configs/skills/email-sequence/SKILL.md
Designs complete email automation sequences with timing, subject lines, copy, and conditional logic. Supports welcome series, nurture campaigns, re-engagement, abandoned cart, post-purchase, review requests, and custom sequences. Adapts sequence type, cadence, frameworks, and conditional branching to business context. Use when user wants to create an automated email series triggered by subscriber actions or time intervals.
npx skillsauth add shenxingy/claude-code-kit email-sequenceInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Designs complete email automation sequences with strategic timing, persuasive copy, and conditional logic.
| Sequence Type | Emails | Duration | Best For | |---------------|--------|----------|----------| | Welcome Series | 4-6 | 14 days | New subscribers | | Nurture | 6-10 | 6-10 weeks | Education, engagement | | Re-engagement | 3-5 | 28 days | Inactive subscribers | | Abandoned Cart | 3 | 3 days | E-commerce recovery | | Post-Purchase | 4-6 | 30 days | Customer experience | | Review Request | 1-2 | 1-24 hours | Social proof | | Custom | Variable | Variable | Specific goals |
Read the business profile for context:
email-profile.md (project root)Load reference files for frameworks and benchmarks:
references/copy-frameworks.mdreferences/benchmarks.mdAsk the user:
Confirm business context from profile:
Based on sequence type, define:
For each email in sequence, create:
Include:
Standard Timeline:
Framework Assignment:
KPI Targets:
Cadence: 1-2 emails per week
Content Mix:
Framework Rotation: PAS -> FAB -> BAB -> 4Ps -> AIDA -> repeat
Progressive Profiling: Gather data over time through link clicks, survey questions
KPI Targets:
Trigger: 90 days no click engagement (not opens, due to Apple MPP)
Standard Timeline:
Framework Assignment:
After sequence: Remove non-responders from active list to protect sender reputation
KPI Targets:
Standard Timeline:
Framework Assignment:
Show cart items: Include product images, names, prices in email body
Target recovery rate: 5-15%
KPI Targets:
Standard Timeline:
Framework Assignment:
KPI Targets:
Timing varies by business type:
Framework: PAS (Problem-Agitate-Solution) - position review as helping others
Include:
KPI Targets:
For custom sequences, ask user:
Design sequence architecture based on responses.
Apply these rules to every sequence:
If opened previous email but didn't click:
If clicked previous email:
If no engagement on 2+ consecutive emails:
If unsubscribed:
If cart value is high (e.g., over $200):
If first purchase:
If repeat customer:
## Email Sequence: [Sequence Type]
**Business**: [from email-profile.md]
**Industry**: [from profile]
**Trigger**: [what starts this sequence]
**Total Emails**: X
**Duration**: X days/weeks
**Goal**: [primary objective]
### Sequence Timeline
Day 0 -> Email 1 (immediate)
Day 1 -> Email 2
Day 4 -> Email 3
Day 7 -> Email 4
[visual timeline]
---
### Email 1: [Descriptive Title] (Day 0 / Immediate)
**Purpose**: [what this email accomplishes]
**Subject Lines:**
| # | Subject | Score | Reason |
|---|---------|-------|--------|
| 1 | [subject line] | 85 | [why this scores high] |
| 2 | [subject line] | 80 | [why this scores high] |
| 3 | [subject line] | 78 | [why this scores high] |
**Preheader**: [30-80 character preview text]
**Framework**: [PAS/AIDA/BAB/FAB/4Ps/Direct]
**Body:**
[Full email copy with proper formatting, following the selected framework structure]
**CTA**: [Button text] -> [link placeholder or description]
**Conditional Logic:**
- **If opened**: Proceed to Email 2 at scheduled time
- **If not opened**: Wait 24h, resend with subject line variant #2
- **If clicked CTA**: [action - skip email, advance sequence, tag subscriber]
- **If no engagement**: [fallback action]
**A/B Test Recommendation**: [specific element to test for this email]
---
[Repeat full structure for each email in sequence]
---
### Implementation Notes
**Platform Setup:**
- [Automation trigger setup instructions]
- [Segmentation requirements]
- [Tag/field requirements]
**Recommended A/B Tests:**
1. [Test for Email 1]
2. [Test for Email 3]
3. [Overall sequence test]
**KPI Targets:**
| Metric | Target | Industry Benchmark |
|--------|--------|-------------------|
| Average Open Rate | X% | X% |
| Average Click Rate | X% | X% |
| Conversion Rate | X% | X% |
| Unsubscribe Rate | <0.5% | <0.5% |
**Monitoring:**
- Check performance after 50 subscribers complete sequence
- Adjust timing if open rates drop >20% between emails
- Test new subject lines if Email 1 opens <30%
**Segment Considerations:**
- [How to adapt for different audience segments]
- [Mobile vs desktop considerations]
- [Geographic/timezone notes if applicable]
Before delivering sequence, verify:
Load ../../references/copy-frameworks.md for detailed structures:
/email audit to verify domain deliverability before launching sequences/email write for individual email drafts or rewrites/email review to score and optimize each email in the sequence/email plan to align sequences with overall marketing strategydevelopment
Orchestrate a fleet of parallel `codex exec` workers with you (Claude Code) as the supervisor — spawn one per isolated git worktree, dispatch headless, verify each INDEPENDENTLY, PR/merge. The manual "codex-ultracode" pattern for fanning out real implementation, research, or review work onto Codex. Bakes in the hard gotchas (stdin blocking, background tracking, don't-trust-self-reports, writer isolation). Triggers on — orchestrate codex, codex workers, codex fleet, spawn codex, delegate to codex in parallel, manual ultracode, 开 codex 小弟, 派 codex worker — NOT for a single cross-vendor opinion (use the `second-opinion-codex` agent), NOT for web-UI worker decomposition (use `/orchestrate`).
development
Create and manage git worktrees for parallel Codex sessions
development
Verify project behavior anchors — compilation, tests, and interaction checks after autonomous runs. NOT the Codex built-in /verify (which runs the app to observe a single change working) — this one walks the AGENTS.md "Features (Behavior Anchors)" list.
documentation
End-of-session documentation sync — updates TODO.md and PROGRESS.md only (run /commit after to commit everything)