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

78%

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 ./axiom-codex/skills/axiom-ai/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.

A well-structured router skill with excellent progressive disclosure and concrete, actionable routing. Its main weakness is redundancy across overlapping routing sections (Decision Tree, Example Invocations, Critical Patterns) that inflates token cost without adding guidance.

Suggestions

Collapse the Decision Tree, Example Invocations, and Critical Patterns sections — they restate the same routes — keeping one canonical routing list and trimming the rest.

Remove or merge the thin 'Critical Patterns' section, which re-lists foundation-models and foundation-models-diag capabilities already covered in Routing Logic.

Tighten the 'When to Use' list since the AI Approach Triage table already enumerates the same triggering intents more usefully.

Dimension	Reasoning	Score
Conciseness	Mostly efficient domain-specific routing content, but several sections overlap heavily — Decision Tree, Example Invocations, Critical Patterns, and When to Use all restate the same routing — adding padding that could be tightened.	3 / 5
Actionability	Routes are concrete with specific file paths, skill names, and slash-commands ("/skill axiom-vision", "Read skills/foundation-models-diag.md"), giving mostly executable guidance for a router skill, though referenced files live outside this bundle and cannot be verified here.	4 / 5
Workflow Clarity	The 13-step Decision Tree and the Triage/Training-Path tables provide a clear, sequenced routing workflow; no validation checkpoints are needed for non-destructive routing, so this sits at clear-sequence-with-minor-gaps rather than the top anchor.	4 / 5
Progressive Disclosure	A clear router overview with well-signaled, one-level-deep references (skills/*.md) organized into triage tables and bullet lists, splitting detailed content appropriately into separate files for easy navigation.	5 / 5
	Total	16 / 20 Passed

Description

85%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, explicit description with concrete actions, good trigger terms, and clear what/when guidance. Its main weakness is over-broad scope (CoreML, speech-to-text) that overlaps with dedicated sibling skills.

Dimension	Reasoning	Score
Specificity	Names three concrete actions ("implementing, testing, or evaluating") and a comprehensive list of specific technologies (Foundation Models, @Generable, LanguageModelSession, Tool protocol, eval suites, model-as-judge scoring, SpeechTranscriber, CoreML), matching the comprehensive-coverage anchor.	5 / 5
Completeness	Explicitly answers both what ("Covers Foundation Models, @Generable, ...") and when ("Use when implementing, testing, or evaluating ANY Apple Intelligence, on-device AI, or speech-to-text feature") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Strong natural-term coverage including synonyms (Apple Intelligence, on-device AI, Foundation Models, speech-to-text, eval suites, model-as-judge), but lacks file-extension-style triggers and a few common phrasings, sitting just below the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	It has a clear Apple Intelligence niche, but the broad "ANY" scope and explicit inclusion of CoreML and speech-to-text overlaps with sibling skills (ios-ml.md, core-ai.md) that the body itself deflects to, creating real overlap risk.	3 / 5
	Total	17 / 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: axiom-codex/skills/axiom-ai/SKILL.md
Commit: 28c2f56

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.