qiskit

Builds, simulates, transpiles, and executes quantum circuits with Qiskit and IBM Quantum Runtime. Use for Qiskit 2.x circuits and operators, V2 Sampler or Estimator primitives, target-aware transpilation, local or noisy simulation, IBM QPU execution, Runtime sessions or batches, error mitigation, and Qiskit ecosystem packages.

Quality

96%

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

92%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 high-quality, current-API skill body: executable examples for every execution path, an explicit core workflow with validation checkpoints, and a clean one-level reference structure. The only weakness is minor token load from a few sections (citation instructions, join_data gotcha detail) that could live in reference files.

Suggestions

Move the detailed multi-register 'join_data' guidance (register ordering, LSB placement caveat) into references/primitives.md, keeping only a one-line pointer in SKILL.md.

Compress the citation-fetching instructions ('Citing Scientific Agent Skills' section) to a short pointer, since the DOI resolution steps rarely need to be in top-level context.

Make the 'IBM QPU Estimation' example self-contained by defining or re-acquiring 'backend' (e.g., via QiskitRuntimeService), since it currently relies on a variable only defined in the earlier sampling section.

Dimension	Reasoning	Score
Conciseness	The body is dense and prescriptive with no basic-concept padding ('Do not install qiskit-terra; it was superseded', 'qiskit.pulse was removed in Qiskit 2.0'), but a few sections could be trimmed: the citation-fetching instructions and the multi-register 'join_data' paragraph duplicate detail that belongs in references. It is not a 3 because nothing explains concepts Claude already knows, and not a 5 because of those minor over-explanations.	4 / 5
Actionability	Five complete, executable code blocks (local sampling, local estimation, IBM QPU sampling, IBM QPU estimation, batch mode) plus concrete install commands and runnable bundled scripts ('python scripts/run_local_primitives.py --shots 1024 --seed 7') cover the common cases copy-paste ready. No pseudocode or vague direction is present.	5 / 5
Workflow Clarity	The Core Workflow gives an explicit Map -> Optimize -> Apply layout -> Execute -> Analyze sequence, reinforced by a Final Checklist with concrete validation steps (verify parameter order, run locally before QPU, inspect depth and two-qubit operations). Validation checkpoints are explicit before the costly QPU submission step, matching the top anchor.	5 / 5
Progressive Disclosure	A Reference Map table routes each topic to one of 11 one-level-deep reference files, all of which exist on disk, and three bundled scripts are listed with their invocations and safety boundaries ('The Runtime inspection script selects or inspects a backend but never submits a quantum job'). Navigation is easy and content is appropriately split.	5 / 5
	Total	19 / 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 action verbs, an explicit 'Use for' clause with scenario-specific triggers, and a clearly distinct niche. No over-claims or filler language.

Dimension	Reasoning	Score
Specificity	'Builds, simulates, transpiles, and executes quantum circuits' names four concrete actions, and the sentence adds error mitigation and ecosystem-package coverage. This matches the 5 anchor (multiple specific concrete actions, comprehensive) rather than 4, since there is no notable gap in the domain's core actions.	5 / 5
Completeness	The first sentence answers 'what' with concrete verbs and the second gives an explicit 'Use for ...' clause enumerating concrete trigger scenarios, exactly the 5 anchor pattern. It is above 4 because the 'when' is explicit and specific, not merely present or generic.	5 / 5
Trigger Term Quality	Natural trigger phrases a user would actually say are comprehensively present: 'Qiskit 2.x circuits', 'V2 Sampler or Estimator primitives', 'target-aware transpilation', 'noisy simulation', 'IBM QPU execution', 'Runtime sessions or batches', 'error mitigation'. This matches the 5 anchor; no common synonym a Qiskit user would type is missing.	5 / 5
Distinctiveness Conflict Risk	The description is firmly niched to Qiskit and IBM Quantum Runtime with distinct triggers (QPU execution, Runtime sessions/batches, V2 primitives), so it is unlikely to fire for any non-Qiskit skill. Clear niche with minimal conflict risk, matching the 5 anchor.	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/qiskit/SKILL.md
Commit: 1549884

Reviewed: 1 day 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.