CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

axiom-audit-touch

Use when the user mentions touch support on the Mac, touchscreen MacBook readiness, Sidecar touch, mouseDown or tracking-loop migration, or wants to audit a macOS app for touch.

Quality

85%

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

88%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 unusually dense, operational audit prompt: exact grep patterns, 18 concrete anti-patterns with specific API-level fixes, explicit validation checkpoints, and clearly signaled cross-references to sibling skills. Its only costs are length (the full catalog lives inline in SKILL.md) and minor redundancy between the pattern list, the grep sections, and the closing Scope section.

DimensionReasoningScore

Conciseness

The body is dense operational content — exact greps, Pattern/Issue/Fix triples, a false-positive list — with almost no explanation of concepts Claude already knows; only minor trimming is possible, e.g. the closing Scope section re-lists the pattern catalog and the NSControl class list repeats across two grep sections.

4 / 5

Actionability

Guidance is fully executable: copy-paste Glob/Grep patterns with regexes ('class [A-Za-z0-9_]+ *: *NS(Button|Slider|Control|...)'), exact API fixes ('addTarget(_:action:for:)' with '.trackingCancelled'), and exact defaults keys ('NSCrashOnStuckGestureTimeout') cover the common cases; for an instruction-only audit skill this is maximally concrete.

5 / 5

Workflow Clarity

Phases 1–5 are clearly sequenced with explicit validation checkpoints: 'Present this map before proceeding', 'For every grep match, Read the surrounding context before reporting', and 'verify the translation against a known-positive string before trusting empty results', plus a False Positives section that filters findings.

5 / 5

Progressive Disclosure

Section headers are clear and cross-skill references are one level deep and clearly signaled ('axiom-macos (skills/touch.md, Recipe 6)', 'axiom-games (skills/game-input.md, Section 9)'), but the entire 18-pattern detection catalog is inlined in SKILL.md rather than split into a reference file — a minor organization gap.

4 / 5

Total

18

/

20

Passed

Description

73%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 highly targeted, third-person trigger description with explicit 'Use when...' guidance and minimal conflict risk, weakened only by a thin capability statement: it says precisely when to fire but little about what the audit does or covers.

Suggestions

State 2–3 concrete capabilities before the trigger clause, e.g. 'Scans AppKit, SwiftUI, and Mac Catalyst code for touch-readiness anti-patterns (custom recognizers that never finish, tracking loops, control-subclass mouse overrides, shipped debug gesture defaults) and ranks findings by severity' — this would raise specificity and make the 'what' fully explicit.

Add one or two common trigger synonyms such as 'multi-touch', 'gesture recognizers', or 'is my app touch-ready' to broaden natural keyword coverage.

DimensionReasoningScore

Specificity

The only capability stated is 'wants to audit a macOS app for touch' — a single concrete action in a named domain (macOS touch readiness), matching the anchor for 1–2 concrete actions without comprehensive coverage; it lists neither several specific actions (4) nor purely generic language (2).

3 / 5

Completeness

The 'when' is explicit with concrete trigger phrases ('Use when the user mentions...'), and a 'what' exists ('audit a macOS app for touch'), but the what is thin — it never states what the audit covers or produces — so it falls just below the anchor that clearly and fully answers both.

4 / 5

Trigger Term Quality

Triggers like 'touch support on the Mac', 'touchscreen MacBook readiness', 'Sidecar touch', and 'mouseDown or tracking-loop migration' are natural user phrases, but common variations such as 'multi-touch', 'gesture recognizers', or 'is my app touch-ready' are missing, so coverage is good rather than comprehensive.

4 / 5

Distinctiveness Conflict Risk

The niche is unambiguous — auditing macOS apps for touch readiness, with distinctive triggers like 'Sidecar touch' and 'tracking-loop migration' — giving it a clear lane with minimal conflict risk against generic audit or document skills.

5 / 5

Total

16

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

CharlesWiltgen/Axiom

Path

axiom-codex/skills/axiom-audit-touch/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.