CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

metrickit

Use when collecting or analyzing production iOS or iPadOS performance telemetry with MetricKit, including iOS 27 MetricManager async metric or diagnostic reports, hang or crash triage, custom signposts, extended launch measurement, durable export, or iOS 26 MXMetricManager compatibility.

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

The canonical home for this skill is dpearson2699/swift-ios-skills

SKILL.md
Quality
Evals
Security

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 well-structured, highly actionable skill body: the ingestion workflow is sequenced with explicit validation checkpoints and error paths, and detailed patterns are correctly split into a clearly signaled one-level-deep reference file. The main costs are minor — duplicated guidance between Common Mistakes and Review Checklist, and code snippets that rely on application-specific placeholders and beta-unverified API accessors.

Suggestions

Merge the Common Mistakes table and Review Checklist into one section (or cross-link them) since they restate the same corrections in two forms, trimming roughly a dozen lines.

Give the placeholder analysis helpers (analyzeHangTime, analyzeCrash, preserveUnknownMetric) one shared line of shape guidance (e.g., signature and side effect) so the switch examples are closer to copy-paste ready.

Flag beta-unverified accessors like intervalEntries.fullDayEntry.values inline, mirroring the top-level beta notice, so a reader knows exactly which lines to re-check against the shipping SDK.

DimensionReasoningScore

Conciseness

The body is dense and API-specific with no filler explaining concepts Claude already knows, but the Common Mistakes table and Review Checklist restate the same guidance in two forms (e.g., the direct-upload correction and the matching "encoded and durably enqueued" checklist item), and the 14-item Contents list adds length. This is the minor-trimmable-overexplanation profile of anchor 4, above the could-be-tightened profile of 3 and below the every-token-earns-its-place profile of 5.

4 / 5

Actionability

Concrete, near-executable Swift for the manager lifecycle, report-result and diagnostic switches, mxSignpost, trackLaunchTask, and a six-step durable-outbox workflow, plus field tables and an explicit routing table. Placeholder helpers (analyzeHangTime, durableOutbox) and beta-unverified accessors (entry.values) leave minor gaps, matching anchor 4 rather than the fully copy-paste-ready profile of anchor 5.

4 / 5

Workflow Clarity

The pipeline is sequenced with explicit validation checkpoints: persist the complete report before extracting, acknowledge only after enqueue succeeds, mark uploaded only after server acceptance, error paths via onTrackingError and @unknown default, and a closing review checklist. This matches anchor 5 (clear sequence, explicit validation, error-recovery loops, checklist) rather than anchor 4, which allows missing checkpoints.

5 / 5

Progressive Disclosure

The body is a well-organized overview that pushes implementation detail (outbox code, MetricResult catalog, iOS 26 subscriber and legacy signpost patterns) into references/metrickit-patterns.md, a single real bundle file one level deep, signaled at point of need with working anchors and listed in a References section. This matches the anchor-5 example of a clear overview with well-signaled one-level-deep references.

5 / 5

Total

18

/

20

Passed

Description

91%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 description with comprehensive, concrete capabilities and the natural trigger vocabulary of the MetricKit domain. Its single weakness is structural: the capability statement and the usage trigger are merged into one sentence, so the "what does this do" half is less crisply separated than it could be.

Suggestions

Lead with a direct third-person capability statement (e.g., "Collects and analyzes MetricKit metric and diagnostic reports for production iOS/iPadOS apps.") before the "Use when..." clause so the what is explicit rather than embedded in the trigger.

Add one or two common user phrasings such as "production crash or hang reports" or "app performance monitoring" to the trigger list to broaden natural-term coverage.

DimensionReasoningScore

Specificity

The description lists multiple concrete capabilities — "collecting or analyzing production iOS or iPadOS performance telemetry", "hang or crash triage", "custom signposts", "extended launch measurement", "durable export", and "iOS 26 MXMetricManager compatibility" — covering the skill's entire surface. It matches the anchor-5 example (multiple specific actions, comprehensive coverage) rather than anchor 4, which reserves room for minor gaps.

5 / 5

Completeness

Both what and when are present and the when is explicit ("Use when collecting or analyzing production iOS or iPadOS performance telemetry with MetricKit"), but the what is fused into the when-clause rather than stated as a standalone capability declaration, leaving it slightly less explicit than the anchor-5 pattern. It is clearly above anchor 3, where the when would be missing or only weakly implied.

4 / 5

Trigger Term Quality

It contains the natural vocabulary developers actually use: "MetricKit", "hang", "crash", "custom signposts", "metric or diagnostic reports", "MXMetricManager", "production telemetry". Only minor variants ("performance monitoring", "app metrics") are absent, so it fits the comprehensive-coverage anchor better than the few-missing anchor at 4.

5 / 5

Distinctiveness Conflict Risk

Framework-specific triggers ("MetricKit", "MetricManager", "MXMetricManager", "extended launch") carve a clear niche with minimal conflict risk; only "custom signposts" slightly overlaps a general os_signpost/logging skill, which is the minimal-risk profile of anchor 5 rather than the minor-overlap profile of anchor 4.

5 / 5

Total

19

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

dpearson2699/swift-ios-skills

Path

skills/metrickit/SKILL.md

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.