axiom-design

Use when making design decisions, implementing HIG patterns, Liquid Glass, SF Symbols, typography, or structuring app entry points and authentication flows.

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 ./.claude-plugin/plugins/axiom/skills/axiom-design/SKILL.md

Quality

Content

85%

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 that gives concrete, navigable routing with clear decision logic and conflict precedence. Its main weakness is redundancy: the same routing table is duplicated across four sections, which costs tokens without adding clarity.

Suggestions

Collapse the duplicated routing into a single authoritative map (e.g. keep the Quick Reference table and the decision tree, but drop the redundant restatement in Critical Patterns and Example Invocations, or merge them).

If Example Invocations are retained, trim them to a few representative cases that illustrate ambiguous routing rather than re-listing every file.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's intelligence (it never explains what HIG or SF Symbols are), but the same task-to-file routing is restated four times — as a dot graph, a numbered list, the Critical Patterns section, and Example Invocations — which is padding that could be tightened.	2 / 3
Actionability	Routing is concrete and copy-paste ready: exact paths like "Read `skills/hig.md`", specific `/skill axiom-swiftui` invocations, and a decision tree that maps each symptom to a file, which is fully actionable for an instruction-only router skill.	3 / 3
Workflow Clarity	The decision tree and numbered list give an explicit, sequenced routing procedure, and the Conflict Resolution section supplies clear precedence rules ("Use design FIRST — then use swiftui"); no validation checkpoints are needed because the skill performs no destructive or batch operations.	3 / 3
Progressive Disclosure	SKILL.md is a lean overview/router pointing one level deep to clearly signaled detail files via the Quick Reference table and decision tree, matching the progressive-disclosure ideal; no bundle files are provided to score against, so structure is judged on the declared references.	3 / 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.

A well-targeted, trigger-rich description for a distinct Apple design skill, but it omits a separate third-person capability statement, leaving the "what" implicit and incurring a voice penalty. Adding a leading capability clause would lift both specificity and completeness.

Suggestions

Lead with a third-person capability clause, e.g. "Applies Apple HIG, Liquid Glass, SF Symbols, and typography guidance to design decisions and app composition.", then keep the "Use when..." trigger.

Make the "what" explicit and distinct from the "when" so the description clearly answers both questions rather than merging them into one trigger clause.

Dimension	Reasoning	Score
Specificity	The description names several concrete domains ("implementing HIG patterns, Liquid Glass, SF Symbols, typography, or structuring app entry points and authentication flows"), which is specific, but the entire clause is framed as the second-person imperative "Use when making..." with no third-person capability statement, triggering the voice penalty that reduces specificity by one.	2 / 3
Completeness	The "when" is explicit ("Use when making design decisions..."), but the "what does this do" is only implied through that trigger clause; there is no distinct third-person capability statement, so what and when are merged rather than both clearly answered.	2 / 3
Trigger Term Quality	It surfaces natural terms an Apple-platform user would actually say — "Liquid Glass", "SF Symbols", "HIG patterns", "typography", "authentication flows" — giving strong coverage of the likely trigger vocabulary.	3 / 3
Distinctiveness Conflict Risk	The niche is sharply defined around Apple HIG, Liquid Glass, SF Symbols, and app composition, with triggers specific enough to be unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 12 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: .claude-plugin/plugins/axiom/skills/axiom-design/SKILL.md
Commit: ea3be7c

Reviewed: 1 day 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.