email-quality-auditor

Use when the user asks to "audit an email program" or "is this campaign safe to send"; runs a typed 20-item SEND profile with authentication, consent, opt-out, and claim veto checks on own evidence. Not for building deliverability setup — use deliverability-qa; not for designing lifecycle flows — use email-sequence-designer. 邮件质量审计/EQS评分/发送前放行

Quality

82%

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

70%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.

The body is a well-structured, validation-conscious auditor workflow with explicit checkpoints and revalidate loops, but its actionability relies heavily on external runtime files, several referenced paths are not bundled in this install, and some shorthand/section numbering could be tightened for token efficiency.

Suggestions

Inline at least one minimal executable scorer invocation or concrete command so the skill is actionable even when external runtime files are unavailable in a standalone install.

Reconcile reference paths with the actual bundle: only auditor-runtime.md is present, so either bundle auditor-runbook.md, scoring-semantics.md, send-benchmark.md, measurement-protocol.md, and runtime-invocation.md or rewrite the in-body references to the bundled runtime file.

Reduce shorthand ('§2/§3/§5', 'S1..D5') repetition and consolidate the worked-examples and guardrails sections to lower token cost without losing the validation guidance.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and dense with domain value (e.g., the SEND worked examples and guardrails), but several sections restate concepts and the shorthand 'S1..D5' and '§2/§3/§5' numbering assume context the reader must reconstruct; some tightening is possible.	2 / 3
Actionability	Guidance is concrete in places (verify vetoes, score 20 criteria, resolve AARON_SKILLS_ROOT) but the executable core lives in referenced runtime/scorer files rather than inline, and most 'examples' are outcome labels (DONE/SHIP) rather than copy-paste-ready commands.	2 / 3
Workflow Clarity	A clear sequenced audit flow is laid out (declare profile -> freeze/reconcile evidence -> score 20 criteria -> verify vetoes -> run scorer -> report) with explicit validation checkpoints ('Validation Checkpoints') and a feedback/persistence-revalidate loop for the destructive write step.	3 / 3
Progressive Disclosure	References are listed and mostly one level deep, but several in-body paths (auditor-runbook.md, scoring-semantics.md, send-benchmark.md, measurement-protocol.md, runtime-invocation.md) point outside the bundle and only auditor-runtime.md is actually bundled; navigation is signaled but some referenced files are absent from this install.	2 / 3
	Total	9 / 12 Passed

Description

95%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.

The description is specific, trigger-rich, and explicitly scopes both what and when, including active disambiguation against sibling skills. It uses appropriate third-person voice and avoids vague fluff, though the appended Chinese gloss and trailing summary line add mild redundancy.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: 'runs a typed 20-item SEND profile with authentication, consent, opt-out, and claim veto checks on own evidence', naming specific checks rather than abstract capability language.	3 / 3
Completeness	Explicitly answers both what (runs a 20-item SEND profile with specific checks) and when ('Use when the user asks to "audit an email program" or "is this campaign safe to send"'), with an explicit trigger clause.	3 / 3
Trigger Term Quality	Provides natural trigger phrases a user would say ('audit an email program', 'is this campaign safe to send') plus concrete keywords (authentication, consent, opt-out, DMARC) covering common variations.	3 / 3
Distinctiveness Conflict Risk	Defines a clear niche and actively disambiguates by naming what it is NOT for ('Not for building deliverability setup — use deliverability-qa; not for designing lifecycle flows — use email-sequence-designer'), minimizing wrong-skill triggering.	3 / 3
	Total	12 / 12 Passed

Validation

81%

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 — 13 / 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: 9 suspicious	Warning

	Total	13 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: email/deliver/email-quality-auditor/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.