What does this skill do, and when should you use it?
List Segment Builder handles audience definition before an email send is designed. It reads user-provided list, CRM, ESP, GA4, or ecommerce exports and produces behavioral segments, attribute and RFM tiers, lifecycle stages, and a suppression list. Every segment size is labeled Measured or Estimated with its basis stated. It does not send email, write creative, design automation flows, or run the SEND quality audit.
Profiles available subscription, open, click, order, unsubscribe, hard-bounce, and complaint fields; builds behavioral groups such as engaged-90d, cart-abandoners, browse-abandoners, and clicked-no-purchase; creates RFM tiers from the user's own Recency, Frequency, and Monetary fields; maps new, active, at-risk, lapsed, and win-back lifecycle stages; reads the consent-registry as the source of truth for consent and suppression; and outputs a segment map with rules, measured or estimated sizes, and SEND E relevance.
- An ecommerce team preparing a retention promotion needs engaged, lapsed, and cart-abandoner audiences from order and ESP exports.
- A CRM team wants champions, loyal, at-risk, and similar RFM tiers from its own order history.
- An email operator needs a pre-send suppression list covering unsubscribes, hard bounces, complaints, and withdrawn consent.
- A growth team has only CSV or GA4/ecommerce exports and wants reusable lifecycle audiences across campaigns.
How do you install this skill?
- Before any sync or suppression mutation, reconcile the consent registry with the target ESP export; missing consent records must not be treated as mailable.
- The skill writes to memory but does not define recovery, versioning, or reversal after a failed or mistaken write; confirm the target path and backup approach first.
- SECURITY.md's supported-version statement conflicts with the skill's 18.0.0 version; verify the actual maintenance and security-support scope.
- There is no evidence of mainland-China network reachability or local ESP integration; prefer the Tier-1 local-export workflow over overseas MCP dependencies.
- Shell / CLI
- Local filesystem
Python 3 for optional Resend synchronization
For Claude Code, run /plugin marketplace add aaron-he-zhu/aaron-marketing-skills, then /plugin install aaron-marketing@aaron. On an Agent Skills-compatible host, run npx skills add aaron-he-zhu/aaron-marketing-skills; alternatively clone the repository and use email/setup/list-segment-builder/SKILL.md.
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/aaron-he-zhu/aaron-marketing-skills.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/email/setup/list-segment-builder" ~/.claude/skills/
rm -rf "$tmp"Generated from the source repository and skill path; it copies only this skill's folder. If the author's install steps above differ, follow those first. To scope it to one project, replace ~/.claude/skills with that project's .claude/skills.
How do you use this skill?
Provide a list, CRM, ESP, or GA4/ecommerce export and state the goal and ESP. Example: Build email segments from my list export: [path]. Goal is retention. ESP export attached. If order, engagement, or consent fields are missing, the skill should mark NEEDS_INPUT rather than infer them, and it should not echo raw email addresses or phone numbers.
What are this skill's strengths and limitations?
- Covers behavioral, RFM, lifecycle, and suppression outputs in one segment map.
- Requires every size to be labeled Measured or Estimated, distinguishing counts from inference.
- Uses the consent-registry as the source of truth for consent and suppression facts.
- Runs from user-provided exports without requiring an ESP API or MCP.
- RFM tiers cannot be grounded without order data.
- Missing consent, engagement, or bounce fields produce NEEDS_INPUT rather than automatic completion.
- The skill defines WHO to target or suppress; it does not send, compose, design flows, or audit EQS.
- The supplied material provides no standalone test suite or validation results for specific ESP platforms.
How does this skill compare with similar options?
Side by side with related skills; every score comes from the same FSRS standard.
| Skill | FS score | Stars | Last updated | License |
|---|---|---|---|---|
| Email List Segment Builder this page | 61 · Recommended | ★ 3k | 13d ago | Apache-2.0 |
| Reactivation Specialist | 57 · Use with care | ★ 3k | 13d ago | Apache-2.0 |
| Email Preference & Frequency Manager | 61 · Recommended | ★ 3k | 13d ago | Apache-2.0 |
| List Growth Designer | 58 · Recommended | ★ 3k | 13d ago | Apache-2.0 |
| Email Quality Auditor | 56 · Use with care | ★ 3k | 13d ago | Apache-2.0 |
Unlike email-creative-builder and email-sequence-designer, this skill defines the email audience and suppression set before creative or lifecycle-flow work; consent facts belong to consent-registry, while the SEND quality verdict belongs to email-quality-auditor.
How did FollowSkills review this skill?
The skill treats exports as untrusted input, forbids echoing raw PII, makes the consent registry the source of truth, and places Resend mutations behind dry-run plus explicit --live confirmation. It does not fully specify rollback for memory writes, and publisher identity is unverified, so 5 points are deducted.
Column profiling, NEEDS_INPUT handling, missing-RFM behavior, suppression reconciliation, and scope guards are internally coherent, with useful failure guidance. However, there are no skill-specific tests, execution traces, or reproducible abnormal-data diagnostics; the score is kept below the static-review ceiling.
Triggers, inputs, goals, output buckets, and non-fit boundaries are clearly stated, with English and Chinese terminology. Tier-1 exports do not require a specific ESP, but regional compliance, field semantics, and threshold choices remain user-dependent, so 3 points are deducted.
Frontmatter supplies name, version, license, compatibility, and argument hint; Quick Starts, contract, data sources, save instructions, handoffs, and termination rules are well organized. Maintenance ownership, changelog, and update path are not clear, and SECURITY.md says 17.x is the current supported line while this skill declares 18.0.0, costing 4 points.
The skill specifies a usable four-bucket segment map, Measured/Estimated labeling, suppression rules, and SEND E handoff notes. No representative executed output or skill-specific validation is provided, so static review cannot confirm parsing, counting, or reconciliation correctness; 6 points are awarded.
The repository includes architecture and audit-validator tests, CI, and version metadata, but the supplied tests do not cover this skill's segmentation, RFM, consent reconciliation, or Resend paths, and there is no third-party execution evidence. Only limited static auditability merits 3 points.
Open a dimension to read why it scored that way
Evidence confidence：Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.
See the full review method →