list-segment-builder

Use when the user asks to "build email segments from my list", "make engaged / lapsed / RFM segments", "set up cart-abandoner or lifecycle-stage audiences", or "build a suppression list of unsubscribes and bounces"; turns the user's OWN list/CRM/GA4/ecommerce export into behavioral, attribute, and lifecycle-stage segments plus a suppression list, with per-segment sizes labeled Measured/Estimated, informing the SEND E (Engagement/targeting) dimension. Not for scoring EQS or running vetoes — use email-quality-auditor; not for authentication or spam-content checks — use deliverability-qa. 邮件列表分群/生命周期分群/抑制名单/流失召回

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a well-structured, actionable instruction skill with a clear sequenced workflow and one-level-deep references; its main weakness is repeated restatement of scope boundaries and the consent-registry read-only rule across multiple sections, which inflates length without adding guidance.

Suggestions

Consolidate the consent-registry 'reads never writes memory/consent/' rule into a single stated place (e.g. the Data Sources section) and reference it rather than restating it in Instruction step 6 and the Scope guard.

State the cross-skill exclusions (not EQS scoring, not vetoes, not auth/spam-content) once in the Scope guard and remove the duplicates in the intro and Next Best Skill sections.

Move the full Resend zero-dependency sync recipe into the connectors README it already links, keeping SKILL.md to a one-line pointer to reduce inline length.

Dimension	Reasoning	Score
Conciseness	Mostly efficient but repeats the same boundaries several times — the 'reads memory/consent/ never writes it' rule appears in Data Sources, Instruction step 6, and Scope guard, and the 'not score EQS / not run vetoes / not auth checks' exclusions appear in the intro, Scope guard, and Next Best Skill, so it could be tightened.	2 / 3
Actionability	Concrete executable guidance throughout: named segments (engaged-90d, cart-abandoners-7d), RFM tiers (champions/loyal/at-risk/hibernating), explicit NEEDS_INPUT handling, concrete save paths, and a real command (`python3 .../scripts/connectors/resend.py contacts`) — actionable per the instruction-skill guidance.	3 / 3
Workflow Clarity	A clear seven-step sequence (confirm goal, profile export, behavioral, RFM, lifecycle, suppression, note E) with explicit validation checkpoints via NEEDS_INPUT flags, consent-registry reconciliation, and a 'Done when' checklist that catches errors early.	3 / 3
Progressive Disclosure	Well-organized sections with one-level-deep, clearly labeled references (Reference Materials, CONNECTORS.md, SECURITY.md, skill-contract.md) and no nested reference chains; the inline connector recipe is the only material that could be split out.	3 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is third-person, concise for its density, and excels across all dimensions: concrete actions, natural trigger phrases, explicit when-guidance, and clear disambiguation from sibling skills. It would benefit only from trimming the trailing non-English summary to avoid redundancy.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions such as building behavioral segments, RFM tiers, lifecycle-stage audiences, and a suppression list with per-segment sizes labeled Measured/Estimated, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	An explicit 'Use when...' clause with concrete triggers plus a clear statement of what the skill does (turns an export into behavioral/attribute/lifecycle segments plus a suppression list) answers both what and when explicitly.	3 / 3
Trigger Term Quality	Direct quoted natural phrases users would say ('build email segments from my list', 'make engaged / lapsed / RFM segments', 'set up cart-abandoner or lifecycle-stage audiences', 'build a suppression list of unsubscribes and bounces') give good coverage of natural terms.	3 / 3
Distinctiveness Conflict Risk	Explicit negative boundaries ('Not for scoring EQS or running vetoes — use email-quality-auditor; not for authentication or spam-content checks — use deliverability-qa') carve a clear niche unlikely to trigger the wrong skill.	3 / 3
	Total	12 / 12 Passed

Validation

75%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 28 suspicious	Warning
referenced_paths_exist	Referenced path issues: 1 missing, 1 deeper-than-1-level	Warning

	Total	12 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: email/setup/list-segment-builder/SKILL.md
Commit: 4a77c48

Reviewed: 9 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.