CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

marketing-reporting-analytics

Analisa e reporta desempenho, infraestrutura e metricas de marketing. Trigger em: "relatorio de ads", "relatorio de campanha", "relatorio de performance", "relatorio mensal", "performance report", "Google Ads report", "Google Ads", "GA4", "setup GA4", "GTM", "Google Tag Manager", "Universal Analytics", "auditoria de dados de marketing", "auditar dados de marketing", "data audit", "pixel do Meta", "Meta Ads", "CAC payback", "payback period", "ROI de marketing", "ROI de", "ROAS", "calculadora de ROI", "cost per acquisition", "customer acquisition cost".

Quality

82%

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

77%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.

An operationally dense, highly actionable instruction-only skill with outstanding validation and feedback loops in its GA4 setup workflow. Its weaknesses are repetition of the validation rule across three sections and a monolithic single-file structure that inlines four sub-capabilities which would navigate better as separate reference files.

Suggestions

Split the four sub-capabilities into reference files (e.g. references/campaign-report.md, references/ga4-gtm-setup.md, references/data-audit.md, references/acquisition-calculators.md) and keep SKILL.md as a routing overview with clearly signaled one-level-deep links.

Deduplicate the GA4 validation rule: state the >5-10% divergence threshold once in Fase 4 and reference it from "Evidencia de Conclusao" and "Anti-padroes" instead of restating it.

Add an explicit formula for churn-adjusted payback next to the nominal one — the current prose ("probabilidade de retencao acumulada ate o mes N") is not directly computable.

DimensionReasoningScore

Conciseness

The body is dense operational content — checklists, tables, formulas — with almost no explanation of concepts Claude already knows. Minor redundancy keeps it below 5: the GA4 validation rule is stated in Fase 4, again in the paragraph after it, and again in "Evidencia de Conclusao", and "Anti-padroes Frequentes" repeats guidance already given inline.

4 / 5

Actionability

Explicit formulas (ROAS, CPA, CTR, CAC payback, ROI, break-even ROAS = 1 / gross margin %), copy-paste-ready phase checklists down to tool level ("DebugView do GA4", "Google Tag Assistant", "comparar contagem de conversao... por 3-7 dias"), and a fully specified report template with audience variants and a severity table. Not 5 because a few items stay directional: the churn-adjusted payback is described in prose ("multiplicando o denominador pela probabilidade de retencao acumulada") without a formula.

4 / 5

Workflow Clarity

The GA4 setup is a clearly sequenced 4-phase workflow with an explicit validation phase (Fase 4) and a feedback loop ("Se a comparacao de 3-7 dias mostrar divergencia relevante (>5-10%)... voltar pra Fase 2"); the audit workflow emits PASS/FAIL/PARTIAL verdicts ordered by severity, and report generation has per-audience adaptation rules. This matches the anchor with checklists, explicit validation, and error-recovery loops; no destructive/batch cap applies.

5 / 5

Progressive Disclosure

A single ~215-line file with no bundle: the four substantial sub-topics (campaign report template, GA4/GTM setup checklist, audit guide, acquisition calculators) each carry enough detail to be separate one-level-deep reference files linked from a lean overview. Internal section structure is clear (so above 2), but all detail is inlined with no reference layer (so below 4).

3 / 5

Total

16

/

20

Passed

Description

77%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 trigger-oriented description with comprehensive bilingual keyword coverage and an explicit trigger clause, written in third person. Its main weakness is a vague "what" clause that undersells the skill's four concrete capabilities, leaving a reader to infer them from the trigger list.

Suggestions

Replace the generic opening with the skill's concrete capabilities, e.g. "Monta relatorios de performance de campanha (Google/Meta Ads), configura GA4 e GTM, audita infraestrutura de dados de marketing e calcula CAC payback, ROI e ROAS."

Drop or complete the truncated trigger "ROI de", which matches unrelated phrases such as "ROI de vendas" or "ROI de produto".

DimensionReasoningScore

Specificity

"Analisa e reporta desempenho, infraestrutura e metricas de marketing" names the domain with two generic verbs, but omits the skill's concrete capabilities (GA4/GTM setup, data audits, CAC payback/ROI calculators) that appear only in the body. It is not 4 because no several specific actions are listed, and not 2 because it goes beyond a bare domain label.

3 / 5

Completeness

Both a "what" ("Analisa e reporta desempenho, infraestrutura e metricas de marketing") and an explicit trigger clause ("Trigger em: ..." with concrete phrases) are present, satisfying the Use-when requirement. Not 5 because the "what" is generic and does not state the concrete capabilities (setup, audit, calculators) that the trigger phrases themselves imply.

4 / 5

Trigger Term Quality

The "Trigger em:" clause lists 24+ natural phrases in both Portuguese and English covering tools ("GA4", "GTM", "pixel do Meta"), synonyms ("auditoria de dados de marketing", "auditar dados de marketing", "data audit"), and finance terms ("CAC payback", "ROAS", "cost per acquisition", "customer acquisition cost") — comprehensive natural-term coverage including synonyms.

5 / 5

Distinctiveness Conflict Risk

Triggers are niche-specific ("setup GA4", "pixel do Meta", "CAC payback", "calculadora de ROI"), making wrong-skill triggering unlikely. Not 5 because broad terms like "Google Ads" and "Meta Ads" carry minor overlap risk with ad-copywriting or budget-planning requests.

4 / 5

Total

16

/

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

felvieira/claude-skills-fv

Path

skills/55-marketing-reporting-analytics/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.