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

86%

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

81%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-structured, validation-rich audit workflow with concrete tooling guidance and clear sequencing. The main gap is progressive-disclosure: most detailed references it cites are external to the bundle rather than co-located.

Suggestions

Either bundle the cited ../../../references/*.md files (auditor-runbook, scoring-semantics, send-benchmark, runtime-invocation, measurement-protocol) or clearly mark them as plugin-level external deps so the bundle's reference set is self-consistent.

Expand the terse §2/§3/§5 sections with one inline sentence each so the body is actionable without forcing a runbook read for common cases.

Consolidate the three reference lists (Runtime Reads, Runtime and Setup prose, Reference Materials) into a single labeled section to avoid duplicate/overlapping path mentions.

Dimension	Reasoning	Score
Conciseness	Dense, jargon-bearing prose that assumes Claude's competence with no concept-over-explanation; a few sections (§2/§3/§5) are terse enough to require the external runbook to act, keeping it just shy of lean.	4 / 5
Actionability	Provides concrete identifiers and commands (score 'S1..D5', resolve AARON_SKILLS_ROOT, validate-audit-artifact.py --relative-path) with mostly executable guidance; some execution detail lives in the external runbook.	4 / 5
Workflow Clarity	Clearly sequenced Runtime → Evidence/Scoring → Report → Validation Checkpoints → Persistence flow with explicit validation checkpoints and a validate→persist-once→revalidate feedback loop for the persistent-artifact writes.	5 / 5
Progressive Disclosure	Good structure with a clear Reference Materials list and Next Best Skill pointers that are well-signaled and one level deep; however the body references five ../../../references/*.md files while the bundle ships only references/auditor-runtime.md, a real organization mismatch.	4 / 5
	Total	17 / 20 Passed

Description

92%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.

A strong, third-person description that clearly states capabilities, gives concrete trigger phrases, and disambiguates from sibling skills. Trigger-term coverage is the only slightly weaker dimension, missing a few plain-language variations.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'runs a typed 20-item SEND profile with authentication, consent, opt-out, and claim veto checks on own evidence' — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both what (the 20-item SEND profile with named checks) and when (concrete 'Use when...' triggers), with negative boundary guidance to sibling skills.	5 / 5
Trigger Term Quality	Includes natural trigger phrases ('audit an email program', 'is this campaign safe to send') plus EQS/SEND, but a few common layperson synonyms are missing; good but not exhaustive coverage.	4 / 5
Distinctiveness Conflict Risk	Clear email send-gate niche with explicit conflict avoidance — 'Not for building deliverability setup — use deliverability-qa; not for designing lifecycle flows — use email-sequence-designer' — minimizing wrong-skill triggers.	5 / 5
	Total	19 / 20 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: 888dd38

Reviewed: 1 day 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.