CtrlK
BlogDocsLog inGet started
Tessl Logo

axiom-audit-foundation-models

Use when the user mentions Foundation Models review, on-device AI audit, LanguageModelSession issues, @Generable checking, or Apple Intelligence integration review.

70

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

100%

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

The content is an exceptionally actionable, well-sequenced audit playbook that respects Claude's competence and bakes validation into every phase. Its only soft spot is progressive disclosure: detail that belongs in bundled reference files is referenced to external paths that aren't part of this skill's bundle.

Suggestions

Move the large OS27 migration table and the evaluations deep-dive into local reference files under references/ and link them one level deep, so the SKILL.md stays a lean overview.

Ensure referenced paths like foundation-models-ref.md resolve to files actually shipped in this skill's bundle (or mark them clearly as cross-skill pointers).

DimensionReasoningScore

Conciseness

The body is dense and assumes Claude's competence — it never explains what Foundation Models is or how the framework works, and every section contributes concrete patterns, grep terms, or fix code with no padding.

3 / 3

Actionability

Every pattern ships exact grep regexes, Read-verification instructions, and copy-paste-ready Swift fix examples, leaving no ambiguity about what to run or write.

3 / 3

Workflow Clarity

The five-phase sequence is explicit with validation checkpoints (mandatory tool use, verify-before-report, false-posititives section, cross-reference severity bumps) providing clear feedback loops for the audit process.

3 / 3

Progressive Disclosure

The body is well-organized into labeled phases, but it is a large single-file skill whose detailed references (e.g. 'axiom-ai (skills/foundation-models-ref.md)' migration table, evaluations guide) point to external skill files not present in this bundle rather than to local, one-level-deep bundle files.

2 / 3

Total

11

/

12

Passed

Description

72%

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 excels at trigger-term coverage and distinctiveness but its 'what does this do' half is implied rather than stated, capping completeness and specificity. A leading clause naming the concrete action (e.g., 'Detects Foundation Models / Apple Intelligence issues ...') would round it out.

Suggestions

Lead with an explicit action statement of what the skill does before the 'Use when ...' clause, e.g. 'Detects Foundation Models (Apple Intelligence) anti-patterns and completeness gaps. Use when ...'.

Add a few concrete capability verbs (audits, flags, cross-references) so the 'what' is stated, not just implied by the trigger list.

DimensionReasoningScore

Specificity

The description names the domain and specific API terms (LanguageModelSession issues, @Generable checking, on-device AI audit) but does not enumerate multiple concrete actions; it reads as a trigger list rather than a capability list.

2 / 3

Completeness

It has an explicit, strong 'when' clause ('Use when the user mentions ...') but the 'what' is only implied from the trigger list; there is no explicit statement of what the skill does (e.g., 'Detects and reports ... issues').

2 / 3

Trigger Term Quality

It covers natural terms a user would actually say — 'Foundation Models review', 'on-device AI audit', 'LanguageModelSession issues', '@Generable checking', 'Apple Intelligence integration review' — including both colloquial and API-specific phrasings.

3 / 3

Distinctiveness Conflict Risk

The niche is clearly Apple Foundation Models / Apple Intelligence with distinct, specialized triggers unlikely to fire for unrelated skills.

3 / 3

Total

10

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
CharlesWiltgen/Axiom
Reviewed

Table of Contents

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.