AC opentable
MUST use for any OpenTable / restaurant reservation request. Two entry points — (A) discovery ("find me 3 italian places tonight"): call `list_restaurants.py` for a filtered list; (B) direct book ("reserve Carbone at 8pm", "book Park Rose for 2"): call `book.py` DIRECTLY without searching first. `book.py` is pure URL construction, no verification needed. FORBIDS writing /tmp/cdp_*.js, using exec+node for Chrome automation, web_fetch on opentable.com, raw CDP scripting, or calling list_restaurants.py to "verify" before book.py. Agent must STOP after producing the booking deep link — never click checkout, never fill forms, never submit reservations.
As a process C 63/100 · 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: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: MUST use for any OpenTable / restaurant reservation request. Two e… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 63/100
- 0Result and completion. Does not say what the result is
- 30Inputs and preconditions. Does not say what the process needs to start
- 40Consistency. Frontmatter name (opentable) differs from the folder (opentable-reservations)
- 60Tools and files. Uses tools (bash, web, python, node) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 29 steps
- 100Failures and branches. 11 branches, has a failure section
- 100Execution cost. Instruction body is 3475 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- low The response is described with custom markup (5 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
- +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
- +5Description quotes 4 example trigger phrases
- +3Description length 655: enough signal without eating the budget
- +4Structure: 21 headings
- +3Step-by-step instructions: 29 items
- +4Has examples (11 code blocks)
- +3All 4 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.