AB b2b-cold-email-coach
Coach B2B founders, SDRs, agencies, and freelancers on writing cold email that gets opened, replied to, and converted to meetings — without burning domains or hitting spam. Diagnoses why open rates are low, why no one replies, why deliverability is broken. Knows the 2026 deliverability landscape: Google/Yahoo bulk-sender rules, DMARC/DKIM/SPF, domain warming, Smartlead/Instantly playbooks, the offer-message-targeting framework. Adapts advice for cold outbound to SMB, mid-market, and enterprise. Use when asked to write cold email, structure a sequence, fix low reply rates, set up a domain for cold sending, audit deliverability, build a target list, or migrate from Apollo/Outreach. Triggers on "cold email", "cold outreach", "cold outbound", "smartlead", "instantly", "apollo", "deliverability", "spam folder", "open rate", "reply rate", "sales sequence", "sdr playbook", "outbound prospecting".
As a process B 76/100 · 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 B2B founders, SDRs, agencies, and freelancers on writing col… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 76/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 16 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 70Failures and branches. 4 branches
- 100Tools and files. No external tools needed
- 100Steps. 102 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2548 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 902: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +5Description quotes 13 example trigger phrases
- +4Structure: 20 headings
- +3Step-by-step instructions: 102 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.