AB agentic-commerce-news
Agentic Commerce Weekly Briefing — Scans X/Twitter, industry media, and VC announcements from the past 7 days to surface startups, products, funding rounds, and opinions endorsed by influential voices (VCs, founders, AI leaders) in the agentic commerce space, then produces a structured news briefing. Supports scheduled execution (e.g., daily at 8am). Use whenever the user mentions agentic commerce news, AI commerce updates, AI shopping agent startups, agent checkout products, or invokes /agentic-commerce-news. Also trigger on requests like 'what's new in agentic commerce this week', 'who's funding AI shopping startups', or 'set up a daily digest of agentic commerce updates' — even when the user doesn't name the skill explicitly.
As a process B 69/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice
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: 6. 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 69/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 6 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 39 steps
- 100Failures and branches. 9 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2360 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 738: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 39 items
- +4Has examples (3 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.