CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

axiom-swift

Use when the question is about Swift or its toolchain rather than a framework — modern idioms, noncopyable types, drag and drop, debug deep links, tvOS targets.

Quality

70%

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 ./axiom-codex/skills/axiom-swift/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 router skill with clear navigation, explicit conflict-resolution rules, and genuinely useful anti-rationalization content. Its main costs are redundant restatements of the same routing map and references to files and external skills that cannot be verified in the bundle.

Suggestions

Collapse the dot decision graph and the numbered Decision Tree into one routing representation — they duplicate each other almost exactly and cost significant tokens.

Trim the Example Invocations section or merge it into the Quick Reference table, since both map the same user phrasings to the same files.

Normalize the external routing entries (items 6-8) to a consistent, resolvable format and ensure the referenced `skills/*.md` files ship alongside SKILL.md.

DimensionReasoningScore

Conciseness

The body avoids explaining concepts Claude already knows, but the same routing information is restated four times — Quick Reference table, dot decision graph, numbered Decision Tree, and Example Invocations — and the dot graph and numbered list are near-duplicates. Not 2 because each section is individually tight and purposeful rather than padded.

3 / 5

Actionability

Routing guidance is concrete and specific ("Read: `skills/swift-modern.md`", "Use swift for Transferable conformance... -> `skills/transferable-ref.md`"), with per-file content previews that make next steps executable. Not 5 because external routing entries use inconsistent, unresolvable formats ("/skill axiom-concurrency", "axiom-performance (skills/swift-performance.md)") and none of the referenced paths exist in the bundle.

4 / 5

Workflow Clarity

The single routing action is made unambiguous by the decision tree plus explicit conflict-resolution tiebreakers ("Use concurrency, NOT swift", "Use axiom-build first"), which function as validation checkpoints for routing decisions. Not 5 because decision-tree entries 6-8 route to external skills with inconsistent formats and no conflict-resolution coverage.

4 / 5

Progressive Disclosure

References are one level deep, clearly signaled, and organized by symptom and topic ("See `skills/tvos.md"), with the body acting as an overview. Not 5 because the referenced files (skills/swift-modern.md, skills/ownership-conventions.md, etc.) do not exist in the bundle, so the navigation cannot be verified to resolve.

4 / 5

Total

15

/

20

Passed

Description

61%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 well-scoped trigger-first description with concrete topic keywords and an explicit disambiguation from framework questions. Its main weakness is the absence of any stated capability — the reader must infer what the skill does from the topic list.

Suggestions

Add an explicit capability statement naming what the skill does, e.g. "Reviews Swift code and provides reference material for modern idioms, ownership, and tvOS development. Use when..."

Broaden trigger synonyms to include terms users naturally say for the covered topics, such as Transferable, ShareLink, Focus Engine, or borrowing/consuming parameters.

DimensionReasoningScore

Specificity

The description enumerates five concrete topic areas ("modern idioms, noncopyable types, drag and drop, debug deep links, tvOS targets") but never states an action or capability verb, so it sits between anchor 2 (domain only) and anchor 3 (domain plus concrete actions).

3 / 5

Completeness

The 'when' is explicit and well-scoped ("Use when the question is about Swift or its toolchain rather than a framework"), but the 'what' — what the skill actually does — is never stated; per the guidelines only explicitly stated content is scored. Not 4 because that anchor requires both 'what' and 'when' present.

3 / 5

Trigger Term Quality

Natural user phrases like "Swift", "drag and drop", "tvOS", and "debug deep links" are present and would be said by users needing this skill, but common synonyms such as Transferable, ShareLink, Focus Engine, or borrowing/consuming are missing. Not 5 because coverage lacks the synonym breadth of the top anchor; not 3 because the terms go well beyond a single generic keyword.

4 / 5

Distinctiveness Conflict Risk

The carve-out "rather than a framework" plus niche topics (noncopyable types, tvOS, debug deep links) makes it mostly distinct, but it still overlaps with closely related sibling skills (Swift concurrency, performance). Not 5 because those adjacent-skill conflicts remain plausible.

4 / 5

Total

14

/

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

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

CharlesWiltgen/Axiom

Path

axiom-codex/skills/axiom-swift/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.