email-sequence-designer

Use when the user asks to "design a welcome flow", "set up an abandoned-cart sequence", "build a light re-engagement branch inside a lifecycle flow", or "plan a cold-outbound sequence"; produces general lifecycle automation flows (welcome, cart, browse-abandon, post-purchase, in-flow re-engagement, B2B cold outbound) with trigger, step timing, branch/exit conditions, goal, frequency governance (send caps, quiet hours, fatigue guardrail), a sunset path, and a SEND N-dimension score. Not for the closed-loop win-back / re-consent (re-permission) program on a lapsed cohort — use reactivation-specialist; not for writing each email's copy — use email-creative-builder; not for computing EQS or the N1 unsubscribe veto — use email-quality-auditor. 邮件自动化流程设计/购物车挽回/流失召回序列

Quality

88%

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

77%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.

A highly actionable, well-sequenced workflow with concrete commands and validation checkpoints, weakened mainly by repeated scope-guard prose and a bundle of external references that are not present in this skill directory to verify.

Suggestions

Collapse the repeated 'not for X — use sibling-skill' scope-guard text into one canonical Scope Guard section and reference it elsewhere instead of restating it in Instructions, Reference Materials, and Next Best Skill.

Define SEND-specific terms (EQS, S1/S2/N1/D1, N-dimension sub-items) on first use or point to a single glossary reference rather than assuming the reader tracks the framework inline.

If references/scripts/ or assets/ are intended to ship with this skill, add the referenced files (skill-contract.md, send-benchmark.md, CONNECTORS.md, SECURITY.md, connectors/resend.py) to the bundle so the signaled paths resolve.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and accurate, but dense proprietary jargon ('SEND N-dimension', 'EQS', 'S1/S2/N1/D1 vetoes', 'fatigue guardrail') and the scope-guard / not-for boundaries repeated in at least three sections add length Claude could do without.	2 / 3
Actionability	Provides fully executable guidance — a concrete `resend.py broadcast-create ...` command with dry-run/--live flow, explicit profile weights (0.15/0.30/0.15/0.20), a Pass=10/Partial=5/Fail=0 scoring scale, and a named save path template.	3 / 3
Workflow Clarity	An explicit 8-step numbered process with 'Done when' criteria, Decision Gates (stop vs continue silently), consent-first and dry-run validation checkpoints, a scope guard, and a termination note with a visited-set feedback loop.	3 / 3
Progressive Disclosure	Sections are well-organized with one-level-deep, clearly signaled references (skill-contract.md, send-benchmark.md, CONNECTORS.md, SECURITY.md, sibling SKILL.md), but no references/, scripts/, or assets/ bundle exists in this skill directory to back those paths.	2 / 3
	Total	10 / 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.

A strong, well-scoped description: concrete capabilities, natural quoted triggers, explicit when-to-use, and clear boundaries against neighboring skills. It is dense and slightly long, but every clause earns its place.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions and outputs — 'trigger, step timing, branch/exit conditions, goal, frequency governance (send caps, quiet hours, fatigue guardrail), a sunset path, and a SEND N-dimension score' — rather than vague language.	3 / 3
Completeness	Explicit 'Use when the user asks to...' trigger plus a clear 'produces...' capability statement answers both what and when; the 'Not for...' boundaries further sharpen the when.	3 / 3
Trigger Term Quality	Quotes natural phrases a user would actually say — 'design a welcome flow', 'set up an abandoned-cart sequence', 'plan a cold-outbound sequence' — with good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Explicit 'Not for ... use reactivation-specialist / email-creative-builder / email-quality-auditor' carve-outs give it a clear niche unlikely to trigger sibling skills.	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: 38 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/nurture/email-sequence-designer/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.