AB mfds-cli
Korean Ministry of Food and Drug Safety (식품의약품안전처) public API CLI. Search drug product permissions (의약품 허가정보), consumer-friendly drug info (e약은요), DUR contraindications (병용금기/특정연령금기/임부금기/효능군중복), and drug recall/sale-stop alerts. Returns clean JSONL for AI agents. Use for pharmacy AI, medication-safety bots, prescription review, supplement diligence, and Korean healthcare data pipelines. Requires a free MFDS_API_KEY from data.go.kr.
As a process B 69/100 · Nearly there — weak spots: when it triggers, inputs and preconditions, 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 · 2
✓ No critical or high findings
Medium and low: 2
-
low Secrets in code
secret-high-entropy-tokenbin/dur.sh:40High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)age) SUB="getS…t03" ;;
quoted -
low Secrets in code
secret-high-entropy-tokenbin/dur.sh:46High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)extended-release) SUB="getS…t03" ;;
quoted
Files scanned: 12. 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 69/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 4 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 100Tools and files. No external tools needed
- 100Steps. 16 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1382 tokens
- low The response is described with custom markup (14 tags): a typed call is more reliable
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 435: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 16 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.