AB cm-etsy-listing-optimizer
Audit and optimize Etsy listings for SEO, conversion, and shop placement. Reviews titles, tags, descriptions, photos, attributes, pricing, and shipping to improve search rank and sales for handmade, print-on-demand, and digital download sellers. Use when asked to optimize an Etsy listing, audit an Etsy shop, fix Etsy SEO, write Etsy titles or tags, improve Etsy conversion, set up Etsy ads, or grow an Etsy store. Triggers on "Etsy SEO", "Etsy listing", "Etsy tags", "Etsy title", "Etsy shop audit", "Etsy ads", "Star Seller", "print on demand Etsy", "digital download Etsy", "Etsy conversion", "Etsy keyword research".
As a process B 74/100 · Nearly there — weak spots: inputs and preconditions, running it twice, progress reporting
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 7003 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 74/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 8 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 70Failures and branches. 5 branches
- 70Execution cost. Instruction body is 7003 tokens
- 100Tools and files. No external tools needed
- 100Steps. 105 steps
- 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
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +5Description quotes 11 example trigger phrases
- +3Description length 621: enough signal without eating the budget
- +4Structure: 29 headings
- +3Step-by-step instructions: 105 items
- +3Output format is stated explicitly
- +4Has examples (7 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.