Name: healthkit
Rating: 57.599999999999994 (1 reviews)
Author: Prisma-Labs-Dev

Blog Docs Log inGet started

healthkit

API reference: HealthKit. Query for HKHealthStore, HKQuantitySample, workouts, health data read/write.

Quality

66%

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/healthkit/SKILL.md

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 an exemplary lean index-style skill page: no filler, a clear topic-to-file map, and an enforced answer format. Its weaknesses are operational — the referenced documentation files are absent from the bundle and no path or search instruction tells the agent where or how to open them.

Suggestions

Ship the six referenced documentation files in the bundle (e.g., under references/) so every path in the Files section actually resolves.

State where the docs live relative to SKILL.md and how to search them (e.g., "grep <topic> references/*.md" or "read references/healthkit-index.md first"), making the lookup step executable.

Treat healthkit-index.md as the explicit entry point ("start here for unknown/multi-API questions") so the navigation order is unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is ~30 lines with zero padding: "Search these docs to answer questions about HealthKit APIs", a compact return format, and a one-line-per-file map. Every token earns its place and nothing re-explains what Claude already knows. Clearly matches the "lean and efficient" anchor; no anchor above exists to drift to.	5 / 5
Actionability	The file map ("hkhealthstore.md - Health data store operations", etc.) and the required two-part return format are concrete, but key execution details are missing: no path or location for the listed files and no instruction on how to search them. Fits "some concrete guidance but incomplete"; not 4 because a reader cannot actually locate or search the docs from what is written.	3 / 5
Workflow Clarity	For this simple single-task skill the action is nearly unambiguous: pick the relevant file from the topic map, read it, and answer in the mandated Summary + file-paths format. Not 5 because the search step itself (which docs, where, how) is left implicit; not 3 because the sequence that is given is clear and nothing risky needs validation.	4 / 5
Progressive Disclosure	The intent matches a good index-overview pattern (one level deep, per-topic files clearly listed with descriptions), but the six referenced files (healthkit-index.md, hkhealthstore.md, etc.) do not exist in the bundle — no references/, scripts/, or assets/ directory is present. Navigation is therefore structurally sound on paper but broken in practice; this sits between "good structure" (4) and the broken-reference case, landing at 3.	3 / 5
	Total	15 / 20 Passed

Description

62%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 communicates a clear, specific HealthKit API-reference purpose with distinct triggers, but it omits any explicit "when to use" guidance and leans on framework class names rather than the natural phrases users would say. It reads as a terse index label rather than a self-contained trigger description.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks about HealthKit, Apple Health/health app data, workouts, heart rate, steps, or reading/writing health metrics on Apple platforms."

Include natural user-facing synonyms alongside class names (heart rate, steps, sleep, fitness data, Apple Watch) so the description triggers on how users actually phrase these requests.

Briefly state the read vs. write/authorization capabilities to close the coverage gap left by the generic "health data read/write" phrase.

Dimension	Reasoning	Score
Specificity	"Query for HKHealthStore, HKQuantitySample, workouts, health data read/write" lists several concrete actions anchored to specific API names, with minor gaps (e.g., saving/authorizing data is only implied by "read/write"). Not 5 because "health data read/write" is generic and coverage of HealthKit's surface is thin; not 3 because multiple concrete, named actions are present.	4 / 5
Completeness	The "what" is clear (HealthKit API reference; query HKHealthStore, HKQuantitySample, workouts, health data read/write) but there is no "Use when..." or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. Not 2 because the "what" half is specific and concrete.	3 / 5
Trigger Term Quality	Relevant keywords exist (HealthKit, workouts, health data, HKHealthStore) but common user phrasings are missing — heart rate, steps, sleep, fitness data, Apple Watch. Fits "some relevant keywords but missing common variations or synonyms"; not 4 because the natural terms users actually say are largely absent in favor of framework class names.	3 / 5
Distinctiveness Conflict Risk	"API reference: HealthKit" plus framework-specific class names (HKHealthStore, HKQuantitySample) carve out a clear niche with minimal overlap risk against generic health/fitness or document skills. Not 4 because no closely related skill would plausibly collide with these HealthKit-specific triggers.	5 / 5
	Total	15 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: Prisma-Labs-Dev/apple-skills
Path: skills/healthkit/SKILL.md
Commit: 4986260

Reviewed: 3 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.