axiom-ai

Use when implementing, testing, or evaluating ANY Apple Intelligence, on-device AI, or speech-to-text feature. Covers Foundation Models, @Generable, LanguageModelSession, Tool protocol, eval suites, model-as-judge scoring, SpeechTranscriber, CoreML.

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.

The body is a well-structured router with clear, actionable navigation and good progressive disclosure, but it carries redundant routing sections that inflate the token budget. Tightening the overlapping routing/triage/decision-tree/example-invocation sections would improve token efficiency.

Suggestions

Consolidate the overlapping routing sections ("When to Use", "AI Approach Triage", "Routing Logic", "Decision Tree", and "Example Invocations") into a single triage table plus a decision tree, removing repeated route-to-file listings.

Drop or merge the thin "Critical Patterns" summary section, since it restates capabilities already enumerated under "Foundation Models Work" and the anti-rationalization guidance.

Trim the "Example Invocations" list to a few representative cases or fold it into the Decision Tree, as most entries duplicate the tree's routing logic.

Dimension	Reasoning	Score
Conciseness	Routing guidance is repeated across "When to Use", "AI Approach Triage", "Routing Logic", "Decision Tree", "Example Invocations", and a thin "Critical Patterns" summary, so the body could be tightened despite containing no concept-padding. It is not a 3 because the overlapping routing sections mean not every token earns its place, and not a 1 because it avoids explaining concepts Claude already knows.	2 / 3
Actionability	Concrete file pointers (e.g. `skills/foundation-models.md`), a numbered decision tree, and user-phrase-to-file mappings give specific, actionable routing guidance. It is not a 2 because the routing is concrete and complete rather than abstract or pseudocode-level.	3 / 3
Workflow Clarity	The numbered Decision Tree (steps 1-13) and Cross-Domain Routing section provide a clear, sequenced triage workflow. It is not a 2 because the sequence is explicit and complete; this router performs no destructive/batch operations that would require validation feedback loops.	3 / 3
Progressive Disclosure	The SKILL.md is an overview with well-signaled, one-level-deep references to detailed sibling files, with no nested reference chains. It is not a 2 because references are clearly labeled and the split is appropriate for a router skill.	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 strong: it pairs an explicit 'Use when' trigger with a concrete technology list in third-person voice, answering both what and when. It is concise, specific, and unlikely to conflict with other skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("implementing, testing, or evaluating") alongside a comprehensive set of specific technologies (Foundation Models, @Generable, LanguageModelSession, Tool protocol, eval suites, model-as-judge scoring, SpeechTranscriber, CoreML), matching the level-3 anchor. It is not a 2 because the action and technology coverage is comprehensive rather than partial.	3 / 3
Completeness	Explicitly answers both when ("Use when implementing, testing, or evaluating ANY Apple Intelligence, on-device AI, or speech-to-text feature") and what ("Covers Foundation Models, @Generable, ..."). It is not a 2 because the trigger guidance is explicit, not merely implied.	3 / 3
Trigger Term Quality	Includes natural terms users would actually say ("Apple Intelligence", "on-device AI", "speech-to-text", "Foundation Models") with good coverage of common variations. It is not a 2 because it covers multiple natural phrasings rather than a single keyword.	3 / 3
Distinctiveness Conflict Risk	The Apple-specific framing (Apple Intelligence, Foundation Models, @Generable) carves a clear niche unlikely to trigger the wrong skill. It is not a 2 because the Apple-scoped triggers are distinct rather than broadly overlapping.	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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

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

Reviewed: 2 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.