CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

creative-fatigue-detector

Diagnose creative fatigue; refresh cadence; when to swap/rotate ads; frequency caps; CTR drop / CPM rise signals; per-platform creative lifespans.

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

93%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.

The body is an exemplary lean, high-signal reference: concrete thresholds, per-platform data, and decision rules with no wasted tokens. The only minor gap is that the diagnostic workflow is implicit rather than an explicitly ordered sequence of checks. No bundle files exist, and none are needed for a skill this size.

DimensionReasoningScore

Conciseness

The body is lean: dense threshold/action tables ("20%+ drop from peak over 3 days", "Above 2.5 for prospecting"), platform lifespan tables, and terse tactic bullets, with zero padding or explanation of concepts Claude already knows. Every line carries operational information, matching the "lean and efficient; every token earns its place" anchor.

5 / 5

Actionability

Fully concrete, executable guidance for an instruction-only skill: exact numeric thresholds with explicit actions ("Above 3.0 for retargeting → Immediate creative swap required"), per-platform lifespans with refresh cadences, pipeline counts ("3-5 concepts in dev... 5-10 running live"), and decision rules for combined signals. This matches the top anchor's coverage of common cases with copy-ready specifics.

5 / 5

Workflow Clarity

The single task (detect fatigue early and act) is unambiguous, and "Reading Signals Together" provides explicit decision rules ("CTR dropping AND frequency climbing → fatigue confirmed, swap creative"), but there is no explicit sequencing of checks (e.g., monitor → confirm with 2+ signals → select tactic → verify recovery). It is not 5 because the sequence is implicit; not 3 because the decision logic is clearly stated with no risky/batch operations requiring validation.

4 / 5

Progressive Disclosure

The skill is under 50 lines, single-purpose, with no need for external references — no references/ or scripts/ files exist in the bundle and none are needed. Content is well-organized into clearly headed sections (Early Warning Signals, Lifespan by Platform, Anti-Fatigue Tactics, Reading Signals Together), which per the rubric's simple-skill guideline merits a 5.

5 / 5

Total

19

/

20

Passed

Description

66%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.

The description is domain-specific and keyword-rich with several concrete capabilities, but it reads as a semicolon keyword list rather than a sentence with an explicit trigger clause. Adding a "Use when..." clause (e.g., for diagnosing declining ad performance or planning creative refreshes) would raise completeness and trigger-term quality.

Suggestions

Add an explicit invocation clause, e.g., "Use when ad performance declines (CTR drop, CPM rise, frequency climbing), planning creative refreshes, or setting frequency caps."

Include common synonyms users would naturally say, such as "ad burnout", "creative rotation", or "banner blindness", to broaden trigger coverage.

Convert topic fragments like "refresh cadence" into stated actions (e.g., "Determines refresh cadence per platform") for fuller capability coverage.

DimensionReasoningScore

Specificity

Lists several specific capabilities — "Diagnose creative fatigue; refresh cadence; when to swap/rotate ads; frequency caps; CTR drop / CPM rise signals; per-platform creative lifespans" — each naming a concrete function in the domain. It falls short of 5 because several entries are topic fragments ("refresh cadence", "frequency caps") rather than fully stated actions, leaving minor gaps in coverage.

4 / 5

Completeness

The "what" is clear (diagnose fatigue, set refresh cadence, per-platform lifespans), but there is no "Use when..." clause or equivalent explicit invocation trigger — "when to swap/rotate ads" describes the skill's content, not when Claude should load it. Per the judging guidelines, a missing 'Use when' clause caps completeness at 3; it is not 2 because the 'what' is concrete and multi-part.

3 / 5

Trigger Term Quality

Good coverage of natural terms an advertiser would say: "creative fatigue", "swap/rotate ads", "frequency caps", "CTR drop / CPM rise", "per-platform". A few natural synonyms are missing (e.g., "ad burnout", "creative rotation", "ad performance declining"), which keeps it below the comprehensive 5 anchor.

4 / 5

Distinctiveness Conflict Risk

The niche is clear — paid-ad creative fatigue with distinctive signals (frequency caps, CTR/CPM, hook rate) — so conflict risk is low. Minor overlap risk remains with broader ad-performance or media-buying optimization skills, keeping it below the 5 anchor.

4 / 5

Total

15

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

Synter-Media-AI/plugin

Path

skills/creative-fatigue-detector/SKILL.md

Reviewed

Table of Contents

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.