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/JAX/TensorFlow. For hardware-specific optimizations use qiskit (IBM) or cirq (Google); for open quantum systems use qutip.

Quality

82%

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%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.

Well-structured body with executable examples and an excellent progressive-disclosure layout pointing to real reference files. The main weakness is that the common workflows read as demonstrations rather than validated pipelines, lacking the checkpoints the rubric rewards.

Suggestions

Add explicit validation checkpoints to the workflows, e.g., assert energy convergence or gradient norm before reporting VQE results, and a simulator-only pre-flight check before submitting to hardware.

Tighten the Overview section so it does not restate automatic differentiation and device portability already covered in the description.

Replace the contrived lambda-based device-switching example with a concrete, reusable function definition that clearly shows the same circuit running on simulator vs. hardware.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with lean install/quick-start/capability sections, but the Overview restates automatic differentiation and portability already covered in the description and a few capability bullets could be tightened.	4 / 5
Actionability	Provides several executable, copy-paste-ready code blocks (circuit+optimizer, VQE, device switching) and concrete install commands, with only minor gaps such as the slightly contrived lambda device-switching example.	4 / 5
Workflow Clarity	Workflows are sequenced with numbered steps and comments, but they are illustrative demos lacking explicit validation checkpoints (e.g., no convergence check before reporting energy, no pre-submission verification for hardware runs).	3 / 5
Progressive Disclosure	Clear overview with well-signaled, one-level-deep references to seven existing reference files, summarized in capability sections and consolidated in a 'Detailed Documentation' navigation map.	5 / 5
	Total	16 / 20 Passed

Description

92%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 both capabilities and trigger conditions, with helpful disambiguation against adjacent quantum libraries. It is slightly jargon-forward in its trigger phrasing but otherwise exemplary.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — 'automatic differentiation', 'training quantum circuits via gradients', 'building hybrid quantum-classical models', 'VQE, QAOA', 'quantum neural networks', 'PyTorch/JAX/TensorFlow integration' — giving comprehensive coverage of the framework's actions.	5 / 5
Completeness	Explicitly answers both 'what' (hardware-agnostic quantum ML framework with automatic differentiation) and 'when' ('Use when training quantum circuits via gradients, building hybrid...models, or needing device portability'), matching the score-5 anchor.	5 / 5
Trigger Term Quality	Includes natural terms users would say ('quantum circuits', 'gradients', 'VQE, QAOA', 'quantum neural networks', framework names), but the phrasing is somewhat jargon-heavy and misses a few colloquial synonyms, so it sits just below the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (quantum ML) with distinct triggers and even provides disambiguation guidance ('For hardware-specific optimizations use qiskit...; for open quantum systems use qutip'), minimizing conflict risk.	5 / 5
	Total	19 / 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/pennylane/SKILL.md
Commit: 1d182e9

Reviewed: 6 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.