BB competitor-offer-monitor
Monitor major competitors' discounting and promotional moves, diagnose whether those moves plausibly caused a sudden drop in your own conversion rate, and design price-power responses including price-match and value-defense playbooks. Use this skill whenever conversion or checkout rate drops without an obvious internal cause, the user suspects a competitor sale or undercutting, they mention price matching, lowest-price guarantees, competitor promos, Google Shopping price gaps, "they're 20% cheaper," MAP or channel pricing conflicts, or they need a structured response to rival offers—even if they only say "CVR tanked this week" or "ads are fine but nobody buys." Also trigger on promo calendar clashes, Black Friday prep vs competitor leaks, or DTC vs Amazon price divergence. Do NOT use for pure SEO/content audits with no pricing or conversion context, single-SKU cost-of-goods-only math with no competitive angle, or legal advice beyond standard commerce guardrails—stay at operational strategy, not attorney-level opinions.
As a process B 67/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- Shorten the description to 1024 characters.
- 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
- error
description-longdescription is 1034 chars, limit 1024
Process rating: all ten parameters 67/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 3 mutating operations with no state check
- 55Failures and branches. 1 branches
- 85Steps. 26 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1092 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
- +3Description length 1034: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 7 headings
- +3Step-by-step instructions: 26 items
- +4Reference files are cited in the instructions (1 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.