fatigue-frequency-manager

Use when the user asks to "is my ad fatiguing", "why is CTR dropping at scale", or "should I rotate creative / widen the audience"; reads frequency, CTR and CVR decay against an early-flight baseline and returns Rotate-creative / Widen-audience / Hold triggers with a per-ad-set fatigue read. Not for building the replacement creative — use ad-creative-builder; not for the RQS score or vetoes — use ad-account-auditor. 广告疲劳检测/频次管理/换素材还是扩人群

Quality

96%

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

92%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-engineered diagnosis skill: executable ledger commands, a numbered workflow with validation checkpoints, and clean one-level-deep references. Its main weakness is mild redundancy between the description, the body intro, and the Skill Contract.

Suggestions

Trim the body intro paragraph so it does not restate the Rotate/Widen/Hold trigger triple and the 'not for / S vs R' boundary already in the frontmatter description.

Collapse the overlap between the 'Quick Start' examples and the 'Skill Contract / Expected output' to avoid repeating the same fatigue-read shape twice.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of basic-concept padding, but the body intro and Skill Contract restate the trigger triple and the 'not for / S vs R lever' boundary already present in the frontmatter, and the Quick Start partly echoes what the contract states — material that could be tightened. Not a 3 because some tokens don't earn their place against the description; not a 1 because nothing explains concepts Claude already knows.	2 / 3
Actionability	Gives executable guidance — the exact ledger.py record/trend invocation with source/field flags, named triggers with the threshold that fired, and concrete Measured/User-provided/Estimated labeling rules — copy-paste ready.	3 / 3
Workflow Clarity	A clearly sequenced 6-step diagnosis with explicit checkpoints (stop if still in learning, confirm CVR against the order truth set, Hold when within noise), a Decision Gate with stop/continue branches, and a 'Done when' acceptance checklist.	3 / 3
Progressive Disclosure	The overview points outward to well-signaled, one-level-deep references (skill-contract.md, measurement-protocol.md, roas-benchmark.md, connectors README) and keeps the SKILL.md body a navigable overview. Note: the referenced bundle directories are absent from this review package, but the referencing pattern itself is exemplary.	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, well-scoped description with natural trigger phrasings, concrete capabilities, and explicit handoff boundaries to sibling skills. The only nit is the trailing CJK summary tag which is decorative but not harmful.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'reads frequency, CTR and CVR decay against an early-flight baseline and returns Rotate-creative / Widen-audience / Hold triggers' — matching the multi-action anchor.	3 / 3
Completeness	Explicit 'Use when…' clause gives the when, the read/trigger language gives the what, and the 'Not for… use ad-creative-builder / use ad-account-auditor' clause adds explicit boundary guidance.	3 / 3
Trigger Term Quality	Quotes natural user phrasings — 'is my ad fatiguing', 'why is CTR dropping at scale', 'should I rotate creative / widen the audience' — that a user would actually say.	3 / 3
Distinctiveness Conflict Risk	The explicit 'Not for' exclusions pointing to sibling skills carve a clear niche unlikely to trigger the wrong skill.	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: 14 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: ad/scale/fatigue-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.