AB openclaw-medrates
Query US hospital price transparency data via the MedRates REST API. Search medical procedure prices, compare hospitals, filter by insurance plan and location. US HOSPITAL DATA ONLY — does not include non-US providers, independent imaging centers, ambulatory surgery centers (ASCs), clinics, or other freestanding facilities. For outpatient procedures (MRIs, CTs, minor surgeries), independent providers may offer lower prices than hospitals. Use when the user asks about US medical costs, hospital prices, procedure pricing, insurance rates, CPT/HCPCS codes, or healthcare cost comparison.
As a process B 70/100 · Nearly there — weak spots: inputs and preconditions, consistency, running it twice
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
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 70/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 7 mutating operations with no state check
- 40Consistency. Frontmatter name (openclaw-medrates) differs from the folder (medrates-fyi)
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 25 steps
- 100Failures and branches. 3 branches, has a failure section
- 100Execution cost. Instruction body is 2232 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)
- +2Single-language instructions
- +3Description length 590: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 25 items
- +3Output format is stated explicitly
- +4Has examples (3 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.