CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

axiom-macos

Use when building ANY macOS app — windows, menus, sandboxing, distribution, AppKit bridging or modernization (control events, state restoration, concentric corners), touch input, or macOS-specific SwiftUI patterns.

Quality

80%

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

Fix and improve this skill with Tessl

tessl review fix ./axiom-codex/skills/axiom-macos/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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.

An exemplary router-style SKILL.md: lean, symptom-indexed, with all detail correctly deferred to clearly signaled one-level-deep references and explicit conflict-resolution rules for overlapping suites. The remaining gains are small — de-duplicating the decision tree and specifying how to invoke the touch auditor.

Suggestions

Trim duplication: the dot decision tree repeats the Quick Reference table row-for-row — keep one, or reduce the tree to the ambiguous cases the table handles poorly.

Specify how to invoke `axiom-audit-touch` (exact command or skill-invocation syntax) instead of only listing it as "Available".

DimensionReasoningScore

Conciseness

The body is a dense symptom-to-file routing table plus conflict rules that assumes Claude's competence and explains nothing it already knows. Minor trims remain: the dot decision tree largely duplicates the Quick Reference table, and "You MUST use this skill for ANY macOS-specific development…" restates the frontmatter description.

4 / 5

Actionability

Mostly concrete routing — e.g. "Another team's app or app group container access denied without a prompt (`OS27`)" maps to an exact file, and rows like "See `skills/sandbox-and-file-access.md`" give unambiguous pointers. The gap keeping it from a 5 is the auditor block, which only says "Available: `axiom-audit-touch`" without specifying how to invoke it.

4 / 5

Workflow Clarity

The Decision Tree provides a clear branching sequence and the Conflict Resolution section gives explicit tie-break rules ("Use axiom-macos for macOS-only concerns… Use axiom-swiftui for cross-platform SwiftUI"). No validation checkpoints exist, though none are needed for a read-only router, and the auditor invocation is underspecified — so it sits at 4 rather than 5.

4 / 5

Progressive Disclosure

The body is a pure overview: every detailed topic sits behind a clearly signaled, one-level-deep reference ("See `skills/windows.md`", "See `skills/direct-distribution.md`", cross-suite routes labeled by suite), and nothing that belongs in a separate file is inlined. Navigation via the symptom table, cross-suite routes, and decision tree is easy.

5 / 5

Total

17

/

20

Passed

Description

75%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 signals when to use the skill and covers the macOS domain with specific, well-chosen terms. Its main weakness is that capabilities are expressed as topic areas rather than concrete actions, leaving the 'what' partially implicit.

Suggestions

State the 'what' as concrete actions rather than only topic areas, e.g. "Guides windows, menus, sandboxing, distribution, and AppKit bridging work in macOS apps" so both halves of the what/when pair are explicit.

Add a few high-frequency trigger synonyms users actually say — "notarization", "Mac app", "menu bar", "Catalyst" — to broaden natural-term coverage.

DimensionReasoningScore

Specificity

Lists several specific areas — "windows, menus, sandboxing, distribution, AppKit bridging or modernization (control events, state restoration, concentric corners), touch input" — with only minor gaps (e.g., notarization and Catalyst are absent). It stops short of a 5 because capabilities are phrased as topic areas rather than concrete actions like "extract" or "fill forms".

4 / 5

Completeness

"Use when building ANY macOS app" is an explicit and specific when-clause, and the enumerated topic list conveys scope. It is not a 5 because the 'what' is implied by the topic list rather than explicitly stated as concrete actions or deliverables.

4 / 5

Trigger Term Quality

Natural terms users would say are well covered: "macOS app", "windows", "menus", "sandboxing", "AppKit", "touch input", "SwiftUI". A few common variations are missing ("notarize", "Mac app", "menu bar", "Catalyst"), keeping it below the comprehensive synonym coverage of a 5.

4 / 5

Distinctiveness Conflict Risk

"macOS-specific SwiftUI patterns" plus AppKit/sandbox/distribution terms carve a clear niche distinct from sibling suites. The breadth of "ANY macOS app" creates minor overlap risk with closely related skills like axiom-swiftui, so it does not reach the minimal-conflict clarity of a 5.

4 / 5

Total

16

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

CharlesWiltgen/Axiom

Path

axiom-codex/skills/axiom-macos/SKILL.md

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.