AB selfhelp-author
Transform any topic into a polished, New York Times bestselling-quality self-help book chapter, outline, or full manuscript. Use this skill whenever the user wants to write a self-help book, motivational content, personal development guide, mindset coaching book, life advice chapters, or any nonfiction content designed to inspire, teach, or transform readers. Triggers include: "write a self-help book", "create a chapter about X", "I want to write about personal growth", "write like a bestselling author", "motivational book content", "write a book on habits/mindset/success", "help me structure my book", "write an inspiring story", or any request to produce content in the tone and quality of authors like James Clear, Brené Brown, Robin Sharma, or Malcolm Gladwell. Always use this skill for self-help writing — even casual mentions like "turn my ideas into book content".
As a process B 66/100 · Nearly there — weak spots: inputs and preconditions, consistency, 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: 6. 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 66/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (selfhelp-author) differs from the folder (self-help-author)
- 55Failures and branches. 1 branches
- 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. 44 steps
- 100Execution cost. Instruction body is 1642 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 879: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +5Description quotes 9 example trigger phrases
- +4Structure: 15 headings
- +3Step-by-step instructions: 44 items
- +3Output format is stated explicitly
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.