AC travel-agent
Personal travel planning assistant. Requires a SerpAPI key (stored in ~/.serpapi_credentials). Searches real flights and hotels via Google (SerpAPI), checks the user's calendar, and builds fully costed itinerary options — including multi-stop trips across a country or region. Use when a user wants to plan a trip — whether they have dates and a destination, dates but no destination, or a destination but no dates. Handles single-destination and multi-stop itineraries, flight search, hotel search, internal transport, destination recommendations, seasonal timing advice, and calendar integration. NOT for booking (links to book externally).
As a process C 50/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
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: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 50/100
- 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
- 30Running it twice. 3 mutating operations with no state check
- 40Consistency. Frontmatter name (travel-agent) differs from the folder (ai-travel-agent)
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 85Steps. 71 steps, 1 vague phrases
- 100Failures and branches. 4 branches, has a failure section
- 100Execution cost. Instruction body is 2405 tokens
- low 10 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
- +3Output format is not stated: the model decides each time
- -225 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 642: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 71 items
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.