BF super-flight
Multi-date flight price comparison assistant. Supports one-way multi-date (≤7 days) comparison via a two-stage flow — discover candidate flights, then lock 1–2 flights and run a date×price matrix. Binds hard constraints to personas (亲子/商务/学生/老人/蜜月 — family/business/student/senior/honeymoon), defaults sort order from historical orders, and provides explainable recommendations. Triggers on: 机票查询/多日期比价/拼假/周末比价/最便宜几天/同航班不同日价格/家庭出行机票/商务票比价/蜜月机票, flight search, multi-date price comparison, cheapest days, same flight across dates, family/business/honeymoon flight planning.
As a process F 65/100 · Will not run — References files that are not bundled: {jumpUrl_A}, {jumpUrl_B}, {jumpUrl_C}
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The text references files that are not there: add them or drop the references.
- 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: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Multi-date flight price comparison assistant. Supports one-way mul… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value - warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
missing-refreference to a missing file: {jumpUrl_A} - warning
missing-refreference to a missing file: {jumpUrl_B} - warning
missing-refreference to a missing file: {jumpUrl_C} - warning
missing-refreference to a missing file: {jumpUrl}
Process rating: all ten parameters 65/100
- 0Tools and files. 4 referenced file(s) missing: {jumpUrl_A}, {jumpUrl_B}, {jumpUrl_C}
- 30Running it twice. 5 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4998 tokens
- 100Steps. 44 steps
- 100Failures and branches. 9 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 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
- +4Description does not say when NOT to use the skill (false activations)
- +2Single-language instructions
- +3Description length 572: enough signal without eating the budget
- +4Structure: 29 headings
- +3Step-by-step instructions: 44 items
- +3Output format is stated explicitly
- +4Has examples (15 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 58.