AB 24h-product-marketing
read one public product page from 24h.chichbong.com and turn it into a compact zalo-shop-ready product block. use when the user provides a single 24h.chichbong.com/product/... link and wants a short professional vietnamese summary under 500 characters, a safer rewritten title, a marked-up price increased by 30 to 50 percent, and the main product thumb. always prioritize direct page reading, use search as fallback, keep outputs factual, avoid sensitive ad terms, and write in a close but professional tone suitable for product listing content rather than social post copy.
As a process B 74/100 · Nearly there — weak spots: inputs and preconditions, consistency, 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: 4. 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 74/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (24h-product-marketing) differs from the folder (chichbong-content-skill)
- 60Result and completion. Output format stated, no completion criterion
- 100Tools and files. No external tools needed
- 100Steps. 71 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 3 branches, has a failure section
- 100Execution cost. Instruction body is 1205 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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)
- +4No input/output examples
- -41 reference files, but SKILL.md never points to them: the model will not open them
- +1No license
- +2Single-language instructions
- +3Description length 575: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 71 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.