CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

73%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-engineered instruction-only skill body: concrete thresholds, a clearly sequenced 11-step workflow with decision gates and validation checklists, and a clean two-file reference bundle that genuinely holds the detailed specs. Its main weakness is redundancy — the skill's scope boundaries and done-criteria are each stated multiple times, which inflates token cost without adding guidance.

Suggestions

State the "writes no copy, scores nothing, runs no veto" boundary once (the Scope guard paragraph) and drop its repetition from the intro, Skill Contract, and Next Best Skill sections.

Merge the Quality bar checklist with the overlapping "Done when" criteria into a single pre-handoff checklist instead of two near-verbatim lists.

In steps 4–8, replace the inline restatements of the dark-mode/accessibility/image-off checklists with one-line pointers to references/email-render-specs.md, keeping only the decision-relevant summary in the body.

DimensionReasoningScore

Conciseness

Mostly efficient and free of beginner-concept padding, but the "writes no copy / scores nothing" boundary is repeated in at least four places (intro, Scope guard, Skill Contract, Next Best Skill) and the Quality bar restates the "Done when" criteria almost verbatim, so it could be meaningfully tightened.

3 / 5

Actionability

Concrete, executable guidance throughout — specific thresholds (≈600px column, ≥44px tap targets, ≥4.5:1 contrast), a copy-paste-ready resend.py render-test command with authorization gating, and named breakage modes (Outlook mso conditionals, Gmail <style> stripping). The core HTML/table skeleton itself is only in the reference file, not shown inline — a minor gap.

4 / 5

Workflow Clarity

Eleven numbered steps in a coherent build→QA→bind→report sequence, a Decision Gates section with explicit stop-and-ask vs continue-silently rules, a pre-handoff quality-bar checklist as a validation gate, and a feedback loop (step 10 routes copy-affecting fixes back to email-creative-builder instead of silently editing).

5 / 5

Progressive Disclosure

The two bundle references (references/email-render-specs.md, references/client-render-matrix.md) are real, one level deep, and clearly signaled in Reference Materials with descriptions; the body stays overview-level. Minor gaps: steps 4–8 inline summaries duplicate the reference checklists, and many multi-hop out-of-bundle links add navigational noise.

4 / 5

Total

16

/

20

Passed

Description

100%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.

An exemplary description: concrete deliverables, natural quoted trigger phrases, explicit when-guidance, and hard boundaries against adjacent skills. The only blemish is the trailing Chinese keyword string ("邮件HTML/响应式邮件/暗色模式渲染") which duplicates content already conveyed, but it adds bilingual trigger coverage and does not dilute clarity.

DimensionReasoningScore

Specificity

The description enumerates five concrete deliverables — "a responsive table layout, dark-mode + accessibility pass, a client-render matrix, image-block fallbacks, and a plain-text parity check" — giving comprehensive, non-generic coverage of the build+QA scope with no gaps.

5 / 5

Completeness

It explicitly answers both questions: an explicit "Use when the user asks to…" clause with concrete trigger phrases, and a clear what ("produces the coded HTML build" with the enumerated artifacts). It also adds explicit not-for boundaries.

5 / 5

Trigger Term Quality

Quoted natural trigger phrases ("build the email HTML", "make this email responsive", "fix dark-mode rendering", "QA the email across clients") cover the ways a user would actually phrase the request, supplemented by Chinese-language synonyms; nothing a user would naturally say is missing.

5 / 5

Distinctiveness Conflict Risk

Clear niche (coded HTML build + render QA) with explicit disambiguation from the two nearest neighbors — "Not for writing the copy — use email-creative-builder; not for scoring the email or computing EQS — use email-quality-auditor" — so conflict risk is minimal.

5 / 5

Total

20

/

20

Passed

Validation

75%

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

CriteriaDescriptionResult

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: 21 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

Reviewed

Table of Contents

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.