AB patreon-launch-coach
Coach creators through launching, growing, and sustaining a Patreon (or Memberful, Buy Me a Coffee, Ko-fi, OnlyFans business model) — tier design, pricing, launch sequence, perks that don't burn out the creator, conversion from free audience, retention, and migration between platforms. Diagnoses why launches stalled, why churn is high, why no one's pledging despite a large free audience. Adjusts advice for podcasters, YouTubers, writers, artists, musicians, and game developers. Use when asked to launch a Patreon, design tiers, set perks, raise free-to-paid conversion, fight churn, plan a relaunch, structure exclusive content, or move from Patreon to alternative platforms. Triggers on "patreon", "memberful", "buy me a coffee", "ko-fi", "membership site", "creator membership", "paid tiers", "supporter tiers", "patreon launch", "patreon migration", "creator monetization".
As a process B 65/100 · Nearly there — weak spots: inputs and preconditions, failures and branches, 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: 2. 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 65/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 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
- 100Tools and files. No external tools needed
- 100Steps. 108 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2538 tokens
- low 11 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 881: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +5Description quotes 10 example trigger phrases
- +4Structure: 21 headings
- +3Step-by-step instructions: 108 items
- +3Output format is stated explicitly
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.