CtrlK
BlogDocsLog inGet started
Tessl Logo

axiom-analyze-swiftui-performance

Use when the user mentions SwiftUI performance, janky scrolling, slow animations, or view update issues.

57

Quality

64%

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-analyze-swiftui-performance/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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.

This is a strong, highly actionable auditor skill: concrete grep patterns, per-pattern verification and fixes, a context-reasoning table, compound-severity matrix, and a ready output template. Its main weakness is minor over-explanation and external references whose targets are not present in the bundle.

DimensionReasoningScore

Conciseness

The body is dense and directive — phases, grep patterns, severity tables, and a health-score rubric with almost no padding or restating of concepts Claude already knows — with only minor over-explanation (e.g. re-justifying why sets are O(1)) that could be trimmed.

4 / 5

Actionability

Each anti-pattern gives an exact grep string, a verification step (Read near 'var body'), a concrete impact, and a specific fix (e.g. 'Move to static let', 'Add .onDisappear { timer?.invalidate() }'), and the output format is a copy-paste-ready template — fully executable guidance covering common cases.

5 / 5

Workflow Clarity

Five phases are explicitly sequenced with checkpoints (produce the Performance Context Map before proceeding, verify each grep with Read, cross-reference compounds in Phase 4) and the destructive/batch guidance 'present this map before proceeding' plus 'require evidence from the Phase 1 map' acts as a validation gate, though there is no explicit validate->fix->retry loop for re-scanning after fixes.

4 / 5

Progressive Disclosure

Content is well-organized into phases with tables and an output template, and cross-references are one level deep and clearly signaled ('See axiom-swiftui (skills/layout-ref.md)', 'axiom-performance (skills/memory-debugging.md)'), but those references point outside the bundle (no references/scripts/assets directories exist) and the bulk anti-pattern catalog lives inline rather than in a split reference file.

4 / 5

Total

17

/

20

Passed

Description

47%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 has strong, natural trigger phrasing and a clear niche, but it is missing any statement of what the skill actually does — it is purely a 'when' clause. Adding a concrete action clause ('Detects SwiftUI performance anti-patterns and frame-drop causes') would lift completeness and specificity.

Suggestions

Lead with a 'what' clause naming concrete actions, e.g. 'Detects SwiftUI performance anti-patterns (file I/O in view body, missing lazy loading, formatter misuse) and context-dependent frame-drop causes.'

Append the trigger clause after the 'what', e.g. 'Use when the user mentions SwiftUI performance, janky scrolling, slow animations, frame drops, or view update issues.'

Add a synonym users say but is currently absent, e.g. 'frame drops' or 'lag', to round out trigger-term coverage toward a 5.

DimensionReasoningScore

Specificity

The description names the SwiftUI performance domain but lists zero concrete actions the skill performs — it only states when to invoke it, never what it does ('detects anti-patterns', 'maps view hierarchy', etc.), matching 'Names the domain but actions are minimal or generic'.

2 / 5

Completeness

Only a 'when' clause is present — 'Use when the user mentions...' — with no 'what' describing what the skill does, matching 'only "when" is present without "what"'; it cannot reach 3 because the 'what' is entirely absent.

2 / 5

Trigger Term Quality

Phrases like 'SwiftUI performance, janky scrolling, slow animations, or view update issues' are natural things a user would say; good coverage with a few synonyms (e.g. 'frame drops', 'lag') missing, placing it just above the midpoint.

4 / 5

Distinctiveness Conflict Risk

The trigger is narrowly scoped to SwiftUI-specific performance symptoms (janky scrolling, view update issues), making it mostly distinct from general performance or UI skills with only minor overlap risk against a sibling SwiftUI debugging skill.

4 / 5

Total

12

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
CharlesWiltgen/Axiom
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.