CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

swift-concurrency

API reference: Swift Concurrency. async/await, Task, TaskGroup, actors, AsyncSequence, AsyncStream, continuations.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/swift-concurrency/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 a well-organized, token-efficient index with a concrete fallback lookup workflow — exactly the right shape for a reference skill. The weaknesses are small: a couple of trimmable redundancies, no terminal fallback if the doc mirror fails, and the seven referenced files are not present in the bundle as provided, leaving the skill's core navigation unverifiable.

Suggestions

Ensure the seven referenced .md files ship in the skill bundle — they are linked in the index table but not present alongside SKILL.md, so the skill's primary navigation is currently broken.

Drop the redundant intro line "Structured concurrency, actors, and async sequences in Swift." and the "This is faster and uses less context" justification to tighten the body to anchor-5 leanness.

Make step 1 concrete with a search command (e.g. a grep over the skill directory) and add a terminal fallback for when the sosumi.ai mirror also lacks the page.

DimensionReasoningScore

Conciseness

The body is a lean ~20-line index plus a three-step lookup procedure with essentially no padding; the only trimmable spots are the intro line "Structured concurrency, actors, and async sequences in Swift." duplicating the frontmatter description and "This is faster and uses less context than fetching new docs from the internet", which Claude could infer — minor over-explanation, matching anchor 4 rather than the every-token-earns-its-place anchor 5.

4 / 5

Actionability

The URL-mapping example ("/documentation/swift/task maps to https://sosumi.ai/documentation/swift/task") is copy-paste ready, but steps 1–2 ("Search this skill's local .md files first", "check the other installed Apple skills... then grep their local files") give direction without a concrete search command — mostly executable guidance with minor gaps, matching anchor 4 rather than the fully-executable anchor 5.

4 / 5

Workflow Clarity

The doc-lookup workflow is a clearly sequenced three-step fallback with explicit conditionals ("If the topic is not here", "If no installed skill has the page"), but it has no error-recovery step if the sosumi.ai mirror lacks the page and does not specify how to search local files — clear sequence with most checkpoints present, matching anchor 4 rather than the feedback-loop-complete anchor 5. No destructive or batch operations, so the cap of 3 does not apply.

4 / 5

Progressive Disclosure

The "Downloaded Reference Files" table signals each one-level-deep reference with a content description — structurally the anchor-5 pattern — but checked against the actual bundle, none of the seven referenced .md files (concurrency-overview.md, task.md, etc.) exist alongside SKILL.md and there is no references/ directory, so the navigation cannot be verified end-to-end. Good structure with a real organization gap, matching anchor 4 rather than anchor 5's easy, working navigation.

4 / 5

Total

16

/

20

Passed

Description

66%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 concise and concrete with strong natural trigger terms for the Swift concurrency domain, but it lacks any explicit 'Use when...' guidance, which caps its completeness and weakens its routing function. Its distinctiveness within an Apple-skills fleet is good but not airtight.

Suggestions

Add an explicit trigger clause, e.g. "Use when answering questions about Swift concurrency or writing async/await, actor, or Task-based Swift code."

Include missing common natural terms such as "Sendable", "async let", and "structured concurrency" to broaden trigger coverage.

Differentiate from sibling Apple skills by scoping the description explicitly to concurrency (it does this implicitly; making the boundary explicit would reduce overlap risk with a general Swift reference skill).

DimensionReasoningScore

Specificity

"API reference: Swift Concurrency" names the skill type and the list "async/await, Task, TaskGroup, actors, AsyncSequence, AsyncStream, continuations" gives seven specific concrete topics with only minor gaps (Sendable, async let) — anchor 4's specificity level, though phrased as topics rather than actions. Not anchor 3, which conveys less concrete information, and not anchor 5, which requires explicit stated actions.

4 / 5

Completeness

"API reference: Swift Concurrency" gives a clear 'what', but there is no 'Use when...' clause or equivalent explicit trigger guidance — the 'when' is only weakly implied by the topic list, so per the judging guideline completeness is capped at 3. Not anchor 4, which requires an explicit 'when'.

3 / 5

Trigger Term Quality

Terms like "async/await", "Task", "TaskGroup", "actors", and "continuations" are exactly what a Swift developer would say, but common variations such as "Sendable", "async let", and "structured concurrency" are missing — good coverage with a few natural terms absent, matching anchor 4 rather than the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

Concurrency-specific terms ("TaskGroup", "AsyncSequence", "AsyncStream", "continuations") carve a clear niche that would not trigger for general Swift work, but "Task" and "actors" carry minor overlap risk with closely related sibling Apple/Swift skills — mostly distinct with minor overlap, matching anchor 4 rather than the minimal-conflict anchor 5.

4 / 5

Total

15

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

relative_links

Relative link issues: 7 missing

Warning

Total

14

/

16

Passed

Repository

Prisma-Labs-Dev/apple-skills

Path

skills/swift-concurrency/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.