CtrlK
BlogDocsLog inGet started
Tessl Logo

ui-ux-pro-max

UI/UX design intelligence with searchable database

48

Quality

51%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.codex/skills/ui-ux-pro-max/SKILL.md

The canonical home for this skill is ui-ux-pro-max in Draculabo/AntigravityManager

SKILL.md
Quality
Evals
Security

Quality

Content

67%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.

The body is a strong, actionable workflow guide: concrete commands, a required-first-step design-system flow, worked examples, and a pre-delivery checklist. Its main weaknesses are padded sections teaching things Claude already knows (Python installation, generic Tailwind rules) and unvalidated assumptions in command paths and referenced data files.

Suggestions

Cut the multi-OS Python installation section and trim the Common Rules tables to only non-obvious rules, deduplicating them against the Pre-Delivery Checklist.

Use a path relative to the skill directory (e.g., scripts/search.py) in commands instead of the hardcoded 'skills/ui-ux-pro-max/scripts/search.py', and verify 'ui-reasoning.csv' is actually shipped in the bundle.

Add a short verification step after persisting a design system (e.g., confirm design-system/MASTER.md and the page override exist and page rules override the Master) to close the workflow's validation gap.

DimensionReasoningScore

Conciseness

The command examples and domain/stack tables are efficient, but the multi-OS Python installation instructions and the generic Tailwind hover/contrast/cursor-pointer rules (e.g., "Add cursor-pointer to all clickable cards", "Use #0F172A for text") explain things Claude already knows, and the Pre-Delivery Checklist largely duplicates the Common Rules tables. This matches 'mostly efficient but includes some unnecessary explanation'.

3 / 5

Actionability

Commands are concrete and copy-paste ready with a realistic worked example ("beauty spa wellness service" --design-system -p "Serenity Spa") and documented flags/output formats. Minor gaps keep it from a 5: commands hardcode 'skills/ui-ux-pro-max/scripts/search.py' rather than a path relative to the skill directory, and 'ui-reasoning.csv' is referenced but not shipped in the bundle.

4 / 5

Workflow Clarity

The four-step workflow (analyze → design system required → supplement → stack) is clearly sequenced and reinforced by a full example workflow, with iterate-on-no-match guidance and a pre-delivery checklist as a final checkpoint. It falls short of a 5 because intermediate outputs (e.g., persisted MASTER.md/page overrides) have no verification steps — the checklist only validates the final UI code.

4 / 5

Progressive Disclosure

The body is well-sectioned and script usage is surfaced through executable commands rather than buried references; the inlined domain/stack tables directly support search usage. Minor gaps: the ~80 lines of Common Rules and checklist content could live in a reference file, and 'ui-reasoning.csv' is mentioned without existing in the provided bundle.

4 / 5

Total

15

/

20

Passed

Description

36%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.

The description is too vague to serve its purpose: it names the UI/UX design domain but gives no concrete capabilities and, critically, no 'when to use' trigger guidance. Users asking for landing pages, color palettes, or font pairings would not reliably surface this skill from this description alone.

Suggestions

Add concrete actions to the description, e.g., 'Recommends UI styles, color palettes, font pairings, UX guidelines, and chart types for web and mobile apps from a searchable database.'

Add an explicit trigger clause, e.g., 'Use when designing or building UI, creating landing pages, picking colors or fonts, or reviewing UI for accessibility and polish.'

Include natural keyword variations users actually say (landing page, dashboard, dark mode, typography, glassmorphism, Tailwind) to improve trigger matching and distinctiveness from general design skills.

DimensionReasoningScore

Specificity

"UI/UX design intelligence" names the domain but "design intelligence" is abstract and "with searchable database" is not a concrete action, matching the anchor for minimal/generic actions. It is not a 3 because no specific action verbs (e.g., recommends styles, generates palettes) appear.

2 / 5

Completeness

The 'what' is vague ("design intelligence with searchable database") and the 'when' is entirely absent — no 'Use when...' or equivalent trigger guidance, matching the anchor for vague 'what' and no 'when'. It cannot be a 3 because the 'what' is not clearly stated either.

2 / 5

Trigger Term Quality

"UI/UX" and "design" are natural terms a user would say, but common variations users actually use (landing page, color palette, fonts, dark mode, dashboard, styling) are all missing. This sits at 'some relevant keywords but missing common variations', above the generic one-or-two-keyword level.

3 / 5

Distinctiveness Conflict Risk

"UI/UX design" marks a recognizable niche but the description could still overlap with other design, styling, or branding skills that trigger on 'design'. It lacks the distinct trigger phrases needed for a 4 or 5.

3 / 5

Total

10

/

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
Draculabo/AntigravityManager
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.