CtrlK
BlogDocsLog inGet started
Tessl Logo

analyzing-marketing-campaign

Analyze weekly marketing campaign performance data across channels. Use when analyzing multi-channel digital marketing data to calculate funnel metrics (CTR, CVR) and compare to benchmarks, compute cost and revenue efficiency metrics (ROAS, CPA, Net Profit), or get budget reallocation recommendations based on performance rules.

76

Quality

93%

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

87%

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 efficient, well-structured analysis skill with concrete formulas, defaults, and output rules, plus a properly signaled one-level reference. The main gap is workflow clarity: the data-quality step lacks an explicit validate/fix/retry feedback loop.

Suggestions

Add an explicit feedback loop after the Data Quality Check — e.g., 'If missing values or anomalies are found, report them to the user and ask whether to proceed or exclude affected rows before running analysis.'

Specify what to do when a denominator is zero or unavailable (e.g., Email channel has no impressions, so CTR is undefined) to make the funnel steps unambiguous edge-case guidance.

Include one short worked example row (actual numbers → computed CTR/CVR/ROAS/Net Profit) so the output format and calculations are unambiguous on first use.

DimensionReasoningScore

Conciseness

The body is lean — formulas are stated directly ('CTR = clicks / impressions × 100'), defaults live in compact tables, and there is no padding explaining what marketing or ROAS is — so every token earns its place rather than the level-2 'could be tightened' case.

3 / 3

Actionability

Though instruction-only (no code), guidance is fully concrete: exact formulas, specific default values (Target ROAS 4.0x, Max CPA $50, Shipping $8, Product Cost 35%), and precise output columns plus status rules ('[OK] Above' if >= target), meeting the actionable top anchor.

3 / 3

Workflow Clarity

Sections are sequenced (Data Quality Check → Funnel → Efficiency → Output) and a data-quality check exists, but there is no explicit feedback loop or 'if the check fails, do X' checkpoint, matching the level-2 anchor of steps present with implicit checkpoints rather than the level-3 explicit validation/retry pattern.

2 / 3

Progressive Disclosure

The body is organized into clear sections and offloads the detailed budget rules to a single one-level-deep, clearly signaled reference ('read references/budget_reallocation_rules.md for the complete decision framework'), which exists as a real file — matching the top anchor.

3 / 3

Total

11

/

12

Passed

Description

100%

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 concise, third-person, and clearly states both capability and explicit trigger conditions, covering concrete marketing-analytics actions with natural user vocabulary. It is a strong, distinct skill description with no notable weaknesses.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'calculate funnel metrics (CTR, CVR) and compare to benchmarks, compute cost and revenue efficiency metrics (ROAS, CPA, Net Profit)', and 'get budget reallocation recommendations' — matching the top anchor rather than the domain-only level 2.

3 / 3

Completeness

Answers both what ('Analyze weekly marketing campaign performance data across channels') and when via an explicit 'Use when analyzing multi-channel digital marketing data to calculate...' clause, satisfying the level-3 anchor rather than capping at 2.

3 / 3

Trigger Term Quality

Natural terms a marketer would actually say appear throughout: 'marketing campaign performance', 'multi-channel digital marketing', 'CTR', 'CVR', 'ROAS', 'CPA', 'budget reallocation' — good coverage rather than the partial level-2 set.

3 / 3

Distinctiveness Conflict Risk

The niche is narrowly marketing-analytics with specific metrics and triggers, making it unlikely to fire for unrelated skills; not the generic level-1 or overlapping level-2 case.

3 / 3

Total

12

/

12

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
datawhalechina/agent-skills-with-anthropic
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.