AB ai-domain-generator
AI-powered domain naming consultation — helps users go from a vague idea to a registrable domain name. Trigger when the user says things like "help me find a domain", "I need a domain for my project", "domain name ideas", "what should I name my startup", "I'm building an X and need a domain", "brand name suggestions", "naming ideas", or any variation where the user describes a project but doesn't have a specific keyword yet. Also trigger when the user says "I'm starting a coffee shop", "I'm building an AI writing tool" — any project description that implies they need a name. Do NOT trigger when the user already has a specific keyword and wants variations (use the domain-generator skill), or when a target domain is taken and they want alternatives (use the domain-name-advisor skill). This skill's entire point is to talk first, generate later.
As a process B 71/100 · Nearly there — weak spots: consistency, running it twice, 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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 71/100
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 9 mutating operations with no state check
- 40Consistency. Frontmatter name (ai-domain-generator) differs from the folder (domain-generator)
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 65Failures and branches. 3 branches
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 44 steps
- 100When it triggers. States when to use and when not to
- 100Execution cost. Instruction body is 3262 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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 853: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +5Description quotes 9 example trigger phrases
- +4Structure: 32 headings
- +3Step-by-step instructions: 44 items
- +3Output format is stated explicitly
- +4Has examples (6 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.