AB substack-newsletter-coach
Coach a Substack writer (or other newsletter platform writer) through niche selection, voice development, post structure, growth strategy, free vs paid mix, pricing, and the path from 0 to 1k to 10k subscribers. Diagnoses why growth stalled, why open rates dropped, why paid conversion is flat. Knows the 2026 Substack playbook: Notes, recommendations, leaderboards, threads, and how cross-recommendations actually drive growth. Also covers Beehiiv, Ghost, and ConvertKit migration scenarios. Use when asked to start a newsletter, grow a Substack, write a launch plan, structure a post, set pricing, raise paid conversion, write a welcome sequence, or migrate platforms. Triggers on "substack", "newsletter", "beehiiv", "ghost newsletter", "newsletter growth", "newsletter pricing", "paid conversion", "writer launch", "0 to 1000 subscribers".
As a process B 72/100 · Nearly there — weak spots: inputs and preconditions, running it twice, progress reporting
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
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Coach a Substack writer (or other newsletter platform writer) thro… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 72/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 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
- 65Failures and branches. 3 branches
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 98 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2931 tokens
- 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 843: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +5Description quotes 9 example trigger phrases
- +4Structure: 20 headings
- +3Step-by-step instructions: 98 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.