Repeat Purchase Flow Review - E-commerce
Use this skill when
The user wants to improve retention, repeat purchase, or lifecycle marketing.
Common requests:
- "Review our Klaviyo flows."
- "How do we get more second purchases?"
- "Audit post-purchase email/SMS."
- "Find missing lifecycle flows."
Required input
Minimum useful input:
- Email/SMS flow screenshots or exports.
- Flow names, triggers, timing, and message summaries.
- Revenue, open rate, click rate, conversion rate where available.
- Product category and typical replenishment or repurchase cycle.
- Customer segments if available.
Optional:
- Cohort repeat-purchase data.
- First-order products and second-order products.
- Review, support, or return themes.
- Promo calendar.
Before analysis
- Confirm whether products are replenishable, seasonal, gifting, fashion, durable, or one-time purchases.
- Confirm the target outcome: second purchase, cross-sell, replenishment, loyalty, review generation, or win-back.
- Avoid generic flow advice when purchase cycle is unknown.
Analysis workflow
- Map existing flows:
- welcome
- browse abandonment
- cart abandonment
- post-purchase
- education/use
- replenishment
- cross-sell
- win-back
- Compare timing to product usage and buying cycle.
- Check message fit:
- reason to buy again
- product education
- next-best product
- proof
- objection handling
- customer care
- Find missing segments and over-message risks.
- Recommend the next 3 retention tests.
Decision and evidence standard
Every finding should include:
- Evidence tag:
export, screenshot, url, review_cluster, support_ticket, return_reason, policy, feed_diagnostics, margin_csv, inventory_export, hypothesis, or needs_data.
- Severity: low, medium, high, or critical.
- Confidence: low, medium, or high.
- Business impact: revenue, margin, cashflow, retention, conversion, support_load, or risk.
- Effort: XS, S, M, or L.
- Owner decision: do_now, test, investigate, monitor, ignore, or approval_needed.
If the evidence is weak, mark the finding as hypothesis or needs_data and lower confidence.
Output format
Retention verdict
Short summary of the biggest lifecycle gap.
Flow table
| Flow |
Status |
Evidence |
Gap |
Recommended change |
Second-purchase opportunities
List product and timing hypotheses.
Measurement plan
Metrics to monitor for each proposed change.
Example input and output
Input:
- flow screenshots
- flow performance export
- product replenishment cycle
- first and second order product mix
Good output excerpt:
| Finding |
Evidence |
Severity |
Confidence |
Business impact |
Effort |
Owner decision |
| No post-purchase education before likely second-use moment |
screenshot, hypothesis |
medium |
low |
retention/support_load |
S |
test |
| Replenishment flow timing is later than the product usage cycle |
export, policy |
high |
medium |
retention |
M |
investigate |
What not to do yet: default to discounts before checking product cycle, customer education, and cross-sell fit.
Guardrails
- Do not write final customer emails unless brand voice and offer rules are provided.
- Do not recommend heavy discounting as the default retention tactic.
- Do not assume one purchase cycle fits all products.
- Do not send or schedule messages.
- Do not invent segmentation data.
1---2name: repeat-purchase-flow-review-ecommerce3description: Reviews e-commerce lifecycle flows from email/SMS exports, screenshots, product cycle data, and purchase timing to find second-purchase and retention opportunities. Use when repeat purchase is weak, email revenue is low, or post-purchase flows need review.4---56# Repeat Purchase Flow Review - E-commerce78## Use this skill when910The user wants to improve retention, repeat purchase, or lifecycle marketing.1112Common requests:1314- "Review our Klaviyo flows."15- "How do we get more second purchases?"16- "Audit post-purchase email/SMS."17- "Find missing lifecycle flows."1819## Required input2021Minimum useful input:2223- Email/SMS flow screenshots or exports.24- Flow names, triggers, timing, and message summaries.25- Revenue, open rate, click rate, conversion rate where available.26- Product category and typical replenishment or repurchase cycle.27- Customer segments if available.2829Optional:3031- Cohort repeat-purchase data.32- First-order products and second-order products.33- Review, support, or return themes.34- Promo calendar.3536## Before analysis37381. Confirm whether products are replenishable, seasonal, gifting, fashion, durable, or one-time purchases.392. Confirm the target outcome: second purchase, cross-sell, replenishment, loyalty, review generation, or win-back.403. Avoid generic flow advice when purchase cycle is unknown.4142## Analysis workflow43441. Map existing flows:45 - welcome46 - browse abandonment47 - cart abandonment48 - post-purchase49 - education/use50 - replenishment51 - cross-sell52 - win-back532. Compare timing to product usage and buying cycle.543. Check message fit:55 - reason to buy again56 - product education57 - next-best product58 - proof59 - objection handling60 - customer care614. Find missing segments and over-message risks.625. Recommend the next 3 retention tests.6364## Decision and evidence standard6566Every finding should include:6768- Evidence tag: `export`, `screenshot`, `url`, `review_cluster`, `support_ticket`, `return_reason`, `policy`, `feed_diagnostics`, `margin_csv`, `inventory_export`, `hypothesis`, or `needs_data`.69- Severity: low, medium, high, or critical.70- Confidence: low, medium, or high.71- Business impact: revenue, margin, cashflow, retention, conversion, support_load, or risk.72- Effort: XS, S, M, or L.73- Owner decision: do_now, test, investigate, monitor, ignore, or approval_needed.7475If the evidence is weak, mark the finding as `hypothesis` or `needs_data` and lower confidence.7677## Output format7879### Retention verdict8081Short summary of the biggest lifecycle gap.8283### Flow table8485| Flow | Status | Evidence | Gap | Recommended change |86|---|---|---|---|---|8788### Second-purchase opportunities8990List product and timing hypotheses.9192### Measurement plan9394Metrics to monitor for each proposed change.9596## Example input and output9798Input:99100- flow screenshots101- flow performance export102- product replenishment cycle103- first and second order product mix104105Good output excerpt:106107| Finding | Evidence | Severity | Confidence | Business impact | Effort | Owner decision |108|---|---|---|---|---|---|---|109| No post-purchase education before likely second-use moment | `screenshot`, `hypothesis` | medium | low | retention/support_load | S | test |110| Replenishment flow timing is later than the product usage cycle | `export`, `policy` | high | medium | retention | M | investigate |111112What not to do yet: default to discounts before checking product cycle, customer education, and cross-sell fit.113114## Guardrails115116- Do not write final customer emails unless brand voice and offer rules are provided.117- Do not recommend heavy discounting as the default retention tactic.118- Do not assume one purchase cycle fits all products.119- Do not send or schedule messages.120- Do not invent segmentation data.
mardab96