DC hotel-booking-ai
Hotel search, comparison, and booking with live room rates and real-time availability. Use for any hotel or accommodation request, including nearby hotels, recommendations, room details, prices, amenities, cancellation policies, rate verification, reservations, order management, and payment.
Hotel search, comparison, and booking with live room rates and real-time availability.
As a process C 62/100 · Has gaps — References files that are not bundled: {web_url}, {hotel_image_render_target}, {hotel_web_url}
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The skill tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.
Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 1
-
high Concealment
en-hide-from-userSKILL.md:305Instruction to hide actions from the user- Show a fee or tax note only when the API explicitly returns a fee, tax amount, or inclusion status, or when the user asks about taxes and fees. Do not notify the user that fee or tax data is absent,
Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 10459 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: {web_url} - warning
missing-refreference to a missing file: {hotel_image_render_target} - warning
missing-refreference to a missing file: {hotel_web_url} - warning
missing-refreference to a missing file: {basic_room_image}
Process rating: all ten parameters 62/100
- 0Tools and files. 4 referenced file(s) missing: {web_url}, {hotel_image_render_target}, {hotel_web_url}
- 30Running it twice. 25 mutating operations with no state check
- 40Execution cost. Instruction body is 10459 tokens: crowds the task out of the window
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 85Steps. 93 steps, 1 vague phrases
- 100Inputs and preconditions. Inputs and preconditions are listed
- 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 14 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 292: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 93 items
- +3Output format is stated explicitly
- +4Has examples (9 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: 70.