AB tripadvisor
TripAdvisor travel data via the Terra API through MCP. Use when the user asks to find hotels, restaurants, or attractions, look up a place's TripAdvisor rating/reviews/photos, compare places to stay or eat, or find what's near a location. Triggers on phrases like "find a hotel in", "best restaurants near", "TripAdvisor reviews for", "what's the rating of", "things to do in", or "attractions near me". Requires the @chrischall/tripadvisor-mcp package installed and the tripadvisor server registered (see Setup), plus a TripAdvisor Terra API key.
TripAdvisor travel data via the Terra API through MCP.
As a process B 65/100 · Nearly there — weak spots: inputs and preconditions, failures and branches, running it twice
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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
edit-residuethe text marks something as outdated (lines 4, 29, 43, 107): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 65/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 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
- 100Tools and files. No external tools needed
- 100Steps. 13 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1435 tokens
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
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +3Description length 547: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 13 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.