BB evidence-based-reviews
Produce honest product reviews and buying guides without fabricated first-hand experience, using disclosed evidence tiers: verified specs, owner-experience synthesis at scale, expert triangulation, and hands-on only when true. Use this skill whenever the user wants to write product reviews or buying guides without hands-on access, set up a review methodology, add evidence disclosure to review content, align reviews with Google's reviews system or FTC affiliate disclosure expectations, or decide when Review and Product schema are honest to use. Triggers on product review, buying guide, best-of list, review methodology, evidence basis, hands-on testing, we tested, affiliate review site, review disclosure, methodology block, original research, reviews system. Also triggers when review content claims testing that did not happen, or when an affiliate site needs a trust mechanism that survives scrutiny.
Produce honest product reviews and buying guides without fabricated first-hand experience, using disclosed evidence tiers: verified specs, owner-experience…
As a process B 78/100 · Nearly there — weak spots: running it twice, progress reporting
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: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "catalog_summary" - note
frontmatter-keyunknown frontmatter key "display_order"
Process rating: all ten parameters 78/100
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 46 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2833 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 14 top-level sections: this looks like several domains in one skill
- high The skill tells the model to perform an irreversible action with no human approval
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 910: 120–800 characters recommended
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Structure: 19 headings
- +3Step-by-step instructions: 46 items
- +3Output format is stated explicitly
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.