CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

swift-concurrency-expert

Review and fix Swift concurrency issues such as actor isolation and Sendable violations.

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-concurrency-expert/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%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 skill body: an iterative triage-fix-verify workflow with explicit validation and a feedback loop, concrete scenario-to-fix mappings, and clean one-level-deep references. The only trims available are the redundant Task.detached alternative and placeholder symbols in the examples.

Suggestions

Drop the Task.detached variant in the background-work example and keep only the @concurrent form (the recommended Swift 6.2 pattern), and trim comments that restate the code.

Make the code examples fully self-contained by defining the placeholder symbols (SomeProtocol, heavyTransform) or noting them explicitly, and add a concrete verify command (e.g., swift build / swift test, or xcodebuild) to step 3.

DimensionReasoningScore

Conciseness

The body is efficient — a triage/fix/verify workflow, a scenario-mapped fix list, and three tight before/after examples with no explanations of concepts Claude already knows. It is not a 5 because the background-work example shows both a Task.detached variant and a @concurrent variant where the latter alone suffices, and a few comments restate what the code already shows (e.g., "// runs on main thread").

4 / 5

Actionability

Concrete, mostly executable guidance: exact syntax for each fix (@MainActor, extension Foo: @MainActor SomeProtocol, @concurrent) and three complete before/after Swift examples covering the main cases. Not a 5 because the examples rely on undefined placeholder symbols (SomeProtocol, heavyTransform) and the verify step gives no concrete build/test commands.

4 / 5

Workflow Clarity

Clear three-step sequence (triage, apply smallest safe fix, verify) with explicit validation steps ("Rebuild and confirm all concurrency diagnostics are resolved", "Run the test suite") and an explicit feedback loop ("treat each one as a fresh triage (return to step 1) and resolve iteratively"). This matches the top anchor including error-recovery loops.

5 / 5

Progressive Disclosure

The body is an overview (workflow plus a few key examples) with detailed material split into three reference files, each signaled with a distinct use condition ("for Swift 6.2 changes", "when the project is opted into approachable concurrency mode", "for SwiftUI-specific concurrency guidance"). All three referenced files exist, contain the promised content, and are one level deep with no nested references — matching the top anchor.

5 / 5

Total

18

/

20

Passed

Description

65%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 clear, specific, well-targeted description that names concrete issue types in a distinct niche, but it is missing any 'use when' trigger guidance and lists only two actions, limiting discoverability and completeness.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to fix Swift compiler diagnostics or mentions data races, actor isolation, @MainActor, Sendable, or async migration" — this would resolve the missing 'when' that caps completeness.

Expand the action coverage beyond 'review and fix' to reflect what the skill actually does (e.g., apply @MainActor isolation, migrate code to @concurrent/actors, resolve strict-concurrency diagnostics) to raise specificity.

Include the natural synonyms users say ("data race", "Swift 6", "async/await", "@MainActor") to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

"Review and fix" are two concrete actions on a clearly named domain ("Swift concurrency issues such as actor isolation and Sendable violations"), which matches the anchor for naming the domain with 1-2 concrete actions. It is not the level above because only two actions are listed, not the 'several specific actions' of a comprehensive description (async migration, @MainActor guidance, etc. are not mentioned).

3 / 5

Completeness

The 'what' is clearly stated ("Review and fix Swift concurrency issues such as actor isolation and Sendable violations") but the 'when' is entirely missing — there is no 'Use when...' clause or equivalent trigger guidance, which the guidelines cap at this level. Not score 2 because the 'what' is specific, not vague.

3 / 5

Trigger Term Quality

"Swift concurrency", "actor isolation", and "Sendable violations" are natural phrases a user would say when needing this skill. It falls short of the top anchor because common variations like "data race", "@MainActor", "async/await", and "Swift 6" are absent.

4 / 5

Distinctiveness Conflict Risk

"Swift concurrency issues such as actor isolation and Sendable violations" carves out a clear niche with distinct technical triggers that would not fire for unrelated skills. It is more specific than the anchor-4 example of overlapping related domains ("PDF and Word document files"), so the top anchor fits best.

5 / 5

Total

15

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

skills/swift-concurrency-expert/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.