swift-concurrency-expert

Swift concurrency review/fix: compiler errors, Sendable, isolation, remediation.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/swift-concurrency-expert/SKILL.md

Quality

Content

72%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 lean, well-structured body with concrete Swift fix recipes and excellent progressive disclosure to real reference files. Its main weakness is the missing verification checkpoint in the workflow, and a minor gap is the absence of a full copy-paste code example.

Suggestions

Add a verification step to the workflow, e.g. "### 3. Verify the fix — recompile to confirm the diagnostic is resolved and run tests to confirm behavior is preserved", to add the validation checkpoint that currently caps workflow_clarity at 3.

Include one complete before/after Swift code example (e.g., a `@MainActor`-annotated type resolving a Sendable sending error) to make the guidance fully copy-paste ready and lift actionability toward 5.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence (no explaining what Swift/Sendable/concurrency is), matching anchor 4's "efficient; minor instances that could be trimmed." It is not a 5 because the attribution line "copied from @Dimillian's ... (2025-12-31)" and the version-specific "Swift 6.2+" date are non-essential/time-sensitive tokens that do not directly serve the task.	4 / 5
Actionability	Concrete recipes with real inline Swift syntax (e.g., `extension Foo: @MainActor SomeProtocol`, "move expensive work into a `@concurrent` async function on a `nonisolated` type") give mostly executable guidance (anchor 4). It is not a 5 because there is no complete copy-paste-ready before/after code block covering a common case.	4 / 5
Workflow Clarity	A clear two-step sequence (Triage → Apply smallest safe fix) is present, but there is no validation/verification checkpoint — no step to recompile and confirm the diagnostic is resolved or run tests to confirm behavior is preserved (anchor 3: sequence present but checkpoints missing). It is above 2 because the steps themselves are well-defined, not "poorly defined".	3 / 5
Progressive Disclosure	A concise overview points to two clearly signaled, one-level-deep references ("See `references/swift-6-2-concurrency.md` for ...", "See `references/swiftui-concurrency-tour-wwdc.md` for ..."), and both files exist in the bundle — matching anchor 5's clear overview with well-signaled one-level-deep references and easy navigation.	5 / 5
	Total	16 / 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 tightly scoped, distinctive description with strong natural trigger terms, but it omits any explicit "Use when..." guidance, which caps completeness at 3. Adding a trigger clause and swapping jargon ("remediation") for user phrasing would raise the two weakest dimensions.

Suggestions

Add an explicit "Use when..." trigger clause, e.g. "Use when fixing Swift 6 concurrency compiler errors involving Sendable, actor isolation, or data-race safety", to lift completeness above 3.

Replace the jargon term "remediation" with natural phrasing like "fixes", and add synonyms users actually say ("actor isolation", "MainActor", "async/await", "data race") to improve trigger-term quality toward 5.

Dimension	Reasoning	Score
Specificity	The phrase "Swift concurrency review/fix: compiler errors, Sendable, isolation, remediation" names the domain and lists several concrete scope areas, matching anchor 4's "lists several specific actions; minor gaps." It is not a 5 because some listed items (compiler errors, isolation) are topics/categories rather than distinct concrete actions, and the only true verbs are "review/fix".	4 / 5
Completeness	The description gives a clear "what" (Swift concurrency review/fix and its scope) but has no "Use when..." clause or equivalent explicit trigger guidance, so per the rubric cap it cannot exceed 3 (anchor 3: clear what, when missing or only weakly implied).	3 / 5
Trigger Term Quality	"Swift concurrency", "compiler errors", and "Sendable" are natural terms users say, giving good keyword coverage (anchor 4). It is not a 5 because "remediation" is jargon rather than user phrasing, and common synonyms like "actor isolation", "MainActor", "async/await", or "data race" are missing.	4 / 5
Distinctiveness Conflict Risk	"Swift concurrency" combined with distinctive triggers like "Sendable" and "isolation" carves a clear niche with minimal conflict risk against other skills (anchor 5). The broad term "compiler errors" is scoped tightly by the Swift-concurrency framing, so it does not pull this down to 4.	5 / 5
	Total	16 / 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: steipete/agent-scripts
Path: skills/swift-concurrency-expert/SKILL.md
Commit: dc4f583

Reviewed: 2 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.