axiom-apple-docs

Use when ANY question involves Apple framework APIs, Swift compiler errors, or Xcode-bundled documentation. Covers Liquid Glass, Swift 6.2 concurrency, Foundation Models, SwiftData, StoreKit, 32 Swift compiler diagnostics.

Quality

92%

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

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-constructed router/index skill: executable paths, a clear routing decision tree, and an ordered fallback chain with a reporting checkpoint. The main weakness is redundancy between the categorized guide tables and the routing decision tree, which re-encodes the same topic→file mappings.

Suggestions

Collapse the Routing Decision Tree into the guide tables or replace it with a single "default routing" line, since it duplicates the topic→filename mappings already listed under "Guide Files".

Reconcile the diagnostics count: the description says "32 Swift compiler diagnostics" but the body states "46 files in the diagnostics directory" — pick one accurate figure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient token-dense tables and assumes Claude's competence, but the "Routing Decision Tree" re-maps topic→file pairs already enumerated in the guide tables above, a clear tightening opportunity. (Not a 3 because not every token earns its place; not a 2-below because nothing explains concepts Claude already knows.)	2 / 3
Actionability	Gives fully executable, copy-paste-ready guidance: a concrete Read invocation with the absolute path, path patterns like `{guides base}/{filename}`, and an `ls $AXIOM_XCODE_PATH/...` fallback command.	3 / 3
Workflow Clarity	The routing decision tree gives a clear sequenced decision flow, and the fallback section is an ordered escalation (sosumi.ai → WebFetch → suggest install) with an explicit reporting checkpoint ("Do not silently fail — tell the user which fallback you used").	3 / 3
Progressive Disclosure	No bundle files exist (references/scripts/assets absent), so it is scored on references: the body is an overview router/index with clearly signaled, one-level-deep pointers ("see axiom-tools/apple-docs-research.md", "see skills/apple-docs-research.md").	3 / 3
	Total	11 / 12 Passed

Description

100%

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 concrete, trigger-rich, and clearly scoped to the Apple/Xcode domain, answering both what it covers and when to use it. The "Use when..." trigger clause follows the accepted third-person/trigger pattern seen in the good examples.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities/topics — "Covers Liquid Glass, Swift 6.2 concurrency, Foundation Models, SwiftData, StoreKit, 32 Swift compiler diagnostics" — rather than vague abstraction.	3 / 3
Completeness	Explicitly answers both what ("Covers Liquid Glass, Swift 6.2 concurrency...") and when ("Use when ANY question involves Apple framework APIs, Swift compiler errors, or Xcode-bundled documentation").	3 / 3
Trigger Term Quality	Uses natural terms a user would say ("Apple framework APIs", "Swift compiler errors", "Xcode-bundled documentation") with good coverage and no opaque jargon.	3 / 3
Distinctiveness Conflict Risk	A clear Apple/Xcode-only niche with distinct triggers unlikely to fire for non-Apple skills.	3 / 3
	Total	12 / 12 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
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: CharlesWiltgen/Axiom
Path: .claude-plugin/plugins/axiom/skills/axiom-apple-docs/SKILL.md
Commit: ea3be7c

Reviewed: 1 day 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.