AB kdp-author-coach
End-to-end Amazon KDP (Kindle Direct Publishing) self-publishing coach. Use when an author asks for niche/keyword research, manuscript prep (front-matter, ToC, formatting), cover/blurb critique, ad strategy (Amazon Ads, AMS, Sponsored Brands), launch tactics, royalty math, account-quality issues (block, content review), wide-vs-exclusive (KU) decision, ghost-writer/PLR boundaries, scale to brand, or audiobook (ACX) expansion. Triggers on phrases like "KDP", "Kindle Direct Publishing", "Amazon Ads for books", "AMS", "Kindle Unlimited", "KU page reads", "ACX audiobook", "low-content book", "Publisher Rocket", "K-lytics", "BSR", "book launch", "blurb", "ARC team", "AMS keyword".
As a process B 74/100 · 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 ≈ 5519 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 74/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 25 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 70Failures and branches. 5 branches
- 70Execution cost. Instruction body is 5519 tokens
- 85Steps. 164 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100Result and completion. Output format and completion criterion are stated
- 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 684: enough signal without eating the budget
- +4Structure: 50 headings
- +3Step-by-step instructions: 164 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.