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

SKILL.md
Quality
Evals
Security

Quality

Content

92%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-engineered reference skill: executable Swift for every workflow, a gated six-step durable-export sequence with explicit checkpoints, an explicit review checklist, and textbook conditional loading of a single one-level-deep reference file. The only real cost is token weight — a redundant table of contents and a critical rule repeated across four sections — which is a trim exercise, not a structural flaw.

DimensionReasoningScore

Conciseness

The body is dense and assumes competence — it never explains what telemetry or MetricKit is — and time-sensitive version info is properly quarantined in a beta-sensitivity callout and a dedicated "iOS 26 Compatibility" section. Minor trimmable material remains: a 16-line Contents table of contents that duplicates the headings, and the durable-enqueue-before-analysis rule restated in at least four places (setup, report receipt, export steps, mistakes table, checklist), which keeps it at anchor 4 rather than the every-token-earns-its-place anchor 5.

4 / 5

Actionability

Provides copy-paste-ready Swift for every core task: retained-manager setup with one consumer task per sequence ("for await report in manager.metricReports"), fullDayEntry result switching with "@unknown default", diagnostic routing, "mxSignpost" begin/end, "trackLaunchTask(id:onTrackingError:_:)", and "JSONEncoder().encode(report)" plus outbox enqueue. The few undefined symbols ("durableOutbox", "analyzeHangTime") are explicitly declared application-owned parameters, not gaps, so this matches anchor 5 rather than anchor 4's 'minor gaps'.

5 / 5

Workflow Clarity

The durable ingestion workflow is a numbered six-step sequence with explicit ordering gates ("Acknowledge local processing only after the enqueue succeeds", "Mark the outbox item uploaded only after the server accepts it"), error feedback paths ("onTrackingError", "@unknown default" preservation), and a closing ten-item Review Checklist that functions as validation, including "iOS 27 APIs have been compiled with the shipping Xcode 27 SDK". This matches anchor 5's explicit checkpoints plus checklist; it is not a destructive/batch operation, so the score-3 cap does not apply.

5 / 5

Progressive Disclosure

The 297-line body stays an overview: detailed ingestion patterns, the full MetricResult catalog, and the legacy iOS 26 subscriber code all live one level deep in references/metrickit-patterns.md, and all three load points are condition-signaled ("Load ... when implementing durable ingestion", "Load the [Key Metric Result Catalog] ... when mapping exact MetricResult cases", "Load [iOS 26 Compatibility] ... for the full subscriber"). Both deep-link anchors resolve to real headings in the actual bundle file, and the reference file contains no second-level file references — a clean match for anchor 5.

5 / 5

Total

19

/

20

Passed

Description

83%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 specific, trigger-rich description that names the exact framework, APIs, OS versions, and task types the skill covers, with an explicit "Use when..." clause. Its main limitation is structural: the capability statement (what) is merged into the trigger clause rather than stated separately, and a few natural synonyms (e.g., "performance monitoring", "CPU exception") are absent. Both minor gaps keep it just below top marks on completeness and trigger term quality.

Suggestions

Lead with a standalone capability sentence (e.g., "Implements MetricKit telemetry ingestion and analysis for production iOS/iPadOS apps.") before the "Use when..." clause so the 'what' is explicit and separate from the 'when'.

Add one or two natural trigger synonyms users commonly say, such as "performance monitoring" or "CPU or disk write exceptions", to broaden natural-language matching.

DimensionReasoningScore

Specificity

Enumerates concrete, named capabilities — "hang or crash triage", "custom signposts", "extended launch measurement", "durable export" — tied to specific APIs and platforms ("iOS 27 MetricManager", "iOS 26 MXMetricManager"), covering every major section of the skill. Matches the anchor 5 example's comprehensive multi-action coverage rather than anchor 4, since no capability area of the skill is missing from the description.

5 / 5

Completeness

An explicit trigger clause is present ("Use when collecting or analyzing production iOS or iPadOS performance telemetry with MetricKit"), and the what — collecting, analyzing, triaging, and exporting MetricKit telemetry — is concrete but folded into that trigger clause rather than stated as its own capability sentence. Above anchor 3 (both what and when are present and concrete) but below anchor 5, which shows what and when as separately explicit statements.

4 / 5

Trigger Term Quality

Contains natural terms users would actually say — "MetricKit", "performance telemetry", "hang", "crash", "diagnostic", "signposts", "MXMetricManager" — but misses common variations such as "performance monitoring", "app hang", or "CPU/memory exceptions". Good coverage with a few natural terms missing fits anchor 4, not the synonym-complete anchor 5.

4 / 5

Distinctiveness Conflict Risk

Scoped to a single Apple framework with named APIs and OS versions ("MetricKit", "MetricManager", "MXMetricManager", "iOS 27", "iOS 26"), giving it a clear niche with distinct triggers and minimal conflict risk against general performance or debugging skills. Not the 4 anchor because the named-framework triggers leave no real overlap ambiguity.

5 / 5

Total

18

/

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

thienqo/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.