BB b2b-saas-pricing-coach
Coach for B2B SaaS founders on pricing — choosing the value metric (per-seat, per-API-call, per-MAU, per-revenue-processed, per-asset-monitored, per-feature-tier, per-outcome), structuring tiers (Starter / Pro / Business / Enterprise) without trapping yourself, setting headline prices that ladder properly to ACV targets, deciding when to sell free trial vs freemium vs no-free, packaging logic (what's in tier vs add-on vs Enterprise-only), discounting policy + sales-led friction, the contract-period question (monthly vs annual vs multi-year), repricing existing customers without losing them, and re-pricing during inflation / cost shocks. Use when founder says "what should we charge", "pricing v2", "raise prices", "going from PLG to sales-led pricing", "free vs freemium", "annual contract pricing", "SaaS pricing tier strategy", "value metric", "per-seat pricing too low", "enterprise tier needed". Triggers on phrases like "B2B SaaS pricing", "SaaS pricing strategy", "value metric", "per-seat pricing", "usage-based pricing", "freemium vs free trial", "tier packaging", "enterprise pricing", "SaaS price increase", "grandfathering customers", "expansion revenue", "annual contract value", "ACV vs ARR".
As a process B 70/100 · Nearly there — weak spots: inputs and preconditions, running it twice, progress reporting
How to improve
- Shorten the description to 1024 characters.
- 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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1213 chars, limit 1024
Process rating: all ten parameters 70/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 15 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Failures and branches. 5 branches
- 70Execution cost. Instruction body is 4786 tokens
- 100Tools and files. No external tools needed
- 100Steps. 185 steps
- 100Consistency. Name and required fields are in place
- low 12 top-level sections: this looks like several domains in one skill
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 1213: 120–800 characters recommended
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +5Description quotes 23 example trigger phrases
- +4Structure: 46 headings
- +3Step-by-step instructions: 185 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 60.