CtrlK
BlogDocsLog inGet started
Tessl Logo

axiom-analyze-swift-performance

Use when the user mentions Swift performance audit, code optimization, or performance review.

56

Quality

63%

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-swift-performance/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

73%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-structured, actionable audit workflow with explicit validation and checklists, scoring highly on workflow clarity and actionability. Its main weakness is cross-phase repetition that could be deduplicated to improve token efficiency.

Suggestions

Deduplicate findings that recur across Phase 2, the Phase 3 table, and the Phase 4 compound table — reference the single canonical description instead of restating impact figures.

Add one or two concrete before/after Swift code blocks for the highest-impact fixes (e.g., borrowing vs. value parameter, any vs. some) to lift actionability from prose to executable examples.

Consider moving the 8-pattern Phase 2 catalog or the output template into a reference file if the skill is also used in contexts where the full prompt is not needed.

DimensionReasoningScore

Conciseness

The body is instruction-dense with no padding of concepts Claude already knows, but several findings (e.g., actor hops in loops) recur across Phase 2, the Phase 3 table, and the Phase 4 compound table, so it could be tightened by deduplication.

3 / 5

Actionability

Copy-paste-ready Grep/Glob patterns, concrete file-exclusion lists, and quantified fixes ('~100μs × N') provide mostly executable guidance, but fixes are given as prose rather than executable before/after Swift code blocks.

4 / 5

Workflow Clarity

A clear five-phase sequence with explicit validation checkpoints ('use Read to verify the surrounding context before reporting'), a Phase 1 output checklist, and a False Positives checklist; this is a read-only audit so the destructive-batch cap does not apply.

5 / 5

Progressive Disclosure

No bundle files exist, so the skill is a single well-organized file with clear phased headers and no nested references; inlining the anti-pattern catalog is justified for an agent prompt that needs all patterns in context, leaving only minor organization gaps.

4 / 5

Total

16

/

20

Passed

Description

52%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 provides a clear, natural trigger clause but omits any explicit statement of what the skill does, relying on the trigger to imply capability. It is reasonably distinct and uses good trigger terms, though it lacks action variety and a few common synonyms.

Suggestions

Add an explicit 'what' clause before the trigger, e.g. 'Detects Swift performance anti-patterns (ARC overhead, unnecessary copies, unspecialized generics, actor-isolation costs). Use when...'

Broaden trigger terms with natural user phrasings like 'slow Swift code', 'Swift profiling', or 'make my Swift code faster'.

Disambiguate from the sibling skill by noting scope, e.g. '...for Swift-level performance; for SwiftUI view-body issues use swiftui-performance-analyzer.'

DimensionReasoningScore

Specificity

The phrase 'Swift performance audit, code optimization, or performance review' names the domain and a couple of actions, but the actions are near-synonyms rather than distinct concrete capabilities, matching the anchor 'Names domain and 1-2 concrete actions, but not comprehensive'.

3 / 5

Completeness

The description only states when to use the skill ('Use when the user mentions...') with no explicit statement of what it does, matching the anchor 'only "when" is present without "what"'; the 'what' must not be inferred per the judging guidelines.

2 / 5

Trigger Term Quality

Terms like 'Swift performance audit', 'code optimization', and 'performance review' are natural phrases a user would say, giving good keyword coverage, though common variations like 'slow Swift code' or 'profiling' are missing.

4 / 5

Distinctiveness Conflict Risk

The Swift-specific framing carves a clear niche, but 'code optimization' and 'performance review' are broad and the description does not disambiguate from the sibling swiftui-performance-analyzer, leaving minor overlap risk.

4 / 5

Total

13

/

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.