CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

healthkit

Builds HealthKit authorization, sample reads/writes, statistics, background delivery, and workout sessions. Use for Apple Health metrics, charts, HKQuantitySample storage, HKLiveWorkoutBuilder, unit handling, workout recording, or health-data delivery and privacy behavior.

Quality

85%

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

71%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 a well-organized, information-dense overview with genuinely useful HealthKit-specific facts (masked read authorization, iPadOS availability, plist keys, unit compatibility rules) and a strong review checklist. Its main weakness is navigation integrity: all four "Route by Task" deep links use anchor slugs that don't match the reference file's actual headings, and the advertised HKUnit Reference section is missing entirely from the bundle.

Suggestions

Fix the Route by Task anchor links to match the reference file's real headings: #statistics-collection-for-charts, #background-delivery-details, and #workout-session-lifecycle.

Add the missing HKUnit Reference section to references/healthkit-patterns.md (string formats, conversion, compound units) or remove the route that promises it, since the body's Writing Samples and Units section defers all unit detail to it.

Include one minimal executable snippet in the body for the most common flow (requestAuthorization with explicit toRead/toShare sets), so the highest-frequency task doesn't require a file jump.

DimensionReasoningScore

Conciseness

The body is dense and factual (query selection table, exact plist keys, unit rules, pitfalls, checklist) with almost no explanation of concepts Claude already knows. Not a 5 because the intro sentence "Covers authorization, quantity samples, statistics collection queries..." duplicates the frontmatter description, and time-sensitive version strings ("Targets Swift 6.4 / iOS 26+") sit in the intro rather than a dedicated version section; clearly above anchor 3 since padding is minimal.

4 / 5

Actionability

Concrete specifics throughout: exact plist keys (NSHealthShareUsageDescription), an executable availability guard snippet, API-level checklist items ("enableBackgroundDelivery(for:frequency:)"), and a concrete unit mistake (".meter() instead of .count()"). Not a 5 because there is no executable authorization-request or sample-write snippet in the body — those common cases are only reachable via routing, and one routed destination (HKUnit Reference) contains no actual unit guidance.

4 / 5

Workflow Clarity

The topic organization is coherent (capability → availability → query selection → writes → routing → mistakes → checklist) and the Review Checklist provides explicit verification checkpoints ("isHealthDataAvailable() checked before accessing store", "UI gracefully handles devices where HealthKit is unavailable"). Not a 5 because there is no sequenced procedure with feedback loops — this is reference-style material, and steps like requesting authorization before enabling background delivery are left implicit.

4 / 5

Progressive Disclosure

Structure is right — one-level-deep reference file with a task-based "Route by Task" section — but the deep links are broken against the actual bundle: the reference file's real headings are "Statistics Collection for Charts", "Background Delivery Details", and "Workout Session Lifecycle", not the linked #statistics-collection-queries/#background-delivery/#workout-sessions, and the promised #hkunit-reference section does not exist in references/healthkit-patterns.md at all. References are clearly signaled but one in four routes leads to nonexistent content, which is more than anchor 4's "minor organization gaps" yet well above the inlining/unsignaled problems of anchor 3's typical case.

3 / 5

Total

15

/

20

Passed

Description

92%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 a strong example: third-person, concrete capability enumeration, an explicit "Use for" trigger clause mixing natural language (Apple Health, charts, workout recording) with precise API terms, and a well-defined niche with minimal conflict risk. The only gap is a few natural user phrasings (heart rate, steps, Apple Watch) that would strengthen trigger coverage.

DimensionReasoningScore

Specificity

"Builds HealthKit authorization, sample reads/writes, statistics, background delivery, and workout sessions" lists multiple concrete capabilities that comprehensively cover the skill's scope, matching the anchor for multiple specific concrete actions. Not a 4 because coverage of the domain's capability areas is complete rather than having notable gaps.

5 / 5

Completeness

Explicitly answers "what" (authorization, sample reads/writes, statistics, background delivery, workout sessions) and "when" via a concrete "Use for..." clause with specific trigger phrases, mirroring the anchor-5 example structure. Not a 4 because the "when" clause is explicit and enumerated rather than generic.

5 / 5

Trigger Term Quality

"Use for Apple Health metrics, charts, HKQuantitySample storage, HKLiveWorkoutBuilder, unit handling, workout recording, or health-data delivery and privacy behavior" covers natural terms (Apple Health, metrics, charts, workout recording) plus key API names. Not a 5 because common user phrasings like "heart rate", "step count", or "Apple Watch" are absent; clearly above anchor 3's partial coverage.

4 / 5

Distinctiveness Conflict Risk

Names a clear niche (Apple Health/HealthKit on Apple platforms) with distinctive API identifiers (HKQuantitySample, HKLiveWorkoutBuilder) that no other plausible skill would trigger on. Not a 4 because there is no meaningful overlap risk with adjacent skills.

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

thienqo/ios-skills

Path

skills/healthkit/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.