invariant-inference

Automatically infer loop invariants for code verification and correctness proofs. Use when analyzing loops to identify properties that hold throughout execution, generating assertions for verification, proving loop correctness, or documenting loop behavior. Supports Python, Java, C/C++, and language-agnostic analysis. Generates invariants as code assertions (assert statements). Triggers when users ask to infer invariants, find loop properties, generate loop assertions, prove loop correctness, or verify loop behavior.

1.12x

Quality

81%

Does it follow best practices?

Impact

97%

1.12x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Quality

Content

62%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 skill body is highly actionable with a clear, well-sequenced workflow including verification checkpoints, but it underuses progressive disclosure by inlining patterns already present in the reference file, which also hurts token efficiency.

Suggestions

Move the inline invariant-category patterns (Bounds/Relationship/Progress/Data Structure, lines 51–148) into references/invariant-patterns.md and replace them with a brief pointer, eliminating the duplication.

Trim or remove the "Tips for Effective Invariant Inference" section, which restates basic heuristics (bounds, accumulation, preservation) Claude already knows.

Fix non-executable assertions (e.g. "assert len(arr) remains constant", "assert arr[j+2:i+1] are shifted right and sorted") so every code example is valid, runnable code.

Dimension	Reasoning	Score
Conciseness	The body inlines full invariant-category patterns (lines 51–148) that are duplicated in references/invariant-patterns.md, and a "Tips for Effective Invariant Inference" section restates heuristics Claude already knows; noticeable padding despite a reference file existing.	2 / 5
Actionability	Mostly executable Python/Java/C code examples with assert statements covering common cases, but a few non-executable pseudocode assertions ("assert len(arr) remains constant", "assert arr[j+2:i+1] are shifted right and sorted") create minor gaps.	4 / 5
Workflow Clarity	A clear six-step sequence (Identify → Analyze → Infer → Generate → Verify → Handle Complex) with an explicit Verify step containing initialization/maintenance/termination checkpoints as a feedback loop.	5 / 5
Progressive Disclosure	The reference file is signaled (lines 53 and 497) and is one level deep, but the invariant-category content that clearly belongs in that reference is duplicated inline rather than split out.	3 / 5
	Total	14 / 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.

A strong, third-person description that concretely states capabilities and gives explicit, natural trigger phrases for when to use the skill. Redundancy between the 'Use when' and 'Triggers when' clauses slightly inflates length but does not hurt coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions—"infer loop invariants", "generating assertions for verification", "proving loop correctness", "documenting loop behavior", "Generates invariants as code assertions"—with comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what ("Automatically infer loop invariants…") and when ("Use when analyzing loops…", "Triggers when users ask to infer invariants…") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Covers natural user phrasings with synonyms—"infer invariants", "find loop properties", "generate loop assertions", "prove loop correctness", "verify loop behavior".	5 / 5
Distinctiveness Conflict Risk	Targets a clear niche (loop invariants/assertions/correctness) with distinct triggers and minimal overlap risk with other skills.	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: ArabelaTso/Skills-4-SE
Path: skills/invariant-inference/SKILL.md
Commit: 4f38503

Reviewed: 7 days 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.