CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

71%

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 ./skills/qiskit/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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 overview with genuinely executable quick-start and pattern code and a clear development workflow, but it is held back by duplication (description restated, decision guide mirroring the capability sections, Pattern 1 duplicating the quick start) and by referencing eight reference files that do not exist in the bundle.

Suggestions

Ship the eight referenced files (references/setup.md through references/algorithms.md) or remove the pointers — every navigation path in the body currently dangles.

Deduplicate: drop the Overview's verbatim restatement of the description, fold the Workflow Decision Guide into the Core Capabilities section headings, and delete Pattern 1 (identical to the First Circuit example).

Make Patterns 2 and 3 self-contained by defining backend, qc, ansatz, hamiltonian, and initial_params, or explicitly labeling them as fragments requiring setup from the referenced guides.

DimensionReasoningScore

Conciseness

Mostly efficient but includes clear tightening opportunities: the Overview repeats the frontmatter description verbatim, the Workflow Decision Guide largely duplicates the per-topic pointers already given in Core Capabilities, Pattern 1 re-runs the First Circuit example almost line-for-line, and "Key Features" carries marketing claims ("83x faster transpilation", "29% fewer two-qubit gates"). Not a 2 because nothing explains concepts Claude already lacks — it is routing and code, just duplicated.

3 / 5

Actionability

Mostly executable: install commands, a complete runnable Bell-state circuit, and concrete patterns for local execution and hardware execution. Not a 5: Pattern 2 uses an undefined `qc`, and Pattern 3 depends on undefined `ansatz`, `hamiltonian`, `backend`, and `initial_params`, so those snippets are not copy-paste ready.

4 / 5

Workflow Clarity

Clear sequencing: a numbered Development Workflow (simulate → transpile → choose primitive → choose mode) with inline code, a decision guide for routing tasks, and checkpoints like "Check backend status before submitting" and "Test with noisy simulators before hardware". Not a 5: no explicit validation/error-recovery loop (e.g., what to do when a job fails or convergence stalls).

4 / 5

Progressive Disclosure

Structure and signaling are good — eight clearly labeled one-level-deep references plus a decision guide — but all eight referenced files (references/setup.md, circuits.md, primitives.md, transpilation.md, visualization.md, backends.md, patterns.md, algorithms.md) are absent from the bundle, so the navigation paths are dangling and the per-file "Topics covered" bullet lists exist only as inline previews. Not a 4 because broken reference targets are more than a minor organization gap; not a 2 because the body itself is well organized and the references are clearly signaled.

3 / 5

Total

14

/

20

Passed

Description

70%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 solid, mostly specific description with good natural trigger terms and a distinct niche, but it lacks any explicit "when to use" guidance and opens with unverifiable marketing claims ("world's most popular", "13M+ downloads") that add tokens without aiding discovery.

Suggestions

Add an explicit trigger clause, e.g. "Use when working with Qiskit, quantum circuits, IBM Quantum backends, or quantum algorithms like VQE/QAOA."

Drop the marketing fluff ("world's most popular", "13M+ downloads", "100+ qubit systems") in favor of concrete capability verbs like transpile, visualize, and run variational algorithms.

Include synonyms and specific terms users actually type ("transpile", "quantum program", "Bell state", "quantum chemistry") to broaden trigger coverage.

DimensionReasoningScore

Specificity

Lists several concrete actions ("Build quantum circuits, optimize for hardware, execute on simulators or real quantum computers, and analyze results") plus named providers. Not a 5: the marketing opener ("world's most popular open-source quantum computing framework with 13M+ downloads") is fluff, and coverage has gaps (no mention of visualization, transpilation, or algorithms).

4 / 5

Completeness

Has a clear "what" (build, optimize, execute, analyze) but no "Use when…" clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. The "when" is only weakly implied by naming the domain.

3 / 5

Trigger Term Quality

Good natural keywords users would say: "quantum circuits", "simulators", "IBM Quantum", "IonQ", "Amazon Braket". Not a 5: missing common variations like "transpile", "quantum program", "VQE", or the framework name itself in the description text.

4 / 5

Distinctiveness Conflict Risk

Quantum computing is a clearly distinct niche with distinctive triggers ("quantum circuits", "IBM Quantum", "IonQ", "Amazon Braket"); minimal overlap risk with any other skill. Confirmed against the 4 anchor: this is more than "mostly distinct" — the triggers are essentially unique to this domain.

5 / 5

Total

16

/

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.

Validation — 13 / 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

Path

skills/qiskit/SKILL.md

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.