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

91%

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

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.

The body is a strong, highly actionable workflow: sequenced steps with concrete thresholds, decision gates with defaults, an explicit quality bar, and clean one-level-deep progressive disclosure into two real, well-scoped reference files. Its main weakness is token efficiency — the scope boundary and labeling rules are repeated across sections and could be stated once.

Suggestions

State the scope boundary (no copy, no EQS scoring, no veto) once — in the Scope guard paragraph — and reduce the restatements in the intro, Skill Contract, and Next Best Skill to a single short pointer, saving roughly 15% of the body.

Merge the Measured/Estimated rule from the closing paragraph into step 7 (or the client-render-matrix reference) so it appears exactly once in the body.

Trim the 'many clients default to off' and 'deliverability + accessibility hygiene' asides in steps 6 and 7 — the motivation already lives in references/email-render-specs.md.

DimensionReasoningScore

Conciseness

The scope boundary ('does not write copy, does not score, use email-quality-auditor') is restated four times (intro, Scope guard paragraph, Skill Contract, Next Best Skill), and the Measured/Estimated labeling rule is stated both in step 7 and again in the closing paragraph — a systematic tightening opportunity that goes beyond the 'minor instances' of the 4 anchor. Domain facts (Outlook Word engine, Gmail style stripping) are skill-specific rather than general knowledge, so they are not penalized.

3 / 5

Actionability

Guidance is fully executable: concrete thresholds (≈600px content width, tap targets ≥44px), named per-client breakages (Outlook 'mso' conditionals, Gmail '<style>' stripping), a copy-paste resend render-test command with explicit authorization gating, exact payload-hash binding, and specific defaults in the Decision Gates. As an instruction-only skill, its procedures cover the common cases completely; not 4 because no significant execution gap remains in the body.

5 / 5

Workflow Clarity

Eleven clearly sequenced steps with explicit validation checkpoints: Decision Gates with numbered stop/continue outcomes, a six-item Quality Bar checked before handoff ('If any item fails, fix it or report it in the handoff'), a 'Done when' contract, and feedback loops that route copy-affecting defects back to email-creative-builder. This matches the anchor with explicit validation, error-recovery loops, and checklists; not 4 because no meaningful checkpoint is missing.

5 / 5

Progressive Disclosure

Verified against the actual bundle: both referenced files (references/email-render-specs.md, references/client-render-matrix.md) exist, hold the detailed specs and support matrix, are one level deep, and are clearly signaled in a Reference Materials section with descriptions, while the body stays an executable overview. Matches the clear-overview anchor; the many cross-skill links are routing pointers within the larger skill family, not nested content.

5 / 5

Total

18

/

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.

The description is exemplary: it combines an explicit 'Use when' clause with four quoted natural trigger phrases, a precise list of five concrete outputs, third-person voice, and explicit negative scope that disambiguates it from sibling skills (creative builder, quality auditor). Bilingual keywords add trigger coverage without introducing fluff.

DimensionReasoningScore

Specificity

Lists five concrete deliverables — 'a responsive table layout, dark-mode + accessibility pass, a client-render matrix, image-block fallbacks, and a plain-text parity check' — which is comprehensive coverage of the skill's output surface, matching the anchor for multiple specific concrete actions rather than the 'minor gaps' of a 4.

5 / 5

Completeness

Explicitly answers both questions: an explicit 'Use when...' clause with concrete trigger phrases, and a clear 'what' ('produces the coded HTML build' with the five named outputs). Both what and when are explicit with concrete triggers, so it is not the 4 anchor where the 'when' could be more specific.

5 / 5

Trigger Term Quality

Quotes four natural user phrasings ('build the email HTML', 'make this email responsive', 'fix dark-mode rendering', 'QA the email across clients') spanning every task type, and adds Chinese synonyms (邮件HTML/响应式邮件/暗色模式渲染), giving comprehensive natural-term coverage including synonyms rather than merely 'good coverage with a few missing'.

5 / 5

Distinctiveness Conflict Risk

Clear niche with explicit negative routing ('Not for writing the copy — use email-creative-builder; not for scoring the email or computing EQS — use email-quality-auditor'), minimizing conflict risk with adjacent skills in the same family. It is not the 4 anchor because the disambiguation is explicit rather than leaving minor overlap risk.

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.