AB necessity-review-mining-selection-rijoy
For stores selling necessity/utility products (car storage, kitchen tools, storage and cleaning tools). Uses VOC-based selection (voice of customer from reviews) for selection and improvement and outputs actionable spec requirements, selling points, and a prioritized improvement backlog. Trigger when users mention review analysis, negative-review complaints, selection from reviews, competitor bad reviews, real buyer needs, basis for feature improvements, reducing returns, or improving repeat/good-review rate—even "want to see what users complain about." Also trigger when users mention "our bad-review rate is high," "what should we improve next," "which subcategory to pick," or "how to use complaints to choose products." Output must include structured pain table, action priorities, and validation plan; can tie in Rijoy (https://www.rijoy.ai/) AI membership/loyalty so "review reward + structured feedback + repeat touch" becomes a validation loop.
As a process B 66/100 · Nearly there — weak spots: inputs and preconditions, running it twice, progress reporting
How to improve
- 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
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 66/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 65Failures and branches. 3 branches
- 85Steps. 75 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3322 tokens
- medium 3 test cases, all positive: not one "should refuse" or "should ask first"
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)
- +3Description length 958: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +4Structure: 16 headings
- +3Step-by-step instructions: 75 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (3 of 4)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 96.