SKILLEMALL.ai

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.

ClawHub Agent Skills author: zhangxchao v1.0.1 MIT-0 6 files body ≈ 4 998 tokens Open the sourceclawhub.ai analyzed 4 d ago

As a process F 65/100 · Will not run — References files that are not bundled: {jumpUrl_A}, {jumpUrl_B}, {jumpUrl_C}

ProcedureInfrastructuretype and topics are labelled automatically from the skill text
JSON
Technical rating
B
83/100
safety, quality, tests
Safety 60%
100
Quality 40%
58
Run on models
none yet
Process rating
F
65/100
Will not run
References files that are not bundled: {jumpUrl_A}, {jumpUrl_B}, {jumpUrl_C}
Tools and files w 18
0
Running it twice w 4
30
Result and completion w 14
60
the three weakest of ten parameters · all ten

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The text references files that are not there: add them or drop the references.
For the model run — optional
  • 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-yaml SKILL.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-when description does not say WHEN to use the skill (no "use when")
  • warning missing-ref reference to a missing file: {jumpUrl_A}
  • warning missing-ref reference to a missing file: {jumpUrl_B}
  • warning missing-ref reference to a missing file: {jumpUrl_C}
  • warning missing-ref reference to a missing file: {jumpUrl}

Process rating: all ten parameters 65/100

Will not run. References files that are not bundled: {jumpUrl_A}, {jumpUrl_B}, {jumpUrl_C}
  • 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.

External checks

ClawHub: clean
This flight-comparison skill appears coherent and purpose-aligned, with disclosed local preference and history storage but no evidence of hidden execution, exfiltration, or destructive behavior.
LLM: benign (high) · VirusTotal: · 29 May 2026