AB keyword-intel
Map available evidence around a known keyword in the domain market, keeping search-audience, advertiser, new-registration open-market participation, supply and active offers, and completed transactions as distinct layers. Treat .com participation as necessary but not sufficient confirmation of open-market registration interest, and never merge the layers into one demand score or investment verdict. Use when a user wants a deep evidence picture for one known keyword. Not for analyzing a specific domain (use domain-analyze), browsing trends (use keyword-trend-hunter), or a market overview (use domain-market-beat).
Map available evidence around a known keyword in the domain market, keeping search-audience, advertiser, new-registration open-market participation, supply…
As a process B 75/100 · Nearly there — weak spots: consistency, 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 ≈ 5011 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 75/100
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 8 mutating operations with no state check
- 40Consistency. Frontmatter name (keyword-intel) differs from the folder (domain-intel)
- 50When it triggers. No condition that starts the skill
- 55Failures and branches. 1 branches
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 5011 tokens
- 100Tools and files. No external tools needed
- 100Steps. 65 steps
- 100Result and completion. Output format and completion criterion are stated
- 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
- +5Description has no quoted example phrases that should trigger the skill
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 619: enough signal without eating the budget
- +4Structure: 7 headings
- +3Step-by-step instructions: 65 items
- +3Output format is stated explicitly
- +4Has examples (0 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.