CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

swift-language

Apply modern Swift language patterns to non-SwiftUI, non-concurrency code, including expressions, typed throws, generics, protocols, result builders, property wrappers, opaque and existential types, regexes, and collections. Route concurrency, Codable, formatting, and API naming to their specialist skills.

Quality

79%

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/swift-language/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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, token-efficient patterns skill with executable examples and an exemplary progressive-disclosure setup: a concise overview body pointing to three real, clearly-labeled, one-level-deep reference files. The main improvements are closing the actionability gaps in the regex/collections section and adding an explicit behavior-preservation validation step.

Suggestions

Add one small executable example to the Modern Collections & Regex section (e.g., a regex literal with a typed capture match), since it is currently the only pattern section with no code.

Add an explicit verification step after modernization (e.g., 'confirm the module still compiles and evaluation order is unchanged before finishing') to complete the workflow's feedback loop.

Drop the redundant 'Contents' table of contents or the restated opening description line to trim the remaining padding.

DimensionReasoningScore

Conciseness

The body is lean — terse section guidance plus compact code examples — with only minor trimmable elements: the opening line re-states the frontmatter description, and phrases like "Preserves underlying static type information, enables compiler optimizations..." explain rationale Claude largely already knows. This matches the 4 anchor (efficient with minor instances that could be trimmed) rather than 5, where every token earns its place.

4 / 5

Actionability

Most guidance is executable and complete (the typed-throws, switch-expression, and Clamped property-wrapper examples are copy-paste ready), but there are minor gaps: the regex/collections section gives no code example ("Use regex literals #/pattern/# with typed capture groups and RegexBuilder") and one example uses a `{ ... }` placeholder body. Not fully at the 5 anchor's 'specific examples cover the common cases'.

4 / 5

Workflow Clarity

As a single-purpose apply-patterns skill the action is unambiguous, and the Review Checklist plus Common Mistakes (e.g., "ensure parameter evaluation order remains strictly preserved") serve as checkpoints. It stays at 4 rather than 5 because there is no explicit validation step confirming behavior is preserved after modernization (e.g., a compile/behavior verification loop).

4 / 5

Progressive Disclosure

The body is a concise overview with well-labeled, one-level-deep references — all three bundle files (swift-6-4.md, swift-patterns-extended.md, swift-attributes-interop.md) exist, are each described with their purpose in the References section, and cross-link only laterally within the same level. This matches the 5 anchor: clear overview, well-signaled references, easy navigation.

5 / 5

Total

17

/

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 specific, well-scoped description with excellent distinctiveness thanks to explicit routing to sibling skills. Its main weakness is the absence of a positive 'Use when' trigger clause, leaving the activation conditions implicit and capping completeness.

Suggestions

Add an explicit trigger clause such as: 'Use when writing or modernizing non-SwiftUI Swift code, or when the user mentions Swift syntax, protocols, generics, regexes, or migrating to Swift 6+.'

Include a natural-language activation phrase users would say (e.g., 'modernize this Swift code', 'use switch expressions') to broaden trigger-term coverage.

Keep the routing sentence — it is the description's strongest distinctiveness signal — but pair it with the positive trigger so both 'when to use' and 'when not to use' are explicit.

DimensionReasoningScore

Specificity

The description enumerates many concrete capability areas — "typed throws, generics, protocols, result builders, property wrappers, opaque and existential types, regexes, and collections" — giving comprehensive topical coverage. It falls short of the 5 anchor because it relies on a single verb ("Apply") with a catalog of topics rather than multiple distinct concrete actions.

4 / 5

Completeness

The "what" is clear and specific ("Apply modern Swift language patterns to non-SwiftUI, non-concurrency code..."), but there is no positive "Use when..." clause or equivalent explicit trigger guidance — the routing sentence ("Route concurrency, Codable, formatting, and API naming to their specialist skills") is exclusion guidance, not when-to-use triggers. Per the rubric guidelines, a missing 'Use when' clause caps completeness at 3.

3 / 5

Trigger Term Quality

Strong natural keywords a Swift user would actually say: "Swift", "protocols", "generics", "regexes", "typed throws", "property wrappers", "collections". A few natural trigger phrasings are missing (e.g., "modernize Swift code", "migrate to Swift 6", "refactor"), keeping it below the comprehensive-synonym coverage of the 5 anchor.

4 / 5

Distinctiveness Conflict Risk

The description explicitly scopes itself ("non-SwiftUI, non-concurrency code") and routes overlapping domains away ("Route concurrency, Codable, formatting, and API naming to their specialist skills"), establishing a clear niche with minimal conflict risk — a direct match to the 5 anchor.

5 / 5

Total

16

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

thienqo/ios-skills

Path

skills/swift-language/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.