AC ui-design-tips
Apply practical UI/UX design principles to improve user interfaces, landing pages, web apps, and components. Use when asked to review, critique, or improve UI design; suggest design improvements for buttons, forms, headers, cards, menus, color usage, visual hierarchy, pricing pages, or any UI element; apply UX laws (Fitts's Law, Gutenberg Principle, Hick's Law, Jakob's Law, etc.); fix accessibility issues; design better onboarding, error messages, empty states, navigation, micro-interactions, or UX copy; or answer questions about UI/UX best practices. Covers visual hierarchy, CTA optimization, color usage, typography, whitespace, alignment, form design, mobile UX, dangerous actions, empty states, onboarding, UX writing, error handling, trust signals, conversion optimization, and more.
As a process C 54/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 54/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 11 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Steps. 110 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3642 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 27 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 795: enough signal without eating the budget
- +4Structure: 28 headings
- +3Step-by-step instructions: 110 items
- +4Has examples (8 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.