email-render-builder

Use when the user asks to "build the email HTML", "make this email responsive", "fix dark-mode rendering", or "QA the email across clients"; produces the coded HTML build — a responsive table layout, dark-mode + accessibility pass, a client-render matrix, image-block fallbacks, and a plain-text parity check. Not for writing the copy — use email-creative-builder; not for scoring the email or computing EQS — use email-quality-auditor. 邮件HTML/响应式邮件/暗色模式渲染

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.

A well-structured build-and-QA skill: clear sequenced workflow with validation checkpoints and feedback loops, actionable thresholds and an executable send command, and clean one-level-deep progressive disclosure to two verified reference files. The main weakness is token redundancy — the quality bar and the no-copy/no-scoping boundary each repeat ~3×.

Suggestions

Consolidate the redundant quality-bar checklist: it appears near-verbatim in the numbered instructions, the Skill Contract 'Done when', and the 'Quality bar before handoff' block — keep one canonical list and reference it from the others.

State the 'does not write copy / does not score' disambiguation once (the Scope Guard) and drop its repetition in the intro paragraph and Next Best Skill section.

Add a minimal inline bulletproof-button or table-skeleton snippet so the primary HTML deliverable has a copy-paste anchor without requiring the reference file for the first build step.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence (no basic-concept explanations), but the 6-point quality bar recurs nearly verbatim in the numbered instructions, the Skill Contract 'Done when', and the 'Quality bar before handoff' block, and the no-copy/no-scoring disambiguation repeats across the intro, Scope Guard, and Next Best Skill — so not every token earns its place. Not score 1 because there is no concept-explaining fluff; not score 3 because of the structural repetition.	2 / 3
Actionability	Concrete thresholds (tap targets ≥44px, content width ≈600px), one copy-paste-ready command ('python3 "${CLAUDE_PLUGIN_ROOT}/scripts/connectors/resend.py" send … --live'), named pass/fail checks, and the Measured/Estimated labeling rule give specific executable guidance; the primary HTML build patterns are deliberately externalized to references, which the instruction-skill carve-out does not penalize when guidance is actionable.	3 / 3
Workflow Clarity	Ten sequenced numbered steps with an explicit 'Quality bar before handoff' checklist, Decision Gates (stop-and-ask vs continue-silently), and feedback loops (defects routed back to email-creative-builder; 'fix it or report it in the handoff — do not ship silently') match the clear-sequence-with-validation-and-checklists anchor.	3 / 3
Progressive Disclosure	The body is an overview pointing one level deep to two real, clearly-signaled bundle files (references/email-render-specs.md and references/client-render-matrix.md, both verified present) via markdown links and a Reference Materials section; content is appropriately split with no nested-reference chains.	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 description: concrete multi-action capability list, natural trigger phrases, explicit what-and-when structure, and clear disambiguation from adjacent skills. It uses the accepted 'Use when…' imperative pattern rather than penalized first/second person.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'a responsive table layout, dark-mode + accessibility pass, a client-render matrix, image-block fallbacks, and a plain-text parity check' — matching the multi-action anchor rather than the single-domain score-2 example.	3 / 3
Completeness	Explicitly answers both halves: 'Use when the user asks to…' (when) and 'produces the coded HTML build — …' (what), satisfying the what-AND-when-with-explicit-triggers anchor; not the score-2 case where 'when' is only implied.	3 / 3
Trigger Term Quality	Natural user-facing phrases ('build the email HTML', 'make this email responsive', 'fix dark-mode rendering', 'QA the email across clients') plus Chinese variants give broad coverage of terms a user would actually say, not jargon.	3 / 3
Distinctiveness Conflict Risk	Explicitly carves a niche from siblings — 'Not for writing the copy — use email-creative-builder; not for scoring the email or computing EQS — use email-quality-auditor' — making wrong-skill triggering unlikely.	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: 19 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/engage/email-render-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.