Marketing AnalyticsAttributionROI

Campaign Analytics

Multi-touch attribution, funnel conversion, and ROI calculation.

$skillfish add ~skills/campaign-analytics

Real Examples Get Started Models & Context

Real Conversations

See how the Campaign Analytics skill responds to actual requests. These are representative examples of what your AI agent will produce.

You

We close deals in 45–90 days. Touches include Google ads, LinkedIn ads, content, SDR outreach, and webinars. Last-click attribution is making our LinkedIn look terrible and content look worthless. How do we actually measure this?

Agent

Multi-Touch Attribution for a 45–90 Day B2B Funnel

Why last-click is lying to you: In a 45–90 day cycle, the closing touch (usually a direct visit or brand search) gets 100% credit. LinkedIn and content — which create awareness and move deals forward — get zero. This causes you to cut budget on exactly the channels that open deals.

Recommended model: W-shaped attribution

30% credit to first touch (what created awareness)
30% credit to lead creation touch (what drove conversion)
30% credit to opportunity creation touch (what moved to pipeline)
10% distributed to all middle touches

Implementation without expensive tools:

In HubSpot/Salesforce, capture:
  - First touch source (UTM at first known visit)
  - Lead creation source (UTM at form fill)
  - Opp creation source (UTM or activity at deal creation)
  - All touches (contact activity timeline)

Build this report in your CRM:

Channel	Deals influenced	Deals first-touch	Deals last-touch	W-shape credit
LinkedIn Ads	28	18	3	22.4
Content/Blog	31	22	4	25.1
Google Ads	19	4	14	12.7

Expected finding: LinkedIn and content will show 4–6x more value under W-shape vs. last-click. This typically changes budget allocation by 20–30%.

You

We spent $42,000 on marketing last quarter across Google Ads ($18K), LinkedIn ($14K), content ($6K), and events ($4K). We closed $180,000 in new ARR. How do I calculate true ROI per channel?

Agent

Campaign ROI Analysis — Q-Last

Step 1: Assign revenue to channels Pull deals closed last quarter from your CRM, filter by close date. For each deal, record first-touch and last-touch source.

Blended ROI (starting point):

Total spend: $42,000 | New ARR: $180,000
Blended ROAS: 4.3x | Blended CAC: $42K / (deals closed) = varies

Per-channel breakdown (requires attribution data):

Channel	Spend	ARR Attributed (last-touch est.)	CAC	ROAS
Google Ads	$18,000	~$90,000	~$900/deal	5.0x
LinkedIn	$14,000	~$36,000	~$1,167/deal	2.6x
Content	$6,000	~$18,000	~$600/deal	3.0x
Events	$4,000	~$36,000	~$667/deal	9.0x

Key corrections to apply:

LinkedIn ROAS looks low on last-touch — apply influence weighting (how many closed deals had a LinkedIn touch at any point)
Events ROI looks high but include loaded cost: staff time, travel, booth prep often 3–4x the direct spend
Content has 3–6 month lag — this quarter's content spend drives next quarter's pipeline

Recommendation: Report both last-touch ROI AND influenced revenue. If LinkedIn influenced 60% of deals, its true contribution is ~$108K, not $36K — changing the optimization decision entirely.

Get Started

How to install and use this skill in your preferred environment.

Skills are designed for AI coding agents (Claude Code, Cursor, Windsurf) and IDE-based workflows where the agent can read files, run scripts, and act on your codebase. Web-based AI can use the knowledge and frameworks, but won't have tool access.

Models & Context

Which AI models and context windows work best with this skill.

Recommended Models

Best

Claude Opus 4 Claude Sonnet 4 GPT-4.1 Gemini 2.5 Pro Grok 3 Kimi K2

Good

Claude Haiku 4.5 GPT-4.1 mini Gemini 2.5 Flash Grok 3 mini

Larger models produce more detailed, production-ready outputs.

Context Window

This skill's SKILL.md is typically 3–10 KB — fits in any modern context window.

8K Skill only

32K+ Skill + conversation

100K+ Skill + references + codebase

All current frontier models (Claude, GPT, Gemini) support 100K+ context. Use the full window for complex multi-service work.

Pro tips for best results

1

Be specific

Include numbers — users, budget, RPS — so the skill can size the architecture.

2

Share constraints

Compliance needs, team size, and existing stack all improve the output.

3

Iterate

Start with a high-level design, then ask follow-ups for IaC, cost analysis, or security review.

4

Combine skills

Pair with companion skills below for end-to-end coverage.

Ready to try Campaign Analytics?

Install the skill and start getting expert-level guidance in your workflow — any agent, any IDE.

$skillfish add ~skills/campaign-analytics

← Browse all 169 skills