CC email-design
Design distinctive, on-brand emails — newsletters, campaigns, welcome series, promo, post-purchase, win-back, transactional, announcements. Use when the user wants to draft, write, compose, design, redesign, critique, polish, or improve an email; or send a campaign / blast / broadcast through any ESP (Nitrosend, Klaviyo, Mailchimp, ActiveCampaign, etc.). Produces a structured design brief and translates it into the sending tool's section format. Bakes in anti-slop principles: own a colour, restrained palettes, real imagery with sourced or prompted image slots, distinctive voice, no category-reflex aesthetics, no orphan whitespace, single column ≤600px, mobile-first, real footers (verified mission only, plus socials + address + unsubscribe). Asks at most three questions to fill brand gaps; otherwise infers from connected ESP account settings or a project brand file. Self-contained — no other skills required. Skip for pure strategy, deliverability, copy-only, or platform-selection questions.
Design distinctive, on-brand emails — newsletters, campaigns, welcome series, promo, post-purchase, win-back, transactional, announcements.
As a process C 51/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
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: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5162 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 51/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 26 mutating operations with no state check
- 40Consistency. Frontmatter name (email-design) differs from the folder (email-design-2)
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 5162 tokens
- 85Steps. 88 steps, 2 vague phrases
- 100Failures and branches. 2 branches, has a failure section
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (3 tags): a typed call is more reliable
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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1004: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Structure: 27 headings
- +3Step-by-step instructions: 88 items
- +4Has examples (7 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.