CtrlK
BlogDocsLog inGet started
Tessl Logo

performance-profiling

Guide performance profiling for Apple platform apps with Instruments, Xcode diagnostics, and MetricKit. Use when investigating app hangs, stutters, high CPU, memory leaks, memory growth, OOM crashes, slow launch, battery drain, thermal issues, App Store performance readiness, or when adding os_signpost and measurement hooks.

73

Quality

90%

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

SKILL.md
Quality
Evals
Security

Quality

Content

81%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, actionable skill body that uses progressive disclosure effectively: a lean overview with a decision tree routing to four real reference files, an executable MetricKit example, and a concrete review checklist. It scores slightly below top on conciseness, actionability, and workflow_clarity due to minor padding and implicit rather than explicit validation feedback loops.

Suggestions

Tighten the Profiling Ground Rules and Xcode Diagnostics sections by trimming commonly known Apple guidance (e.g. 'Release configuration because optimizations can change hot paths') to lift conciseness toward 5.

Make the workflow's verification step an explicit feedback loop, e.g. '6. Re-profile; if the bottleneck persists, return to step 4 and inspect the next-hotspot path', to push workflow_clarity to 5.

Add at least one inline concrete Instruments command or signpost snippet in the body so actionability does not depend entirely on the reference files.

DimensionReasoningScore

Conciseness

Largely lean and assumes competence, with a focused decision tree, quick-reference table, and checklists; minor padding exists where some ground rules and diagnostics rows restate commonly known Apple guidance.

4 / 5

Actionability

Provides an executable MetricKit Swift snippet and concrete tools/metrics per problem, plus a clear decision tree and checklist; minor gaps in that profiling commands themselves are deferred to the reference files rather than shown inline.

4 / 5

Workflow Clarity

A clear six-step profiling workflow is sequenced with an explicit re-profile/measurement verification step; it is one level short of a 5 because validation/error-recovery feedback loops are implicit rather than fully spelled out.

4 / 5

Progressive Disclosure

SKILL.md is a concise overview with well-signaled, one-level-deep references to four real files in references/, each mapped via the decision tree, quick-reference table, and a final references list — clean navigation with no nested references.

5 / 5

Total

17

/

20

Passed

Description

100%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 strong, well-crafted description that concisely states capabilities and an explicit, thorough 'Use when' clause with natural trigger terms. It is distinct, specific, and free of vague fluff.

DimensionReasoningScore

Specificity

Names the domain (Apple platform profiling) and multiple concrete capabilities — Instruments, Xcode diagnostics, MetricKit, os_signpost, and measurement hooks — with comprehensive coverage.

5 / 5

Completeness

Explicitly answers both what it does ('Guide performance profiling...with Instruments, Xcode diagnostics, and MetricKit') and when to use it via a thorough 'Use when investigating...' clause with concrete trigger conditions.

5 / 5

Trigger Term Quality

Comprehensive natural trigger phrases users would actually say: 'app hangs', 'stutters', 'high CPU', 'memory leaks', 'OOM crashes', 'slow launch', 'battery drain', 'thermal issues', covering synonyms and common variations.

5 / 5

Distinctiveness Conflict Risk

Clear niche (Apple-platform performance profiling) with highly specific triggers unlikely to conflict with other skills; the Apple-specific tooling language further narrows the scope.

5 / 5

Total

20

/

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
MengTo/Skills
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.