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

88%

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 1-5

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 sequencing, validation checkpoints, and appropriate progressive disclosure into real reference files. The main improvement opportunity is trimming the redundant scope/boundary language that re-appears from the description into the body's opening.

Suggestions

Collapse the repeated boundary disambiguation in the intro paragraph and 'Scope guard' since it already appears verbatim in the description; keep one concise scoping statement.

Add one short inline example of the expected output artifact (e.g., a minimal subject-line + preheader + CTA + plain-text block) to push actionability from mostly-executable to fully copy-paste ready.

The handoff hash/freezing step (step 11) describes the process abstractly; a one-line concrete command or field template for creative_ref/version would make it executable rather than descriptive.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence (no basic-concept padding), but the opening paragraph and 'Scope guard' repeat the boundary clauses already in the description, which could be trimmed — efficient with minor over-explanation rather than perfectly lean.	4 / 5
Actionability	Paste-ready Quick Start prompts, a numbered 11-step procedure with concrete file references, and an exact output shape give mostly executable guidance; it is instruction-style with no inline code, which is acceptable for an instruction skill but keeps it just shy of fully copy-paste ready.	4 / 5
Workflow Clarity	An explicit 11-step sequence is reinforced by a handoff Quality-bar checklist, Done-when criteria, and Decision Gates, with feedback loops ('fix it or report it… do not ship silently', unresolved claims blocking ready-to-send) matching the level-5 anchor.	5 / 5
Progressive Disclosure	Mode pattern sets and subject-line specs are split into real one-level-deep reference files (email-creative-modes.md, subject-line-specs.md, both present in ./references/), clearly signaled with one-line descriptions and easy navigation from the Reference Materials section.	5 / 5
	Total	18 / 20 Passed

Description

92%Weight 40%Scale 1-5

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, third-person description that explicitly states both what it produces and when to use it, with thorough negative-boundary disambiguation from sibling skills. Its only gap is slightly narrower trigger-term coverage (a few common English phrasings absent) preventing a perfect trigger_term_quality score.

Suggestions

Add a few more natural English trigger phrases (e.g., 'email copy', 'cold email', 'newsletter draft') to round out trigger-term coverage.

The trailing '邮件文案/主题行/邮件创意' duplicates the summary; consider folding non-English synonyms more deliberately into the trigger list rather than appending them.

The 'produces the pre-click unit' phrasing is framework-jargon-heavy; a plainer restatement of the deliverable could aid natural triggering without sacrificing specificity.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — subject-line variants, preheader, body copy, one CTA, plain-text alt, message-matching, claims-ledger-awareness — for comprehensive coverage matching the level-5 anchor.	5 / 5
Completeness	Explicit 'Use when the user asks to...' clause with concrete trigger phrases plus a clear 'what' (produces the pre-click E/D unit) and extensive not-for boundaries — both what and when are explicitly and concretely answered.	5 / 5
Trigger Term Quality	Includes natural user phrases ('write the email', 'draft subject lines', 'build email creative') plus Chinese synonyms, but misses common English variations like 'email copy', 'cold email', or 'newsletter draft' that would warrant a 5.	4 / 5
Distinctiveness Conflict Risk	Four explicit 'not for X — use skill-Y' disambiguations (subject-line-lab, email-quality-auditor, email-sequence-designer, send-experiment-designer) carve a clear niche with minimal conflict risk.	5 / 5
	Total	19 / 20 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: 19 suspicious	Warning

	Total	13 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: email/engage/email-creative-builder/SKILL.md
Commit: 888dd38

Reviewed: 6 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.