preference-frequency-manager

Use when the user asks to "build a preference center", "set up a frequency opt-down ladder", "give people a step-down instead of unsubscribe", or "design a topic/cadence preference page"; produces a preference-center field spec, a frequency/topic opt-down ladder (down-tier paths that substitute for a hard unsubscribe), a preference-to-suppression mapping, and a SEND N-dimension sub-item note on preference-center / frequency options offered. Not for the lifecycle flow map or cadence governance — use email-sequence-designer; not for the consent/suppression record itself — use consent-registry; not for computing EQS or ruling the N1 unsubscribe veto — use email-quality-auditor. 邮件偏好中心/降频阶梯设计/退订替代降档

Quality

88%

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

77%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 highly actionable and clearly sequenced with validation gates and a repair feedback loop, but it is verbose — repeating the same scope boundaries across the intro, step 8, and a Scope guard paragraph — and keeps all instructions inline with no progressive-disclosure bundle files. Tightening the repeated scope statements would lift conciseness.

Suggestions

Consolidate the scope boundaries into one place (e.g., keep only the 'Scope guard' paragraph) and remove the duplicate 'does not ... ' lists from the intro and step 8 to cut repetition.

Extract the 8-step Instructions or the cadence-tier / ladder definitions into a bundled reference file under references/ and link to it, so SKILL.md stays a lean overview and progressive disclosure improves.

Trim the repeated cross-skill links to email-sequence-designer and consent-registry (they appear in Reads, multiple steps, Scope guard, Reference Materials, and Next Best Skill) to a single clearly-signaled reference each.

Dimension	Reasoning	Score
Conciseness	The body restates the same scope boundaries three times (intro paragraph, step 8, and the dedicated 'Scope guard' paragraph — each repeating 'does not design the lifecycle flow', 'does not hold the consent record', 'does not compute EQS or rule N1'), which is repetition that could be tightened; otherwise the domain-specific content earns its place.	2 / 3
Actionability	Eight numbered steps give concrete, executable guidance with specific examples ('weekly → monthly → pause → sunset', 'pause 90d → suppress until date, then resume prior tier') and explicit Pass/Partial/Fail criteria — fully actionable for an instruction-only skill.	3 / 3
Workflow Clarity	A clearly sequenced 8-step process with validation checkpoints ('Done when' criteria, Decision Gates' stop-vs-continue rules, Measured/User-provided/Estimated labeling) and a feedback loop ('if it returns BLOCK on N1, route back here to repair').	3 / 3
Progressive Disclosure	Well-organized sections with a one-level-deep Reference Materials list, but the core instructions are a monolithic inline block in a single file and no bundle files (references/scripts/assets) are provided alongside this skill, so content is not actually split out.	2 / 3
	Total	10 / 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.

The description is specific, trigger-rich, complete, and sharply distinguished from sibling skills via explicit 'not for' clauses, all in third-person voice. The trailing CJK tag duplicates the summary field and is mild redundancy but does not weaken any dimension.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'produces a preference-center field spec, a frequency/topic opt-down ladder ... a preference-to-suppression mapping, and a SEND N-dimension sub-item note' — matching the multi-action anchor.	3 / 3
Completeness	Explicitly answers both what (the four artifacts it produces) and when ('Use when the user asks to ...') with explicit trigger guidance, satisfying the top anchor.	3 / 3
Trigger Term Quality	Quoted natural phrasings a user would actually say ('build a preference center', 'set up a frequency opt-down ladder', 'give people a step-down instead of unsubscribe', 'design a topic/cadence preference page') give good keyword coverage.	3 / 3
Distinctiveness Conflict Risk	Explicit negative boundaries ('Not for ... use email-sequence-designer', 'not for ... use consent-registry', 'not for ... use email-quality-auditor') carve a clear niche unlikely to trigger the wrong skill.	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: 29 suspicious	Warning

	Total	13 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: email/nurture/preference-frequency-manager/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.