks to build, simulate, or run quantum circuits with Cirq, or mentions qubits, quantum gates, or quantum algorithms."

Replace the generic verbs with more concrete actions (e.g. "build quantum circuits from gates, simulate circuits with noise models, run on Google/IonQ hardware") to lift specificity.

Add natural synonyms users actually say (qubits, quantum gates, quantum algorithms, .py circuit scripts) to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

The description names the quantum domain and three actions ("designing, simulating, and running quantum circuits"), but these are high-level verbs rather than concrete operations like "extract text" or "fill forms," so it lands at the domain-plus-actions-but-not-comprehensive anchor rather than the several-concrete-actions anchor.

3 / 5

Completeness

It clearly answers "what" (a framework for designing/simulating/running quantum circuits) but provides no "Use when..." clause or equivalent trigger guidance, which per the rubric caps completeness at 3.

3 / 5

Trigger Term Quality

It surfaces several natural terms a user would say ("Cirq", "quantum circuits", "quantum computers", "simulators", "Google Quantum AI"), giving good keyword coverage, though synonyms like qubits/gates/algorithms and file extensions are absent.

4 / 5

Distinctiveness Conflict Risk

Naming a specific framework (Cirq) plus the quantum niche makes it largely distinct with minor overlap risk against other quantum skills, but the absence of explicit distinguishing trigger phrases keeps it just below the clear-niche anchor.

4 / 5

Total

14

/

20

Passed

Validation

81%

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

Validation13 / 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

referenced_paths_exist

Referenced path issues: 6 missing

Warning

Total

13

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.