What makes Email Render Builder notable?

1.1K downloads. Trust evidence available

How should Email Render Builder be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

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 cod...

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.1k

Updated

Oct 11, 2026

Version

19.0.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1.1K downloadsadoption · observed Oct 11, 2026
Latest release: 19.0.0release · observed Jul 24, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17e1tg8pjra8dn1dvtq21sahx83hrxj:email-render-builder

Install using `clawhub skill install s17e1tg8pjra8dn1dvtq21sahx83hrxj:email-render-builder` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/aaron-he-zhu/email-render-builder before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-aaron-he-zhu-email-render-builder/snapshot"

Documentation

CLAWHUB

139,306 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: email-render-builder
slug: aaron-email-render-builder
displayName: "Email Render Builder · 邮件HTML"
summary: "邮件HTML/响应式邮件/暗色模式渲染"
description: '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'
version: "19.0.0"
license: Apache-2.0
compatibility: "Claude Code and compatible agent-skill hosts"
homepage: "https://github.com/aaron-he-zhu/aaron-marketing-skills"
when_to_use: "Use when coding or QA-ing the HTML build of an email that copy is already written for: converting approved creative into a responsive table-based layout, checking dark-mode color inversion, running an accessibility pass (alt text, semantic order, contrast, font-size), producing a client-render matrix (Gmail/Outlook/Apple Mail/mobile), specifying image-off fallbacks and bulletproof buttons, and verifying the plain-text alternate matches the HTML. Covers B2C promo, B2B, and newsletter builds. Not for authoring the words, and not for the EQS gate."
argument-hint: "<email creative or HTML> [target clients] [mode: promo|cold|newsletter]"
metadata: {"author": "aaron-he-zhu", "version": "19.0.0", "discipline": "email", "phase": "engage", "geo-relevance": "low", "hermes": {"tags": ["marketing", "email", "engage"], "category": "email"}, "openclaw": {"emoji": "✉️", "homepage": "https://github.com/aaron-he-zhu/aaron-marketing-skills"}}
---

# Email Render Builder

Builds and QAs the coded HTML for a single email — a responsive table-based layout, a dark-mode + accessibility pass, a client-render matrix, image-block fallbacks with bulletproof CTAs, and a plain-text-parity check. This is the render half of SEND **Engage**: `email-creative-builder` writes the words, this skill turns them into a build that lands the same in Gmail, Outlook, Apple Mail, and on mobile. It does not write copy, and it does not score the email or run any veto — that is `email-quality-auditor`.

**Scope guard**: this skill produces the HTML build + render QA + plain-text parity only. It writes no subject-line or body *copy* ([email-creative-builder](../email-creative-builder/SKILL.md) owns that), scores no SEND dimension, runs no veto, and does not compute the profile-weighted EQS — [email-quality-auditor](../../deliver/email-quality-auditor/SKILL.md) owns all four vetoes (S1/S2/N1/D1) and the EQS rollup.

