email-creative-builder

Use when the user asks to "write the email", "draft subject lines", or "build email creative"; produces the pre-click unit — subject-line variants + preheader, body copy, one clear CTA, and a plain-text alt — message-matched to the destination page and claims-ledger-aware. Not for pre-scoring or ranking subject-line variants (spam/truncation/render pre-score) — use subject-line-lab; not for scoring the email or computing EQS — use email-quality-auditor; not for the multi-step flow — use email-sequence-designer; not for the A/B test plan — use send-experiment-designer. 邮件文案/主题行/邮件创意

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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.

A well-structured, actionable instruction skill with clear workflow sequencing, validation checkpoints, and verified one-level-deep references. The main weakness is mild redundancy of the sibling-skill disambiguation across three sections.

Suggestions

Consolidate the 'does not score / not email-quality-auditor / not sequence-designer' disambiguation so it appears once (e.g. in Scope Guard or Next Best Skill) rather than in the intro, Scope Guard, and Next Best Skill.

Consider moving the SEND/D1/EQS vocabulary gloss into the email-creative-modes reference if any readers may not share the domain lexicon, keeping the body leaner.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes competence (no 'what is an email' filler), but the sibling-skill boundaries are restated three times — intro paragraph, Scope Guard, and Next Best Skill — which a tighter draft would consolidate. Fits 'mostly efficient but could be tightened' rather than the fully-lean top anchor.	2 / 3
Actionability	As an instruction-only skill it gives concrete, specific guidance: 'extract the page's headline, primary value prop, the concrete offer/claim, and the CTA', '3-5 distinct subjects (curiosity, benefit, offer, personalization, question)', and 'annotate each claim-bearing line with the destination claim it echoes'. The scoring note excuses the absence of code since guidance is actionable.	3 / 3
Workflow Clarity	A 10-step numbered sequence is backed by explicit Decision Gates (stop-and-ask vs continue-silently), a 'Done when' criteria block, and a pre-handoff quality-bar checklist with validation steps (message-match enforcement, claim resolution, de-slop pass).	3 / 3
Progressive Disclosure	Body signals two real one-level-deep local references (references/email-creative-modes.md and references/subject-line-specs.md, both present on disk) plus clearly labeled shared repo references, with a clean section structure for navigation.	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.

A strong, well-scoped description: it states concrete outputs, opens with natural trigger phrasing, and sharply distinguishes itself from four adjacent skills. No meaningful weaknesses against the rubric.

Dimension	Reasoning	Score
Specificity	Names multiple concrete deliverables — 'subject-line variants + preheader, body copy, one clear CTA, and a plain-text alt — message-matched to the destination page' — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both what (the pre-click unit and its components) and when (an explicit 'Use when...' clause with triggers), matching the top anchor; third-person voice is maintained.	3 / 3
Trigger Term Quality	Open 'Use when the user asks to "write the email", "draft subject lines", or "build email creative"' uses natural phrasing a user would actually say, with good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Disambiguates four sibling skills by name (subject-line-lab, email-quality-auditor, email-sequence-designer, send-experiment-designer) with explicit 'not for...' boundaries, giving a clear niche unlikely to trigger the wrong skill.	3 / 3
	Total	12 / 12 Passed

Validation

81%

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 — 13 / 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: 17 suspicious	Warning

	Total	13 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: email/engage/email-creative-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.