AB ui-doctor
Audits an existing app's UI for consistency and layout/state-sync bugs (e.g. a sidebar that collapses but siblings don't adjust, or icons disappearing entirely instead of just their labels), responsive breakpoint failures, accessibility gaps, performance issues, and — for chat/workspace apps — message bubble, markdown/table/code-block rendering, and input control quality — then fixes them in code with evidence-based verification (not assumed-working fixes). Always verifies the project's actual installed library versions against current official docs, and checks for build/dev-server cache staleness before re-diagnosing a fix that "didn't work." Trigger when the user reports UI that "looks off," components out of sync, layout breaking at certain sizes, a fix that doesn't seem to have taken effect, or asks for a UI audit/review/health-check. For designing a new system from scratch, use `design-system-architect` instead (this skill uses its state-matrix/token definitions as audit criteria when present).
Audits an existing app's UI for consistency and layout/state-sync bugs (e.g. a sidebar that collapses but siblings don't adjust, or icons disappearing…
As a process B 73/100 · Nearly there — weak spots: result and completion, progress reporting
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 73/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 55Failures and branches. 1 branches
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 10 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1941 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1014: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +4Structure: 11 headings
- +3Step-by-step instructions: 10 items
- +4Reference files are cited in the instructions (5 of 5)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.