axiom-analyze-swift-performance

Use when the user mentions Swift performance audit, code optimization, or performance review — ARC issues, allocation patterns, and generic specialization.

Quality

80%

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 ./axiom-codex/skills/axiom-analyze-swift-performance/SKILL.md

Quality

Content

85%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 highly actionable, well-sequenced audit prompt with concrete search commands, specific fixes, and explicit verification checkpoints. Its main weakness is progressive disclosure: all content lives in one long SKILL.md with no reference files to offload the detailed anti-pattern catalog or output templates.

Suggestions

Move the 8-pattern anti-pattern catalog (Phase 2) into a references/ file (e.g., ANTI_PATTERNS.md) and summarize it in SKILL.md with a clearly signaled link.

Offload the full output-format template and health-score table into a references/OUTPUT_FORMAT.md, keeping only a brief example inline.

Tighten the few passages that define concepts Claude already knows (existential containers, witness tables) to bare detection/fix essentials.

Dimension	Reasoning	Score
Conciseness	The ~285-line body is dense with concrete detection patterns, severity tables, and fix directives, with cost figures (~100μs, ~10x) that earn their place; only minor explanatory passages (e.g., defining existential/witness-table behavior) could be trimmed.	4 / 5
Actionability	Copy-paste-ready Grep/Glob patterns, specific fix directives ("Use `borrowing` for read-only", "add `isKnownUniquelyReferenced` guard", "Use `some` instead of `any`"), and a fully templated output format give executable guidance across the common audit cases.	5 / 5
Workflow Clarity	A clearly sequenced Phase 1–5 pipeline with explicit verification checkpoints ("use Read to verify the surrounding context before reporting", "Require evidence from the Phase 1 map") provides feedback discipline appropriate to a read-only audit skill.	5 / 5
Progressive Disclosure	The file is well-organized by headings but is a monolithic ~285-line document with no bundle files in references/scripts/assets, so content that could be offloaded (the 8 anti-pattern catalog, output template) is inlined rather than split into one-level-deep reference files.	3 / 5
	Total	17 / 20 Passed

Description

75%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 concise, well-structured description with an explicit trigger clause and concrete performance sub-domains. It is specific and distinct, though it names issue categories rather than actions and could add a few more natural synonyms.

Suggestions

Lead with an explicit action verb (e.g., "Detects and reports Swift performance issues...") to sharpen the 'what'.

Add natural synonyms users say, such as "slow", "speed up", "profiling", or "Instruments", to broaden trigger coverage.

Narrow "code optimization" or qualify it as "Swift code optimization" to reduce overlap with general-purpose optimizers.

Dimension	Reasoning	Score
Specificity	Names the Swift performance domain plus three concrete sub-areas ("ARC issues, allocation patterns, and generic specialization"), giving several specific capabilities, though it lists issue categories rather than action verbs and omits other body-covered areas like collections and actor isolation.	4 / 5
Completeness	An explicit "Use when the user mentions..." clause answers 'when' with concrete triggers, and the named issue categories answer 'what', but the 'what' lacks an explicit action verb (e.g., "Detects/audits") so it is not maximally explicit.	4 / 5
Trigger Term Quality	Includes natural phrases a user would say ("Swift performance audit, code optimization, or performance review") plus domain terms (ARC, allocation, generic specialization), but misses common synonyms like "slow", "speed up", "profiling", or "Instruments".	4 / 5
Distinctiveness Conflict Risk	The Swift-specific performance niche with concrete sub-triggers is clearly distinct, but "code optimization" is somewhat broad and overlaps with general optimizers and the related swiftui-performance-analyzer, creating minor conflict risk.	4 / 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: CharlesWiltgen/Axiom
Path: axiom-codex/skills/axiom-analyze-swift-performance/SKILL.md
Commit: 9cbcd2d

Reviewed: 3 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.