AC ui-craft-pro
Design, refine, and implement better UI for websites, dashboards, apps, landing pages, and components by using a local design knowledge base plus a code-first implementation workflow. Use when the goal is not just to get style ideas, but to turn a chosen visual direction into real interface code that looks more polished, more intentional, and less like generic AI UI. Especially useful for choosing styles, colors, typography, layout patterns, UX guidelines, chart types, generating a project-specific design system, and then coding the UI to match that system.
As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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: 31. 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 51/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70Failures and branches. 15 branches
- 85Steps. 98 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2091 tokens
- 100Running it twice. No mutating operations
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 563: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 98 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (3 of 6)
- +3All 4 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.