CtrlK
BlogDocsLog inGet started
Tessl Logo

swift-6-agent-skill

Generate, review, or refactor Swift code using modern language features from Swift 6.0 through 6.3. Use when writing new Swift code, reviewing existing code for outdated patterns, migrating from Swift 5.x to 6.x, debugging concurrency warnings, or answering questions about current Swift idioms. Covers concurrency, typed throws, noncopyable types, observation, C interop, optimization controls, testing, and more.

70

Quality

85%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

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 clearly communicates what the skill does, when to use it, and what specific Swift topics it covers. It uses third-person voice, includes natural trigger terms across multiple user scenarios, and is distinctive enough to avoid conflicts with other coding-related skills. The explicit version range (6.0-6.3) and migration path from 5.x further strengthen its precision.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('Generate, review, or refactor Swift code') and enumerates specific capability areas like concurrency, typed throws, noncopyable types, observation, C interop, optimization controls, and testing.

3 / 3

Completeness

Clearly answers both 'what' (generate, review, refactor Swift code using modern features) and 'when' with an explicit 'Use when...' clause listing five specific trigger scenarios including writing new code, reviewing for outdated patterns, migrating versions, debugging concurrency warnings, and answering idiom questions.

3 / 3

Trigger Term Quality

Includes strong natural trigger terms users would say: 'Swift code', 'Swift 6.0', 'Swift 5.x to 6.x', 'concurrency warnings', 'refactor', 'review', 'Swift idioms', 'migrating'. Covers version numbers and common task descriptions users would naturally use.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive due to the specific focus on Swift 6.0-6.3 modern features, version migration, and enumerated Swift-specific topics like typed throws, noncopyable types, and C interop. Unlikely to conflict with generic coding skills or other language-specific skills.

3 / 3

Total

12

/

12

Passed

Implementation

70%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a well-organized, comprehensive Swift modernization skill with excellent workflow structure, clear progressive disclosure to reference files, and thorough coverage of Swift 6.0–6.3 features. Its main weakness is the complete absence of executable code examples — for a skill focused on code generation and review, at least a few concrete before/after Swift code snippets would significantly improve actionability. The content is moderately concise given its broad scope but could trim the philosophy section and some explanatory framing.

Suggestions

Add 3-5 concrete, executable Swift code examples for the most common patterns (e.g., Mutex usage, typed throws, @Observable with Observations, InlineArray declaration, @c attribute) — even brief inline snippets would significantly boost actionability.

Trim or remove the Philosophy section, which explains meta-decisions about the skill rather than instructing Claude on Swift patterns — these meta-notes could move to a comment or separate file.

Add at least one before/after code example directly in the Quick Reference table or Core Guidelines for the highest-impact migrations (e.g., NSLock → Mutex, @_cdecl → @c) rather than deferring all code to MIGRATION.md.

DimensionReasoningScore

Conciseness

The skill is comprehensive and mostly efficient, but the sheer volume of content (review checklist, quick reference table, core guidelines, workflow decision tree, version coverage, philosophy section) is substantial. The philosophy section and some guideline explanations add tokens that don't directly instruct action. However, given the breadth of Swift 6.0–6.3 features covered, most content earns its place. The philosophy section and some framing text could be trimmed.

2 / 3

Actionability

The skill provides highly specific guidance with SE proposal numbers, concrete attribute names, and clear old→new mappings, but it lacks executable code examples entirely. For a code generation skill, the absence of any copy-paste-ready Swift code snippets (e.g., showing Mutex usage, typed throws syntax, InlineArray declaration, @c attribute usage) is a notable gap. The guidance is specific but descriptive rather than demonstrative.

2 / 3

Workflow Clarity

The workflow decision tree clearly sequences five distinct use cases (generate, review, refactor, debug, answer questions) with ordered steps and cross-references. The review checklist provides explicit validation checkpoints organized by category. The migration workflow has a clear sequence with version-specific routing. The debug section maps specific error messages to specific solutions, which serves as an effective feedback loop.

3 / 3

Progressive Disclosure

The skill is well-structured as an overview document with clear one-level-deep references to version-specific files (SWIFT_6_0.md through SWIFT_6_3.md, MIGRATION.md). Each reference file is described with its contents. The main document provides enough actionable content to be useful standalone while pointing to detailed references for deeper exploration. Navigation is clear and well-signaled throughout.

3 / 3

Total

10

/

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
pchelnikov/Swift-6-Agent-Skill
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.