jpc0/provably-correct-software
Build provably correct software using formal methods like Hoare Logic, Weakest Preconditions, and Design-by-Contract.
99
Quality
100%
Does it follow best practices?
Impact
99%
1.45xAverage score across 5 eval scenarios
Discovery
100%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 an excellent skill description that hits all the marks. It specifies concrete formal verification methods, provides clear use cases for when to apply the skill, and includes natural trigger phrases users would actually say. The specialized domain ensures minimal conflict with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete methods: 'Hoare Logic, wp calculus, Design-by-Contract' and concrete actions: 'writing new functions, implementing algorithms, modifying existing logic, performing code reviews'. | 3 / 3 |
Completeness | Clearly answers both what (formal verification methods for software correctness) and when (explicit 'Use this skill whenever...' clause plus 'Trigger when asked to...' with specific phrases). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger phrases users would say: 'prove correctness', 'verify code', 'check invariants', 'mathematical proof of code', 'ensure the algorithm is correct' - these are realistic user queries. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche - formal verification is a specialized domain unlikely to conflict with general coding skills. The specific methods (Hoare Logic, wp calculus) and trigger terms ('prove correctness', 'check invariants') create clear boundaries. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent skill that efficiently teaches formal verification methods with concrete, actionable guidance. The content is well-organized with clear workflows, executable code examples, and appropriate references for deeper exploration. It respects Claude's intelligence while providing precise, copy-paste ready implementation patterns.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, presenting formal verification concepts without unnecessary explanation. It assumes Claude understands Hoare Logic and wp calculus fundamentals, focusing only on actionable rules and conventions. | 3 / 3 |
Actionability | Provides fully executable Python code with a complete binary search example demonstrating all concepts. The worked example is copy-paste ready with embedded assertions for runtime verification. | 3 / 3 |
Workflow Clarity | The 4-step Implementation Workflow is clearly sequenced with explicit validation checkpoints. Loop verification includes specific checks (Initialization, Preservation, Termination) and mandates runtime assertion embedding for verification. | 3 / 3 |
Progressive Disclosure | Well-structured with a concise overview, clear methodology sections, and one-level-deep references to detailed materials (Hoare Logic, Weakest Precondition, Design-by-Contract). Navigation is straightforward. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
Install with Tessl CLI
npx tessl i jpc0/provably-correct-softwareReviewed
Table of Contents