list-hygiene-monitor

Use when the user asks to "watch my list health over time", "flag decaying / unengaged subscribers on a schedule", "why is my open rate drifting down / bounces creeping up", or "build me a re-permission and prune worklist"; runs the scheduled SEND list-decay + suppression-drift watch — an engagement-recency cohort read (30/90/180/365-day), hard-bounce and spam-complaint trend vs benchmark, suppression-list growth/leakage check, and a segmented re-permission / sunset / prune worklist tied to SEND S (list hygiene) and E (engagement-decay) sub-items. Not for the one-time pre-send authentication pre-flight — use deliverability-qa; not for the consent/suppression record itself — use consent-registry; not for computing the EQS or enforcing vetoes — use email-quality-auditor. 邮件列表健康度监控/退订漂移/沉睡用户清理

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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.

A highly actionable, well-sequenced skill body with concrete thresholds, executable connector commands, and strong validation feedback loops for a batch subscriber operation. The only weakness is repeated restatement of the scope guard, which adds tokens without adding clarity.

Suggestions

State the scope guard once in the intro and once in the Instructions; remove the third restatement to reduce token cost without losing the disambiguation signal.

Consolidate the 'recurring not pre-flight' framing into a single sentence rather than re-explaining it in the intro, Skill Contract, and Scope guard sections.

The Skill Contract 'Expected output' and the Instructions largely cover the same ground; consider trimming the contract to outputs/handoff only and letting the numbered steps carry the process.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and assumes Claude's domain competence (no padding explaining bounces or open rates), but the scope-guard / 'recurring not pre-flight' framing is restated three times (intro, dedicated Scope guard section, and elsewhere) — repetition that could be tightened without losing the safety signal.	3 / 5
Actionability	Provides fully executable guidance: exact cohort bands (≤30d, 31–90d, 91–180d, 181–365d, >365d), a numeric spam-complaint red line (<0.1%), concrete commands ('python3 "${CLAUDE_PLUGIN_ROOT}/scripts/connectors/resend.py" contacts --limit 100', ledger record/diff), and a sized-bucket decision table.	5 / 5
Workflow Clarity	A 7-step numbered sequence with explicit validation checkpoints — 'mark NEEDS_INPUT... never invent a delta', leakage routing to the auditor, 'never pass-by-default' reads, and a send-hold gate — plus a 'Done when' checklist and feedback loops for a destructive/batch subscriber operation.	5 / 5
Progressive Disclosure	SKILL.md is a well-structured overview that pushes detail into a real one-level-deep bundle (references/hygiene-checklist.md, verified present) and clearly signals cross-skill references (send-benchmark.md, CONNECTORS.md, SECURITY.md, skill-contract.md, sibling skills); navigation is easy and nothing is nested 2+ levels.	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.

A strong, trigger-rich description that concretely states what the skill does, when to use it, and where its boundaries lie relative to sibling skills. It is dense but every clause earns its place and the negative-scope disambiguation is exemplary.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'engagement-recency cohort read (30/90/180/365-day)', 'hard-bounce and spam-complaint trend vs benchmark', 'suppression-list growth/leakage check', and a 'segmented re-permission / sunset / prune worklist' — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both 'what' (the scheduled decay + drift watch and its component reads) and 'when' (a 'Use when...' clause with concrete trigger phrases), and adds negative scope ('Not for...') to bound usage.	5 / 5
Trigger Term Quality	Quotes four natural user phrases — "watch my list health over time", "flag decaying / unengaged subscribers on a schedule", "why is my open rate drifting down / bounces creeping up", "build me a re-permission and prune worklist" — covering synonyms and variations a user would actually say.	5 / 5
Distinctiveness Conflict Risk	Carves a clear recurring-hygiene niche and explicitly disambiguates from deliverability-qa, consent-registry, and email-quality-auditor, minimizing the chance of triggering for the wrong sibling skill.	5 / 5
	Total	20 / 20 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: 27 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/list-hygiene-monitor/SKILL.md
Commit: 888dd38

Reviewed: 3 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.