CtrlK
BlogDocsLog inGet started
Tessl Logo

axiom-audit-liquid-glass

Use when the user mentions Liquid Glass review, iOS 26 UI updates, toolbar improvements, or visual effect migration.

59

Quality

67%

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-audit-liquid-glass/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

The body is highly actionable with a clear, well-gated audit workflow and executable examples, but it is over-long for a single file with cross-phase redundancy and no progressive disclosure into reference files. Splitting the pattern catalog and recommendation examples into bundle files would improve both conciseness and progressive disclosure.

Suggestions

Move the seven Phase 2 detection patterns (with their recommendation code blocks) into a reference file, keeping SKILL.md as a phase overview that links to it.

Deduplicate grep patterns between Phase 1 mapping steps and Phase 2 detection — define each pattern once and reference it, or note that Phase 1 reuses Phase 2 searches.

Pull the Phase 3 completeness table and Phase 4 compound matrix into a single reference table to reduce re-treading of the same findings across phases.

DimensionReasoningScore

Conciseness

It avoids explaining concepts Claude already knows and stays action-oriented, but Phase 1's grep lists (Steps 1-5) duplicate Phase 2's search patterns, and Phase 3/4 re-tread Phase 2 findings, so it could be tightened.

2 / 3

Actionability

It supplies specific grep regex patterns and copy-paste-ready Swift recommendations with availability gates (e.g. the `if #available(iOS 26, *) { view.glassBackgroundEffect() } else { ... }` example), giving fully executable guidance.

3 / 3

Workflow Clarity

A clear five-phase sequence with explicit verification checkpoints ("use Read to verify the surrounding context", "Require evidence from the Phase 1 map") plus a false-positive checklist provides strong workflow guidance.

3 / 3

Progressive Disclosure

It is well-sectioned into phases and tables but remains a monolithic ~300-line file with detailed pattern catalogs and code examples that could be split into reference files; no internal bundle references exist.

2 / 3

Total

10

/

12

Passed

Description

57%

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 is a strong, distinctive trigger clause but functions almost entirely as a *when* statement, omitting the concrete actions the skill performs. Adding an explicit capability clause before the "Use when" trigger would lift specificity and completeness.

Suggestions

Lead with a concrete action clause, e.g. "Audits Liquid Glass adoption in iOS 26+ SwiftUI/UIKit codebases, identifying migration opportunities and completeness gaps." before the "Use when" trigger.

Expand trigger coverage with common variations users might actually say ("glass effect", "Liquid Glass migration", "translucency", "iOS 26 design language").

Mirror the good-example pattern: state 2-3 specific actions (detect legacy blur, recommend availability gates, flag glass-on-glass nesting) then the "Use when" clause.

DimensionReasoningScore

Specificity

The description names concrete domains ("Liquid Glass review", "iOS 26 UI updates", "toolbar improvements", "visual effect migration") but states no explicit actions the skill performs — the verbs (audit, detect, migrate) are absent.

2 / 3

Completeness

An explicit "Use when..." trigger clause is present (strong *when*), but the *what* is only weakly implied via the word "review" rather than stated as concrete capabilities, so it does not clearly answer both.

2 / 3

Trigger Term Quality

"Liquid Glass" and "iOS 26 UI updates" are natural terms a user would say, but the four-phrase set is narrow and omits common variations like "glass effect", "Liquid Glass migration", or "translucency".

2 / 3

Distinctiveness Conflict Risk

The Liquid Glass / iOS 26 niche is highly specific with distinct triggers unlikely to overlap with unrelated skills.

3 / 3

Total

9

/

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.