AB korea-domestic-flights
Search, compare, and monitor 대한민국 domestic flights using a Playwright-backed airfare workflow. Use when the user wants 한국 국내선 항공권 최저가 조회, 김포-제주/부산-제주 같은 노선 비교, 편도/왕복 검색, 날짜 범위 최저가 탐색, 여러 국내 목적지 비교, 시간대 선호(늦은 출발/늦은 복귀) 반영, 국내선 운임 브리핑, 목적지+날짜 범위 최적 조합 탐색, or 목표가 이하 가격 감시/가격 알림 저장·점검. Accept common Korean airport names like 김포, 제주, 부산, 청주 and natural-language dates like 오늘/내일/모레/이번주말/내일부터 3일. Prefer this skill for Korean domestic airfare tasks; do not use it for international flights.
As a process B 70/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Dangerous commands
cmd-execpolicy-bypassreferences/price-alerts-schema.md:183Runs PowerShell with execution policy bypassedpowershell -ExecutionPolicy Bypass -File skills/korea-domestic-flights/scripts/regi…ps1 -IntervalMinutes 30
Files scanned: 16. 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
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 100Tools and files. No external tools needed
- 100Steps. 113 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 4 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2758 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
- +3Output format is not stated: the model decides each time
- -32 of 10 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 486: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 113 items
- +4Has examples (25 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.