BA competitor-experience-audit
Audit the brand, UX, and site design of the leading sites in a vertical as a set of observable cross-site patterns, producing the experience bar a new build must meet or beat. Use this skill whenever the user wants to assess the competitive design field, capture vertical conventions, identify the design and UX bar of a category, or set the experience standard before a build. Triggers on competitor experience audit, UX audit, site design audit, brand audit, design conventions, what makes these sites good, vertical conventions, storefront patterns, merchandising patterns, layout density, primary task, design bar, category conventions, retail vs marketing register, what does the field do. Also triggers when an audit of the competitive field has captured technical signals (SEO, accessibility) but never named the brand, UX, or design conventions, and the build downstream will read as off-vertical without that bar.
Audit the brand, UX, and site design of the leading sites in a vertical as a set of observable cross-site patterns, producing the experience bar a new build…
As a process A 80/100 · Runs to the end — weak spots: running it twice, progress reporting
The same skill appears in 2 more places: claude-skills, claude-skills
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: 4. 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 80/100
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 60 steps, 2 vague phrases
- 100Tools and files. No external tools needed
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3336 tokens
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)
- +3Description length 922: 120–800 characters recommended
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Structure: 19 headings
- +3Step-by-step instructions: 60 items
- +3Output format is stated explicitly
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.