CtrlK
BlogDocsLog inGet started
Tessl Logo

qiskit

Qiskit is the world's most popular open-source quantum computing framework with 13M+ downloads. Build quantum circuits, optimize for hardware, execute on simulators or real quantum computers, and analyze results. Supports IBM Quantum (100+ qubit systems), IonQ, Amazon Braket, and other providers.

57

Quality

68%

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-claude/skills/qiskit/SKILL.md

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

SKILL.md
Quality
Evals
Security

Quality

Content

61%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 well-structured with executable examples and good reference navigation, but it carries marketing fluff, repeats the description verbatim, and lacks validation checkpoints for batch hardware execution; the referenced reference files are also absent.

Suggestions

Remove the marketing bullets ("83x faster", "29% fewer gates", "13M+ downloads") and the verbatim description repeat from the Overview to respect the token budget.

Add an explicit validation checkpoint before hardware submission (e.g. verify the transpiled circuit and check backend status before proceeding) to lift the workflow-clarity cap.

Provide the referenced files under references/ (setup.md, circuits.md, primitives.md, transpilation.md, visualization.md, backends.md, patterns.md, algorithms.md) so the signaled navigation resolves.

DimensionReasoningScore

Conciseness

Mostly efficient code/topic lists, but padded with marketing over-claims ("83x faster transpilation", "29% fewer two-qubit gates", "13M+ downloads") and the Overview repeats the frontmatter description verbatim, so it could be tightened.

3 / 5

Actionability

Provides copy-paste-ready executable code for the common cases (Bell-state circuit, hardware execution with transpile) and concrete install commands; minor gaps like the VQE pattern referencing undefined ansatz/hamiltonian/backend keep it just below 5.

4 / 5

Workflow Clarity

Sequences are present (install → build → transpile → execute → analyze) with a decision guide, but hardware job submission is a batch operation with no explicit validate-then-proceed checkpoint, so workflow clarity is capped at 3 per the rubric.

3 / 5

Progressive Disclosure

Clear overview with eight well-signaled one-level-deep references plus a Workflow Decision Guide, but the referenced files do not exist (no references/ directory), so navigation leads to dead ends — a minor organization gap keeping it below 5.

4 / 5

Total

14

/

20

Passed

Description

75%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 concretely names the domain and several actions with strong distinctiveness, but it leads with marketing over-claims ("world's most popular", "13M+ downloads") and omits any explicit "Use when..." trigger guidance, capping completeness at 3.

Suggestions

Drop the marketing lead ("world's most popular... 13M+ downloads") and replace it with an explicit 'Use when...' trigger clause naming natural user phrases (e.g. 'Use when building quantum circuits, running on simulators or IBM Quantum hardware, or implementing VQE/QAOA').

Add common synonyms and tool names users say ('quantum program', 'qiskit circuit', 'IBM Quantum runtime') to broaden trigger coverage.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "Build quantum circuits, optimize for hardware, execute on simulators or real quantum computers, and analyze results" — plus named providers (IBM Quantum, IonQ, Amazon Braket), matching the comprehensive-coverage anchor.

5 / 5

Completeness

The "what" is clear (build, optimize, execute, analyze), but there is no "Use when..." clause or equivalent explicit trigger guidance, so completeness is capped at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

Good domain keywords a user would say ("quantum circuits", "quantum computing", "simulators", "IBM Quantum"), but it lacks synonyms/variations and any "Use when..." phrasing, leaving a few natural terms missing.

4 / 5

Distinctiveness Conflict Risk

Names a specific framework (Qiskit) in a highly distinct niche (quantum computing) with provider-specific triggers, giving minimal conflict risk with other skills.

5 / 5

Total

17

/

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: 20 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.