swiftui-performance-audit

SwiftUI performance: render, scroll, CPU/memory, updates, layout, Instruments.

Quality

60%

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 ./skills/swiftui-performance-audit/SKILL.md

Quality

Content

61%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 well-structured with executable code-smell examples and a clear five-stage workflow backed by real reference files. It is held back by a duplicated culprit list between sections 1 and 3, implicit rather than explicit validation checkpoints in the workflow, and reference links that are listed but not contextualized for when to use each.

Suggestions

De-duplicate the six-item culprit list that appears verbatim in both 'Code-First Review' and 'Analyze and Diagnose' — reference one list from the other.

Make the Verify step an explicit checkpoint: 'Have the user re-capture the same interaction and report CPU/frame-drop/memory delta before/after; do not consider the fix done until the delta is reported.'

Annotate each reference link with its trigger condition (e.g. 'read when triaging hangs/hitches') so the right reference is consulted at the right step.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with focused smell/fix pairs, but sections 1 and 3 duplicate the same six-item culprit list verbatim and the 'Collect'/'Focus on'/'Provide' headers add modest overhead that could be tightened.	3 / 5
Actionability	Concrete, executable Swift code examples for every common smell plus paired fixes, with only minor gaps — some fixes are sketched ('update filtered when inputs change') rather than fully copy-paste ready.	4 / 5
Workflow Clarity	The five-step sequence (Code-First → Profile → Diagnose → Remediate → Verify) is clear, but validation/checkpoint steps are implicit; the Verify step relies on the user supplying metrics rather than an explicit re-run-and-compare checkpoint, so it sits at 3 not 4.	3 / 5
Progressive Disclosure	SKILL.md is a well-organized overview with a References section pointing to four real, one-level-deep reference files (all verified present), keeping detail out of the main body; minor gaps are the lack of in-body navigation cues for when to consult each reference.	4 / 5
	Total	14 / 20 Passed

Description

58%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 specific and reasonably distinctive, listing concrete performance dimensions and naming Instruments, but it lacks an explicit 'Use when...' trigger clause and misses natural user phrasings like 'frame drops' and 'hitches'. Completeness is capped at 3 by the missing trigger guidance.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when auditing SwiftUI scroll/frame-drop/hang issues or when the user reports slow SwiftUI rendering.'

Include natural trigger terms users actually say — 'frame drops', 'hitches', 'hangs', 'slow scrolling', 'janky' — alongside the technical terms.

Clarify the scope distinction from general performance work by tying it explicitly to SwiftUI view bodies and invalidation.

Dimension	Reasoning	Score
Specificity	Lists several concrete performance dimensions — 'render, scroll, CPU/memory, updates, layout, Instruments' — naming specific SwiftUI performance concerns rather than generic actions, with only minor coverage gaps (no explicit mention of hangs/hitches).	4 / 5
Completeness	There is a clear 'what' (audit SwiftUI performance across listed dimensions) but no 'Use when...' trigger clause; the 'when' is only weakly implied, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Contains relevant keywords ('SwiftUI performance', 'scroll', 'Instruments') but omits the natural phrases a user would say such as 'slow scroll', 'frame drops', 'hitches', or 'hangs'.	3 / 5
Distinctiveness Conflict Risk	The SwiftUI-performance niche is fairly specific and unlikely to trigger for unrelated skills, though 'CPU/memory' and 'layout' could lightly overlap with a general performance-investigation skill.	4 / 5
	Total	14 / 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: steipete/agent-scripts
Path: skills/swiftui-performance-audit/SKILL.md
Commit: dc4f583

Reviewed: 2 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.