CtrlK
BlogDocsLog inGet started
Tessl Logo

qiskit

IBM quantum computing framework. Use when targeting IBM Quantum hardware, working with Qiskit Runtime for production workloads, or needing IBM optimization tools. Best for IBM hardware execution, quantum error mitigation, and enterprise quantum computing. For Google hardware use cirq; for gradient-based quantum ML use pennylane; for open quantum system simulations use qutip.

84

1.39x
Quality

77%

Does it follow best practices?

Impact

99%

1.39x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./scientific-skills/qiskit/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Discovery

89%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a strong skill description that excels at completeness and distinctiveness, particularly through its explicit 'Use when' clause and cross-references to alternative tools for different quantum computing needs. The main weakness is that the specific capabilities could be more concrete—listing actual operations like 'build quantum circuits', 'submit jobs to IBM backends', or 'apply error mitigation techniques' rather than broad categories. Overall, it would perform well in a multi-skill selection scenario.

Suggestions

Add more concrete action verbs describing specific operations, e.g., 'Build and transpile quantum circuits, submit jobs to IBM backends, apply error mitigation techniques, optimize circuit execution on IBM hardware.'

DimensionReasoningScore

Specificity

Names the domain (IBM quantum computing) and some actions like 'quantum error mitigation', 'IBM hardware execution', and 'optimization tools', but doesn't list multiple concrete specific actions (e.g., 'build circuits', 'run jobs', 'transpile circuits'). The actions mentioned are more like categories than concrete operations.

2 / 3

Completeness

Clearly answers both 'what' (IBM quantum computing framework for hardware execution, error mitigation, optimization) and 'when' ('Use when targeting IBM Quantum hardware, working with Qiskit Runtime for production workloads, or needing IBM optimization tools'). The explicit 'Use when' clause with specific triggers is present, plus helpful negative triggers for alternative skills.

3 / 3

Trigger Term Quality

Excellent coverage of natural trigger terms: 'IBM Quantum', 'Qiskit', 'Qiskit Runtime', 'IBM hardware', 'quantum error mitigation', 'enterprise quantum computing'. Also includes cross-references to competing tools (cirq, pennylane, qutip) which helps with disambiguation. Users asking about IBM quantum work would naturally use these terms.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive with explicit disambiguation from related quantum computing skills (cirq for Google, pennylane for gradient-based ML, qutip for open quantum systems). This cross-referencing makes it very unlikely to conflict with other quantum computing skills.

3 / 3

Total

11

/

12

Passed

Implementation

64%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a well-structured skill with strong actionability — the code examples are complete, executable, and cover the most common use cases. The progressive disclosure design is sound but undermined by missing bundle files, and the content includes some unnecessary marketing language and redundant topic listings. Adding validation/error-handling steps to the workflow would strengthen it for production use.

Suggestions

Remove marketing claims ('83x faster', '13M+ downloads', '29% fewer two-qubit gates') — these waste tokens and don't help Claude execute tasks.

Add validation checkpoints to workflows: e.g., check backend.status() before submitting, verify transpiled circuit depth, handle job errors with try/except patterns.

Provide the referenced bundle files (references/setup.md, references/circuits.md, etc.) or remove the topic lists under each section to reduce redundancy.

Trim the per-reference 'Topics covered' bullet lists — the Workflow Decision Guide already serves as the navigation index.

DimensionReasoningScore

Conciseness

The overview includes some marketing-style claims ('83x faster transpilation', '13M+ downloads', '29% fewer two-qubit gates') that are unnecessary for Claude. The topic lists under each reference section are somewhat redundant given the Workflow Decision Guide already maps needs to files. However, the code examples are lean and the structure is generally efficient.

2 / 3

Actionability

The skill provides fully executable, copy-paste ready code examples for all common patterns (simple execution, hardware execution with transpilation, VQE). Installation commands are concrete, and the three common patterns section gives complete working code blocks.

3 / 3

Workflow Clarity

The Development Workflow section provides a clear sequence (simulators → transpile → choose primitives → choose execution mode) and the Common Patterns show multi-step processes. However, there are no explicit validation checkpoints or error recovery steps — e.g., no guidance on what to do if transpilation fails, if a job errors on hardware, or how to verify circuit correctness before submission.

2 / 3

Progressive Disclosure

The skill has excellent structure with clear references to 8 separate reference files and a helpful Workflow Decision Guide for navigation. However, no bundle files were provided, meaning all those references (references/setup.md, references/circuits.md, etc.) point to non-existent files, which undermines the progressive disclosure in practice. The inline topic lists for each reference also add bulk that could be omitted if the reference files existed.

2 / 3

Total

9

/

12

Passed

Validation

90%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

10

/

11

Passed

Repository
K-Dense-AI/claude-scientific-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.