pennylane

Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building hybrid quantum-classical models, or needing device portability across IBM/Google/Rigetti/IonQ. Best for variational algorithms (VQE, QAOA), quantum neural networks, and integration with PyTorch or JAX. For hardware-specific optimizations use qiskit (IBM) or cirq (Google); for open quantum systems use qutip.

Quality

84%

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

68%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 body with strong progressive disclosure pointing to verified reference files, but it loses conciseness to redundant overview prose and version-pin bulk, and its workflows lack explicit validation checkpoints for hardware-bound and long-running operations.

Suggestions

Trim the Overview paragraph and best-practice explanations of concepts Claude already knows (e.g. 'enables training quantum computers like neural networks') to reduce padding.

Add explicit validation/checkpoint steps to hardware execution and optimization workflows (e.g. verify convergence, check device connectivity before submitting) to support error recovery.

Move pinned version strings into a separate compatibility or versioning note rather than weaving them into the installation narrative, since time-sensitive details penalize conciseness outside a deprecated/old-patterns section.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable code, but several padded sections — e.g. 'PennyLane is a quantum computing library that enables training quantum computers like neural networks' restates concepts Claude already knows, and pinned version strings ('PennyLane 0.45.0 requires Python 3.11') add time-sensitive bulk without an old/deprecated framing.	3 / 5
Actionability	Multiple copy-paste ready examples covering common cases (circuit construction, variational classifier, VQE, device switching) with specific commands and concrete APIs like `qml.specs()` and `page.extract_tables()`-style hints.	5 / 5
Workflow Clarity	Workflows are sequenced as numbered comments inside code, but operations that touch quantum hardware or run long optimization loops have no explicit validation checkpoints or error-recovery feedback loops, capping clarity per the destructive/batch guidance.	3 / 5
Progressive Disclosure	Clear overview with one-level-deep references — each capability section signals a real file in references/ (verified present), and the Detailed Documentation section maps topics to specific files, giving easy navigation.	5 / 5
	Total	16 / 20 Passed

Description

100%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, specific description that clearly states what the skill does and when to use it, with concrete trigger terms and explicit boundaries against adjacent tools. Minor reliance on version numbers does not detract from the trigger quality.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('training quantum circuits via gradients', 'building hybrid quantum-classical models', 'device portability across IBM/Google/Rigetti/IonQ') plus named algorithms (VQE, QAOA) and framework integrations, giving comprehensive coverage of the domain.	5 / 5
Completeness	Explicitly answers both 'what' (hardware-agnostic quantum ML framework with automatic differentiation) and 'when' via a clear 'Use when' clause with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Comprehensive natural terms users would say — 'quantum circuits', 'hybrid quantum-classical models', 'VQE', 'QAOA', 'quantum neural networks', 'PyTorch', 'JAX' — plus provider names and explicit alternatives (qiskit, cirq, qutip) as synonyms.	5 / 5
Distinctiveness Conflict Risk	Clear niche (quantum ML) with distinct triggers and explicit boundary guidance steering away from qiskit/cirq/qutip, minimizing conflict risk with adjacent skills.	5 / 5
	Total	20 / 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/pennylane/SKILL.md
Commit: 9e8b0cb

Reviewed: 2 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.