CtrlK
BlogDocsLog inGet started
Tessl Logo

ads-apple

Audit Apple Ads measurement, AdServices and AdAttributionKit, campaign and keyword structure, Search Match, App Store placements, custom product pages, bidding, budgets, MMP reconciliation, and policy. Use for Apple Ads, Apple Search Ads, App Store ads, Search Match, custom product pages, AdServices, or Apple app-install campaigns.

74

Quality

91%

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

82%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 concise, well-structured audit procedure with clear sequencing and sensible guardrails. It is actionable for an orchestration skill but could add an explicit fix-retry loop around the mutation gate and name individual shared reference files.

Suggestions

Add an explicit feedback loop: if the mutation gate fails or findings are not schema-valid, state that Claude should diagnose, fix, and re-validate before proceeding.

Replace the generic 'the relevant shared measurement, benchmark, creative, automation, policy, and scoring references' with named reference files (e.g., 'ads/references/benchmarks.md') so navigation is unambiguous.

Include a short concrete example of the expected finding/output shape or a sample command for running the audit to lift actionability toward fully executable guidance.

DimensionReasoningScore

Conciseness

The body is lean — terse numbered procedure steps and tight boundary rules with no over-explanation of concepts Claude already knows, so every token earns its place.

5 / 5

Actionability

Concrete guidance is present (specific file path 'ads/references/apple-audit.md', enumerated control areas, explicit output categories), but as an instruction-only orchestration skill it lacks executable code/commands, leaving minor gaps.

4 / 5

Workflow Clarity

An 8-step procedure is clearly sequenced with validation checkpoints ('Keep every account change as a draft until the main mutation gate passes', 'Return schema-valid findings'), but there is no explicit validate-fix-retry feedback loop for failed gates.

4 / 5

Progressive Disclosure

Well-organized into Procedure, Boundaries, and Output sections with one-level-deep references signaled ('Read ads/references/apple-audit.md'), though the shared references are described generically rather than as distinct links and no local bundle exists.

4 / 5

Total

17

/

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, specific description that enumerates concrete audit capabilities and provides a clear 'Use for' trigger clause with good synonym coverage. It cleanly answers both what the skill does and when to invoke it.

DimensionReasoningScore

Specificity

Lists multiple specific concrete audit areas — 'AdServices and AdAttributionKit, campaign and keyword structure, Search Match, App Store placements, custom product pages, bidding, budgets, MMP reconciliation, and policy' — giving comprehensive coverage rather than vague abstraction.

5 / 5

Completeness

Explicitly answers both 'what' (the audit scope enumeration) and 'when' (the 'Use for ...' trigger clause) with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

The 'Use for...' clause covers natural synonyms users would say — 'Apple Ads, Apple Search Ads, App Store ads, Search Match, custom product pages, AdServices, or Apple app-install campaigns' — with strong synonym coverage.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (Apple Ads audit) with distinct, domain-specific triggers, making conflict with unrelated skills minimal.

5 / 5

Total

20

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
AgriciDaniel/claude-ads
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.