AC hk-bus-eta
Query Hong Kong bus ETA/stop data and MTR heavy rail ETA from natural-language transport questions using official KMB/LWB, Citybus, and MTR open-data endpoints. Use when the user asks in Cantonese, Chinese, or English things like「74X 幾多分鐘後喺九龍灣有車」「A41 去機場而家幾時到青衣站」「城巴 20 喺啟德幾耐到」「火炭站去金鐘方向幾點有車」「金鐘去北角下一班港島線幾時」or any message that combines a bus route with a stop/place, or an MTR station with a destination/direction/ETA intent.
Query Hong Kong bus ETA/stop data and MTR heavy rail ETA from natural-language transport questions using official KMB/LWB, Citybus, and MTR open-data endpoints.
As a process C 59/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
The same skill appears in 1 more place: ClawHub
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 · 0
✓ No critical or high findings
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
edit-residuethe text marks something as outdated (lines 12): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 59/100
- 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
- 40Consistency. Frontmatter name (hk-bus-eta) differs from the folder (hk-transit-eta)
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 85Steps. 45 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 4 branches, has a failure section
- 100Execution cost. Instruction body is 1517 tokens
- 100Running it twice. No mutating operations
- low The response is described with custom markup (4 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 424: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 45 items
- +4Has examples (6 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.