## Quick Start

```
Build responsive HTML from this creative: [paste subject + body + CTA], destination [URL]
```

```
QA this email HTML across Gmail, Outlook, Apple Mail, and mobile: [paste HTML]. Flag dark-mode and image-off breakage.
```

```
This renders broken in Outlook and images-off — fix the lay

_meta.json

{
  "ownerId": "kn73qjxwmbna25qq8q051epqt980sys5",
  "slug": "email-render-builder",
  "version": "19.0.0",
  "publishedAt": 1784903681955
}

references/client-render-matrix.md

# Client Render Matrix (SEND-E QA)

The per-client support facts `email-render-builder` uses to fill the render-QA matrix. **Every row is Estimated** unless the user ran a real seed-list / inbox-preview test — then that row is Measured. Never present an Estimated render pass as Measured; name the row a call came from.

## Target set (default)

Gmail (app + web), Outlook (desktop Word-engine + web/new Outlook), Apple Mail, iOS Mail, Android (Gmail/Samsung Mail).

## Support facts (Estimated baseline)

| Client | Rendering quirk to check | Common breakage |
|---|---|---|
| **Outlook desktop** | Word (`mso`) engine — no `float`/`flex`/`grid`, spotty `border-radius`, needs ghost tables + VML buttons | broken multi-column, square/clipped buttons, extra gaps |
| **Gmail (web + app)** | strips/relocates `<head>` `<style>`; clips messages >102KB ("[Message clipped]") | media queries dropped, dark-mode auto-inversion, clipped tail |
| **Apple Mail / iOS Mail** | strong CSS + media-query support; aggressive dark-mode inversion | logos/text lost on forced-dark backgrounds |
| **Android (Gmail/Samsung)** | mixed dark-mode handling; smaller tap targets | reflow gaps, sub-44px tap targets |
| **Outlook web / new Outlook** | closer to standards than desktop; still partial | dark-mode + `<style>` handling differs from desktop |

## Matrix template (fill per email)

| Client | Layout | Dark mode | Images-off | Verdict | Label |
|---|---|---|---|---|---|
| Gmail web | ✓ / ✗ | ✓ / ✗ | ✓ / ✗ | pass/fail + note | Measured/Estimated |
| Gmail app | | | | | |
| Outlook desktop | | | | | |
| Outlook web | | | | | |
| Apple Mail | | | | | |
| iOS Mail | | | | | |
| Android | | | | | |

## Labeling rule

- **Measured** — the user ran a seed-list / inbox-preview / render-preview test and you read the actual render.
- **Estimated** — derived from the support facts above; no real render seen. State it plainly and, where a client's behavior is genuinely unknown, return it as an open loop rather than guessing a pass.

Keyed render-preview services (Litmus, Email on Acid) are an optional Tier-2/3 convenience that can upgrade a row to Measured; they are never a Tier-1 precondition.

references/email-render-specs.md

# Email Render Specs (SEND-E build)

Build patterns and QA checklists for `email-render-builder`. The layout carries the approved copy from [email-creative-builder](../../email-creative-builder/SKILL.md) unchanged; this pack governs the *build*, not the words. All checklists feed the render-QA report that [email-quality-auditor](../../../deliver/email-quality-auditor/SKILL.md) reads before scoring the E/D unit.

## Layout skeleton

- **Table-based, single column.** Nested `<table>`/`<td>` for structure — not `float`, `flex`, or `grid` (Outlook's Word rendering engine ignores them).
- **Constrained width ≈600px** content area inside a full-width background wrapper; content column set with a fixed `width` attribute *and* inline `max-width` so mobile can reflow.
- **Inline styles only** for anything load-bearing; a `<style>` block may hold media queries and dark-mode rules but must degrade gracefully — Gmail strips/relocates `<head>` styles.
- **No external dependency** — no linked stylesheet, no web-font `@import` that blocks render; use a system-font stack with brand-font as an enhancement only.

## Responsive approach

| Approach | How | Client support |
|---|---|---|
| **Fluid / hybrid** | percentage widths + `max-width` + `mso` ghost tables | widest — works even where media queries are stripped |
| **Media-query** | `@media max-width` reflow in `<style>` | good on Apple/iOS/Android; unreliable on some Gmail/Outlook contexts |

Default to fluid/hybrid for a broad target set; note the choice. Tap targets ≥44px; body font ≥14px (≥16px preferred) so mobile reads without zoom.

## Dark-mode checklist (pass / fail each)

- [ ] Explicit `color` + `background-color` set on text containers (do not rely on client defaults).
- [ ] Every foreground/background pair passes contrast in **light** mode (≥4.5:1 body text).
- [ ] Every pair still passes after a **dark-mode inversion** (text not buried, logo not lost on a now-dark panel).
- [ ] Logos / dark-on-transparent images have a padded solid backing or a dark-mode variant.
- [ ] No color-only meaning (a link is underlined/bolded, not only colored).

## Accessibility checklist (pass / fail each)

- [ ] Semantic reading order — content order in source matches visual order.
- [ ] Meaningful `alt` on every content image; `alt=""` only for pure decoration.
- [ ] `lang` attribute set; a real `<title>`/preheader present.
- [ ] Body contrast ≥4.5:1; base font size holds on mobile.
- [ ] Links are descriptive (no bare "click here" as the only cue).

## Image-off fallbacks (required)

Many clients block images by default — the email must still work.

- Every image has `alt` text that conveys its message.
- **No offer, price, claim, or CTA lives only inside an image.**
- Background images carry a solid `bgcolor` fallback.
- Each CTA is a **bulletproof button** — HTML/CSS, not an image:

```html
<!--[if mso]><v:roundrect ... fillcolor="#1a56db"><![endif]-->
<a href="{{DEST_URL}}" style="background:#1a56db;color:#ffffff

skill-card.md

## Description:

Builds responsive email HTML and render-QA handoffs from approved email creative or existing HTML, including dark-mode, accessibility, image-off, client-render, and plain-text parity checks.

This skill is ready for commercial/non-commercial use.

## Publisher:

[aaron-he-zhu](https://clawhub.ai/user/aaron-he-zhu)

### License/Terms of Use:

MIT-0

## Use Case:

Developers, email marketers, and marketing operations teams use this skill to convert approved email creative into responsive table-based HTML and to produce a render-QA report across common email clients. It is intended for build and QA work, not copywriting, scoring, or campaign sending.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Generated email HTML or render-QA guidance may be incorrect for a target client if it is not verified with a real seed-list or inbox-preview test.

Mitigation: Treat untested render results as Estimated, run a seed or inbox-preview test for important sends, and review the client-render matrix before deployment.

Risk: A live ESP render test can send email if the user explicitly chooses that path.

Mitigation: Use only verified sender identities and the user's own test inboxes, and treat any live send as an explicit action requiring confirmation.

Risk: The skill may save render-QA handoff summaries to memory after confirmation.

Mitigation: Review saved handoffs for sensitive campaign, brand, or customer data before confirming persistence.

## Reference(s):

- [ClawHub Skill Page](https://clawhub.ai/aaron-he-zhu/skills/email-render-builder)
- [Project Homepage](https://github.com/aaron-he-zhu/aaron-marketing-skills)
- [Email Render Specs](references/email-render-specs.md)
- [Client Render Matrix](references/client-render-matrix.md)

## Skill Output:

**Output Type(s):** [Markdown, Code, Configuration instructions, Guidance]

**Output Format:** [Markdown with email HTML code and render-QA checklist sections]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [May include client-render pass/fail rows, accessibility and dark-mode checks, image-off fallback notes, plain-text parity, and handoff summary text.]

## Skill Version(s):

19.0.0 (source: server release metadata and SKILL.md frontmatter)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 2d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.