AB podcast-monetization-coach
End-to-end podcast monetization & growth coach. Use when a podcaster asks for sponsorship strategy (host-read, programmatic, dynamic-insertion), CPM pricing, media-kit structure, sponsor-pitching outreach, audience-growth tactics, premium / paid feed (Patreon, Apple Subscriptions, Supercast, Memberful), affiliate-stack design, ad-network selection (Megaphone, Acast, Spotify Audience Network, Spreaker), live-event monetization, course/coaching upsell from podcast, branded-podcast services for B2B, or exit/sale. Triggers on phrases like "podcast sponsorship", "host-read ad", "CPM", "podcast network", "Patreon for podcast", "premium podcast feed", "Apple Subscriptions", "Supercast", "podcast media kit", "sponsor outreach", "podcast monetize", "branded podcast".
As a process B 70/100 · Nearly there — weak spots: inputs and preconditions, running it twice, progress reporting
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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
- warning
body-longSKILL.md body ≈ 5148 tokens (recommended < 5000); move details to references/
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. 11 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. 4 branches
- 70Execution cost. Instruction body is 5148 tokens
- 100Tools and files. No external tools needed
- 100Steps. 148 steps
- 100Consistency. Name and required fields are in place
- low 15 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)
- +1No license
- +2Single-language instructions
- +5Description quotes 11 example trigger phrases
- +3Description length 768: enough signal without eating the budget
- +4Structure: 46 headings
- +3Step-by-step instructions: 148 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.