abstract-domain-explorer

Applies abstract interpretation using different abstract domains (intervals, octagons, polyhedra, sign, congruence) to statically analyze program variables and infer invariants, value ranges, and relationships. Use when analyzing program properties, inferring loop invariants, detecting potential errors, or understanding variable relationships through static analysis.

1.01x

Quality

63%

Does it follow best practices?

Impact

98%

1.01x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/abstract-domain-explorer/SKILL.md

Quality

Content

56%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 and actionable with a clear workflow, but it is verbose due to repeated domain-selection guidance and worked examples that re-teach known mechanics, and it overlaps with the bundled reference while leaving an unreferenced placeholder file.

Suggestions

Collapse the three domain-selection sections (step 1, the Domain Comparison table, and 'Choosing the Right Domain') into one to remove redundancy.

Move most worked examples into references/abstract_domains.md and keep one representative example in the body to trim tokens.

Either populate references/api_reference.md with real content and link to it, or delete the placeholder file so the bundle has no dead references.

Dimension	Reasoning	Score
Conciseness	Domain-selection guidance is covered three times ('Select Appropriate Domain(s)', the 'Domain Comparison' table, and 'Choosing the Right Domain'), and the seven worked examples re-explain abstract-interpretation mechanics (widening traces, transfer-function steps) Claude already knows, making it noticeably padded.	2 / 5
Actionability	As an instruction-only skill it gives concrete, actionable methodology (domain-selection criteria, initialization rules, transfer-function application, widening/narrowing steps, report format) with specific worked examples, though no executable tooling or automated procedure exists.	4 / 5
Workflow Clarity	A clear six-step sequence (select domain, initialize, transfer functions, widening, narrowing, extract invariants) with a convergence/fixpoint feedback loop in the widening step; minor gap is the lack of an explicit 'verify invariants are sound' checkpoint before reporting.	4 / 5
Progressive Disclosure	The body signals references/abstract_domains.md one level deep with a content summary, but the body itself inlines seven worked examples plus comparison/selection guidance that overlap the reference's 'Complete analysis examples' scope, and references/api_reference.md is an unreferenced placeholder.	3 / 5
	Total	13 / 20 Passed

Description

71%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 is strong: third-person, concrete, and explicitly pairs a clear 'what' with a 'Use when' trigger clause. Minor room to tighten the lead action and broaden trigger synonyms.

Dimension	Reasoning	Score
Specificity	Names concrete actions ('statically analyze program variables and infer invariants, value ranges, and relationships') plus five specific domains, but the lead action 'statically analyze program variables' is somewhat abstract as an umbrella rather than a fully granular action list, keeping it just below the comprehensive-coverage anchor.	4 / 5
Completeness	Explicitly answers both what ('Applies abstract interpretation ... to statically analyze program variables and infer invariants, value ranges, and relationships') and when ('Use when analyzing program properties, inferring loop invariants, detecting potential errors, or understanding variable relationships through static analysis') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural trigger phrases users would say ('analyzing program properties', 'inferring loop invariants', 'detecting potential errors', 'understanding variable relationships', 'static analysis') with good coverage, though a few common synonyms of the domain are not present.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear, specialized niche (abstract interpretation with named abstract domains) with distinct triggers and minimal overlap risk against other skills.	5 / 5
	Total	18 / 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/abstract-domain-explorer/SKILL.md
Commit: 4f38503

Reviewed: 19 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.