AC design-guide
Frontend design and production engineering orchestrator that inventories projects, scales design depth, presents review artifacts, locks executable contracts, implements accessible responsive interfaces, and verifies interactions, visual regressions, and performance. Use when the user invokes design-guide, @design-guide, /design-guide, asks for frontend design/development/redesign, web app UI, dashboard, tool interface, landing page, responsive React/HTML/CSS work, design previews or choices, screenshot QA, production frontend quality, or says they are dissatisfied with generic AI-looking UI. If invoked without a concrete task, enter navigation mode and recommend the best available frontend-related skills/tools for the user's environment instead of coding.
Frontend design and production engineering orchestrator that inventories projects, scales design depth, presents review artifacts, locks executable contracts…
As a process C 60/100 · 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: 51. 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 60/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 4 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70Execution cost. Instruction body is 4781 tokens
- 85Steps. 105 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
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
- -5TODO / placeholder text left in the skill
- -2localhost URLs: will not work for another user
- -38 of 15 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +3Description length 766: enough signal without eating the budget
- +4Structure: 23 headings
- +3Step-by-step instructions: 105 items
- +4Has examples (7 code blocks)
- +4Reference files are cited in the instructions (15 of 18)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.