AC ocas-taste
Use when generating personalized recommendations grounded in real consumption signals (purchases, visits, plays, watches), scanning email and calendar for consumption data, enriching venue entities with taste-relevant attributes, exploring cross-domain discovery based on actual behavior, checking taste model status, or producing periodic taste pattern reports. Trigger phrases: 'recommend', 'what would I like', 'based on what I've liked', 'suggest something similar', 'my taste', 'what should I try', 'scan my email', 'what have I been eating', 'restaurant recommendations', 'update taste'. Do not use for generic search, editorial top-10 lists, or ad-copy generation.
As a process C 62/100 · Has gaps — weak spots: result and completion, inputs and preconditions
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: 11. 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 4, column 14: description: Use when generating personalized recommendations grounded in real … ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value - note
frontmatter-keyunknown frontmatter key "source" - note
frontmatter-keyunknown frontmatter key "install"
Process rating: all ten parameters 62/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 100Steps. 88 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3180 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 16 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
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 671: enough signal without eating the budget
- +4Structure: 21 headings
- +3Step-by-step instructions: 88 items
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (7 of 7)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.