Email Render Builder
Turns approved email creative into responsive, cross-client HTML and delivers a structured render QA report.
The skill treats HTML and other supplied assets as untrusted data and forbids embedded instructions from being executed. Sending is dry-run by default, requires explicit --live, is limited to the user's own test inboxes, and result persistence requires confirmation. Deducted 6 points because memory writes, data-flow boundaries, rollback, and sensitive email-data handling are not fully specified; publisher identity is unverified.
The instructions are internally coherent and include input confirmation, a NEEDS_INPUT path, Estimated/Measured labeling, abnormal-input routing, and quality gates. The cited references add concrete rules. Deducted 11 points because static files do not show skill-specific execution tests or controlled runtime failure feedback; the static ceiling also prevents a higher score.
Triggers, inputs, outputs, non-fit boundaries, default clients, and next-skill routing are clearly stated, covering B2C, B2B, and newsletter builds. Deducted 4 points because Chinese-language email and mainland-China client/network fit are not demonstrated, while some client behavior remains Estimated. Core functionality does not entirely depend on overseas services.
The skill has a standard contract, Quick Starts, an argument hint, versioning, Apache-2.0 licensing, references, decision gates, and limitation disclosures. Deducted 4 points because no skill-specific changelog, named maintenance responsibility, or update path is supplied; compatibility evidence is mainly repository-level.
The intended result is a directly usable HTML build plus render matrix, accessibility, dark-mode, image-off, and plain-text-parity QA. Static calibration caps this at 7; no representative output or real client-render evidence is included, so completeness and practical effectiveness cannot be verified. Deducted 8 points.
The skill requires real seed or inbox-preview evidence for Measured results and otherwise requires Estimated labels, with unknown behavior returned as an open loop. Repository-level tests and CI provide some auditable material. Deducted 5 points because there are no skill-specific key-path tests, real render records, or independently corroborating sources; static review cannot exceed 5.
- Without a real seed-list or inbox-preview test, every client-render result must remain Estimated; do not claim Gmail, Outlook, or mobile support as verified.
- If Resend --live is used, the user should explicitly confirm the sender, inboxes, and idempotency; the skill does not define a complete pre-send approval record or rollback process.
- Email content, URLs, and brand assets may be sensitive, but redaction, retention, and memory-access controls are not specified.
- Chinese email, Chinese font behavior, mainland-common clients, and mainland-China network reachability should be validated separately.
What does this skill do, and when should you use it?
Email Render Builder focuses on coded HTML production and render QA for a single email. It does not write copy or calculate email quality scores. The skill builds a responsive table layout and checks dark mode, accessibility, image-off fallbacks, bulletproof buttons, and plain-text parity. It also produces a Gmail, Outlook, Apple Mail, and mobile client-render matrix. Without a real seed test, render findings must remain labeled Estimated.
Reads approved email creative or raw HTML, the destination URL, message mode, target clients, and brand constraints; produces an inline-styled, single-column responsive table layout at approximately 600px width; checks dark-mode contrast, semantic order, image alt text, font size, and button accessibility; adds image-off fallbacks including alt text, solid background colors, and HTML/CSS buttons; outputs a client pass/fail matrix, render QA report, and a plain-text alternate carrying the same core message and links as the HTML.
- A marketer has approved promotional copy and needs a responsive HTML build for Gmail, Outlook, and mobile.
- An email developer needs to diagnose an Outlook layout break caused by table or CSS compatibility.
- A brand team needs to verify that text, backgrounds, and logos remain readable in dark mode.
- An email operator needs to ensure the offer and CTA still work when images are blocked.
- A team needs a pre-send check that the HTML and plain-text versions share the same message and links.
What are this skill's strengths and limitations?
- Covers responsive table layout, dark mode, accessibility, image-off fallbacks, and plain-text parity.
- Clearly distinguishes Measured results from Estimated support-matrix expectations.
- Supports B2C promotional, B2B, and newsletter builds.
- Hands off naturally to email-quality-auditor for SEND scoring and pre-send review.
- Does not write subject lines, body copy, or CTA wording; approved creative is required.
- Does not score SEND dimensions, calculate EQS, or run auditor vetoes.
- Without a real seed list or preview test, client-render results remain Estimated.
- A destination URL is required to confirm CTA message match.
How do you install this skill?
In Claude Code, run /plugin marketplace add aaron-he-zhu/aaron-marketing-skills, then /plugin install aaron-marketing@aaron. On a compatible generic Agent Skills host, run npx skills add aaron-he-zhu/aaron-marketing-skills -s aaron-email-render-builder. You can also clone the repository with git clone https://github.com/aaron-he-zhu/aaron-marketing-skills.
How do you use this skill?
Provide approved creative or HTML, the destination URL, mode, and target clients. Example: Build responsive HTML from this creative: [paste subject + body + CTA], destination [URL]. For QA, use: QA this email HTML across Gmail, Outlook, Apple Mail, and mobile: [paste HTML]. Flag dark-mode and image-off breakage.
How does this skill compare with similar options?
It pairs with email-creative-builder in the same repository: that skill owns the words, while this one owns HTML construction and render QA. email-quality-auditor owns scoring and SEND vetoes, which are outside this skill's scope.