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

68%

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 ./.claude-plugin/plugins/axiom/skills/axiom-ai/SKILL.md

Quality

Content

47%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-structured router with clear navigation and strong workflow sequencing, but it is verbose (heavy redundancy across triage, decision tree, and example sections) and offers little executable guidance itself — it delegates nearly everything to referenced files.

Suggestions

Collapse the redundancy between AI Approach Triage, Training Path Boundaries, Decision Tree, and Example Invocations into a single canonical routing table; reference it from the others instead of restating.

Since this is a router, make that explicit up front ('This skill routes; detailed code lives in the linked files') so a reader doesn't expect executable examples here and judges the conciseness accordingly.

Trim the inlined Critical Patterns and Example Invocations sections, which restate routing already covered by the triage table and decision tree.

Dimension	Reasoning	Score
Conciseness	The 296-line body repeats the same routing decisions across AI Approach Triage, Training Path Boundaries, Routing Logic, Decision Tree, Critical Patterns, and Example Invocations — substantial redundancy that pads the token budget without adding new guidance.	2 / 5
Actionability	It is almost entirely a router pointing to other files with no executable code or commands; the few concrete bits (entitlement strings, error names) are reference fragments rather than runnable steps.	2 / 5
Workflow Clarity	Decision Tree and triage tables give a clear, ordered routing sequence with explicit boundary rules; no destructive/batch operation requires validation checkpoints, so the workflow is well-sequenced for a routing skill.	4 / 5
Progressive Disclosure	Content is appropriately split across clearly signaled one-level-deep skills/*.md references with a useful overview router; minor gaps are the large inlined anti-rationalization table and absence of a bundle directory to verify against.	4 / 5
	Total	12 / 20 Passed

Description

88%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 strong, trigger-rich description that explicitly covers both what the skill handles and when to invoke it, naming concrete Apple frameworks. It risks minor boundary overlap with adjacent ML/CoreML skills the router itself deflects to.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — Foundation Models, @Generable, LanguageModelSession, Tool protocol, eval suites, model-as-judge scoring, SpeechTranscriber, CoreML — giving comprehensive coverage of the skill's scope.	5 / 5
Completeness	Explicitly answers 'what' (covers enumerated frameworks) and 'when' ('Use when implementing, testing, or evaluating ANY Apple Intelligence, on-device AI, or speech-to-text feature') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural terms (Apple Intelligence, Foundation Models, speech-to-text) but some are SDK jargon (@Generable, LanguageModelSession) a user would less often say verbatim; a few common phrasings are absent.	4 / 5
Distinctiveness Conflict Risk	The Apple Intelligence niche is fairly distinct, but 'on-device AI' and 'CoreML' overlap with sibling ML/vision skills routed elsewhere, creating minor conflict risk at the boundary.	4 / 5
	Total	18 / 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
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: 4ae86a3

Reviewed: 5 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.