Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →メールシーケンス、ステップメール、ドリップキャンペーンの設計・最適化を行うスキル。 「メール設計」「ステップメール作成」「ウェルカムメール」等のリクエストで発動。 For in-app onboarding, see onboarding-cro.
.claude/skills/minicoohei-email-sequence/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 67% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 92% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 82% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 114% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 29% | 0% |
You are an expert in email marketing and automation. Your goal is to create email sequences that nurture relationships, drive action, and move people toward conversion.
Check for product marketing context first: If .claude/product-marketing-context.md exists, read it before asking questions. Use that context and only ask for information not already covered or specific to this task.
Before creating a sequence, understand:
Depends on:
Consider:
Patterns that work:
Length: 5-7 emails over 12-14 days Goal: Activate, build trust, convert
Key emails:
Length: 6-8 emails over 2-3 weeks Goal: Build trust, demonstrate expertise, convert
Key emails:
Length: 3-4 emails over 2 weeks Trigger: 30-60 days of inactivity Goal: Win back or clean list
Key emails:
Length: 5-7 emails over 14 days Goal: Activate, drive to aha moment, upgrade Note: Coordinate with in-app onboarding—email supports, doesn't duplicate
Key emails:
For detailed templates: See references/sequence-templates.md
For detailed email type reference: See references/email-types.md
For detailed copy, personalization, and testing guidelines: See references/copy-guidelines.md
Sequence Name: [Name]
Trigger: [What starts the sequence]
Goal: [Primary conversion goal]
Length: [Number of emails]
Timing: [Delay between emails]
Exit Conditions: [When they leave the sequence]Email [#]: [Name/Purpose]
Send: [Timing]
Subject: [Subject line]
Preview: [Preview text]
Body: [Full copy]
CTA: [Button text] → [Link destination]
Segment/Conditions: [If applicable]What to measure and benchmarks
For implementation, see the tools registry. Key email tools:
| Tool | Best For | MCP | Guide | |------|----------|:---:|-------| | Customer.io | Behavior-based automation | - | customer-io.md | | Mailchimp | SMB email marketing | ✓ | mailchimp.md | | Resend | Developer-friendly transactional | ✓ | resend.md | | SendGrid | Transactional email at scale | - | sendgrid.md | | Kit | Creator/newsletter focused | - | kit.md |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-04 | pass→pass | 12,389 | 8,030 | -35% | 1 | 1 | 0% | 1,957 | 3,282 | +68% | 0 | 0 | — |
case-01 | fail→pass | 20,629 | 22,652 | +10% | 1 | 1 | 0% | 3,415 | 5,714 | +67% | 0 | 0 | — |
case-02 | pass→pass | 12,707 | 7,800 | -39% | 1 | 1 | 0% | 2,171 | 3,344 | +54% | 0 | 0 | — |
case-03 | fail→pass | 13,828 | 13,399 | -3% | 1 | 1 | 0% | 2,202 | 4,238 | +92% | 0 | 0 | — |
case-05 | fail→pass | 11,466 | 8,794 | -23% | 1 | 1 | 0% | 1,870 | 3,407 | +82% | 0 | 0 | — |
case-06 | fail→pass | 8,093 | 6,045 | -25% | 1 | 1 | 0% | 1,426 | 3,048 | +114% | 0 | 0 | — |
case-07 | pass→pass | 12,362 | 9,794 | -21% | 1 | 1 | 0% | 2,170 | 3,553 | +64% | 0 | 0 | — |
case-08 | fail→pass | 16,071 | 5,708 | -64% | 1 | 1 | 0% | 2,369 | 3,048 | +29% | 0 | 0 | — |
case-09 | pass→pass | 11,279 | 7,734 | -31% | 1 | 1 | 0% | 1,786 | 3,302 | +85% | 0 | 0 | — |
case-10 | fail→pass | 5,309 | 4,877 | -8% | 1 | 1 | 0% | 823 | 2,871 | +249% | 0 | 0 | — |
case-11 | fail→pass | 13,187 | 10,740 | -19% | 1 | 1 | 0% | 1,879 | 3,727 | +98% | 0 | 0 | — |
case-12 | fail→fail | 14,343 | 12,293 | -14% | 1 | 1 | 0% | 2,166 | 4,097 | +89% | 0 | 0 | — |
case-13 | fail→pass | 9,273 | 9,288 | +0% | 1 | 1 | 0% | 1,567 | 3,296 | +110% | 0 | 0 | — |
case-14 | pass→pass | 10,757 | 4,189 | -61% | 1 | 1 | 0% | 1,658 | 2,638 | +59% | 0 | 0 | — |
case-15 | pass→pass | 11,719 | 10,268 | -12% | 1 | 1 | 0% | 2,011 | 3,827 | +90% | 0 | 0 | — |
case-16 | fail→pass | 5,523 | 5,860 | +6% | 1 | 1 | 0% | 851 | 2,966 | +249% | 0 | 0 | — |
case-17 | fail→pass | 7,859 | 6,065 | -23% | 1 | 1 | 0% | 1,249 | 2,979 | +139% | 0 | 0 | — |
case-18 | pass→pass | 14,898 | 10,642 | -29% | 1 | 1 | 0% | 2,392 | 3,749 | +57% | 0 | 0 | — |
case-19 | pass→pass | 13,360 | 11,909 | -11% | 1 | 1 | 0% | 1,962 | 4,052 | +107% | 0 | 0 | — |
case-20 | fail→pass | 11,883 | 11,927 | +0% | 1 | 1 | 0% | 1,996 | 3,803 | +91% | 0 | 0 | — |
case-21 | fail→fail | 19,195 | 26,984 | +41% | 1 | 1 | 0% | 3,565 | 7,463 | +109% | 0 | 0 | — |
case-22 | fail→fail | 20,561 | 10,902 | -47% | 1 | 1 | 0% | 3,528 | 3,878 | +10% | 0 | 0 | — |
case-23 | fail→fail | 17,192 | 20,145 | +17% | 1 | 1 | 0% | 3,556 | 6,311 | +77% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted. The headline lift of +48 percentage points is the difference between those two pass rates over the 23 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.