deliverability-qa

Use when the user asks to "run a deliverability pre-flight before I send", "check my SPF/DKIM/DMARC/BIMI", "why am I landing in spam / promotions", or "score my sender reputation and list hygiene"; runs the ONE-TIME pre-send SEND S1 authentication pre-flight and builds the SEND S (Sender-integrity / Deliverability) evidence read — DNS + DMARC-RUA auth, domain/IP reputation, inbox placement, content/link/render, and point-in-time bounce/complaint hygiene — using Pass/Partial/Fail/Unknown/N/A states and scoring only at complete applicable coverage. Not for the recurring hygiene trend — use list-hygiene-monitor; not for final EQS or veto verdicts — use email-quality-auditor; not for segments/suppression lists — use list-segment-builder. 邮件送达率预检/SPF DKIM DMARC认证/发件域声誉

Quality

92%

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

85%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.

A well-structured, highly actionable pre-flight skill with clear sequencing, real validation checkpoints, and clean progressive disclosure. The main weakness is redundancy — the scope boundary is restated several times across the body.

Suggestions

Consolidate the scope guard into a single statement (currently repeated at the intro, in Instructions, in the dedicated Scope guard block, and in Next Best Skill) to recover tokens without losing the boundary.

Move the repeated 'recurring trend belongs to list-hygiene-monitor' contrast into the one Next Best Skill entry and reference it by name rather than re-explaining in each section.

Dimension	Reasoning	Score
Conciseness	Mostly task-specific content Claude lacks (DMARC/SEND framework, profile weights, thresholds), but the scope guard ('does not own the recurring trend' / 'does not compute EQS') is restated at the intro, the Instructions, the Scope guard block, and Next Best Skill — repeated 3–4 times and could be tightened. Not 3 due to this redundancy; not 1 because no basic concepts are over-explained.	2 / 3
Actionability	Executable commands ('python3 "${CLAUDE_PLUGIN_ROOT}/scripts/connectors/resend.py" domains', 'doh.py auth <domain> [--selector ...]'), concrete thresholds ('spam-complaint red line < 0.1%'), profile weights (0.30/0.20/0.35/0.25), and an exact save path give copy-ready guidance. Not 2 because the code is real and complete, not pseudocode.	3 / 3
Workflow Clarity	An 8-step numbered sequence with explicit validation checkpoints ('If the DMARC RUA report is absent…Unknown…NEEDS_INPUT — never pass-by-default', 'If no test was run…Unknown…not Pass'), a 'Done when' block, and termination rules. Not 2 because checkpoints are explicit rather than implicit.	3 / 3
Progressive Disclosure	Body points one level deep to references/deliverability-checklist.md (verified to exist) for the full checklist, with a clean Reference Materials index; cross-skill links are clearly signaled. Not 2 because the split is appropriate and navigation is easy, not nested.	3 / 3
	Total	11 / 12 Passed

Description

100%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.

A precise, third-person description with concrete capability listing, natural trigger phrasings, and strong sibling disambiguation. It cleanly answers both what the skill does and when to invoke it.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'runs the ONE-TIME pre-send SEND S1 authentication pre-flight', 'builds the SEND S…evidence read — DNS + DMARC-RUA auth, domain/IP reputation, inbox placement, content/link/render' — with explicit state labels; not 2 because coverage is comprehensive rather than partial.	3 / 3
Completeness	Explicit 'Use when…' trigger answers 'when' and the action list answers 'what' clearly; third-person voice ('runs') keeps it clean, so it is not capped at 2.	3 / 3
Trigger Term Quality	Quotes natural user phrasings — 'run a deliverability pre-flight before I send', 'check my SPF/DKIM/DMARC/BIMI', 'why am I landing in spam / promotions', 'score my sender reputation and list hygiene' — covering the common variations a user would actually say.	3 / 3
Distinctiveness Conflict Risk	Explicitly routes away siblings — 'Not for the recurring hygiene trend — use list-hygiene-monitor; not for final EQS or veto verdicts — use email-quality-auditor; not for segments/suppression lists — use list-segment-builder' — giving it a clear niche unlikely to conflict.	3 / 3
	Total	12 / 12 Passed

Validation

75%

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 — 12 / 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: 24 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/setup/deliverability-qa/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.