quantum-qiskit

Reference qiskit 2.x patterns for variational quantum machine learning. Covers data-encoding feature maps, variational quantum classifier (VQC) training, variational quantum eigensolver (VQE) for chemistry, matrix-product-state circuits, and noise model integration. Use when writing Python code that imports `qiskit`, `qiskit_aer`, `qiskit_algorithms`, `qiskit_machine_learning`, or `qiskit_nature`.

Quality

89%

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

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 strong, actionable code reference with executable functions and a useful error-fix table, lightly held back by some trimmable prose and a monolithic single-file structure that inlines material a progressive-disclosure layout would externalize into reference files.

Suggestions

Move the longer implementation sections (MPS classifier, VQE loop, noisy-sampler construction) into reference files under references/ and keep SKILL.md as an overview with one-level-deep links, lifting progressive_disclosure above 3.

Tighten the explanatory prose in sections 5 and 6 (the MPS-equivalence paragraph and the running-mean rationale) to drop commentary Claude can infer, pushing conciseness toward 5.

Add a short top-of-file workflow checklist (encode → build ansatz → train → validate convergence → report metrics) so the reference reads as an explicit sequenced workflow with checkpoints, supporting a workflow_clarity of 5.

Dimension	Reasoning	Score
Conciseness	The body is mostly purposeful code plus targeted API/migration notes and does not re-explain basics Claude already knows, but a few prose passages (the MPS↔circuit equivalence paragraph, the running-mean convergence rationale) could be trimmed, keeping it at 4 rather than the fully lean 5.	4 / 5
Actionability	Provides complete, copy-paste-ready functions (build_angle_encoding, train_vqc, run_vqe, build_h2_hamiltonian, build_noisy_sampler, mps_class_logits) plus a wrong/why/correct error table covering the common cases — fully executable, not pseudocode.	5 / 5
Workflow Clarity	Sections are sequenced (imports → encoding → ansatz → training → VQE → MPS → noise → compat → errors) with validation checkpoints present (cumulative_shots_to_threshold convergence check, the training_failed marker guidance against predicting on an unfitted model), but it is a reference catalogue rather than a single linear workflow with full feedback-loop checklists, so it sits at 4 rather than 5.	4 / 5
Progressive Disclosure	The 470-line file is well-organized (section overview plus 10 numbered headers), but it is a monolithic single file with substantial implementation code (MPS, VQE, noise sampler) fully inlined and no bundle files or one-level-deep references to split detail into, matching the anchor where content that could be separate is inline.	3 / 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.

An exemplary description: third-person voice, concrete capability list, and an explicit "Use when" clause keyed to the exact package imports that signal the skill. It answers what and when with minimal conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capability areas — "data-encoding feature maps", "variational quantum classifier (VQC) training", "variational quantum eigensolver (VQE) for chemistry", "matrix-product-state circuits", and "noise model integration" — giving comprehensive, non-generic coverage rather than the 1-2 actions of a 3.	5 / 5
Completeness	Explicitly answers both what ("Reference qiskit 2.x patterns... Covers...") and when ("Use when writing Python code that imports...") with concrete trigger phrases, matching the anchor for a clear both-what-and-when description.	5 / 5
Trigger Term Quality	The "Use when writing Python code that imports `qiskit`, `qiskit_aer`, `qiskit_algorithms`, `qiskit_machine_learning`, or `qiskit_nature`" clause gives comprehensive, natural trigger coverage via the exact import names a developer encounters, plus VQC/VQE/feature-map terms; it is not below 4 because no meaningful natural variants are missing for this domain.	5 / 5
Distinctiveness Conflict Risk	It carves a clear niche (qiskit 2.x variational QML) with distinct, package-specific triggers, so conflict with unrelated skills is minimal; it is well above the 4 anchor's "minor overlap risk with closely related 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: aiming-lab/AutoResearchClaw
Path: researchclaw/skills/builtin/domain/quantum-qiskit/SKILL.md
Commit: be4ba47

Reviewed: 5 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.