BB Flight
Searches, compares, books, and fixes flights — fares and fare rules, connections, baggage, seats, miles, delays, and passenger rights. Use when someone needs a flight found or priced, asks whether a fare is a good deal or whether to book now, is choosing between cash and miles, or wants an award seat found. Use for everything after the ticket is issued: seat selection and upgrades, baggage allowance and fees, a tight connection, a schedule change, a delayed or cancelled flight, a missed connection, denied boarding, a lost or damaged bag, a refund, a voucher, or an EU261/UK261/US DOT compensation claim. Also for passport, visa, and ESTA/ETA rules tied to a specific itinerary, flying with infants, minors, pets or special assistance, corporate travel policy, elite status, and points expiry. Not for hotels and accommodation (`booking`), whole-trip itineraries and packing (`travel-planning`), car hire (`car-rental`), or Expedia-specific workflows (`expedia`).
As a process B 69/100 · Nearly there — weak spots: inputs and preconditions, 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: 19. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
body-longSKILL.md body ≈ 6657 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "changelog"
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
- 60Tools and files. Uses tools (bash, read) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Failures and branches. 5 branches
- 70Execution cost. Instruction body is 6657 tokens
- 100Steps. 47 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 top-level sections: this looks like several domains in one skill
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
- +3Description length 968: 120–800 characters recommended
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 13 headings
- +3Step-by-step instructions: 47 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.