MARKETING AGENCIES · AG-03
Lead-Generation Report Reconciler
Make sense of the differences between Ads, GA4, and CRM before your next client review.
Paid release in preparation. No purchase is available yet. Prices exclude applicable taxes.
What this agency workflow is designed to do.
Compare one client's aggregated Ads, GA4, and CRM tables across two periods, preserve differences in what each source measures, and prepare an editable client report.
Use the input and output contract above to assess whether it matches the decision you need to make. The examples below show the intended structure, with source information and human review kept visible.
Read the guide: Write a monthly client report from supplied KPIsSEE THE SHAPE OF THE WORK
From supplied facts to a useful draft.
Example input
Fictional Cedar Desk report: July to August 2026, both 31 days, UTC. [ADS] Same campaign scope: spend $4,000 → $4,800; clicks 2,000 → 2,400; platform-attributed forms 100 → 108. Form count uses conversion date and a 30-day click window. [GA4] Paid-traffic lead submission events 92 → 96; events are not unique people. [CRM] Paid-source leads created 80 → 84; qualified at the September 3 extraction 40 → 42. Cohorts have different maturity. Definitions differ across sources. No matched lead-level dataset or experiment is supplied.
Illustrative output
Client report draft — human review required Ads spend: +$800 (+20%); clicks: +400 (+20%); CPC: $2.00 in both periods [ADS]. August records 108 Ads-attributed forms, 96 GA4 events, and 84 CRM leads. These measure different populations; the differences do not prove lost leads [ADS, GA4, CRM]. CRM qualified counts are snapshots of cohorts with different maturity. They do not establish improved lead quality [CRM]. Proposed review actions: confirm the reporting definitions; request equally mature CRM cohorts; investigate the source differences using approved evidence. No accounts are connected or changed.
Fictional, hand-authored reference example. This is not a customer result or an evaluated AI run. No accuracy or time-saving results have been established.
Inside the planned package.
The workflow
A SKILL.md instruction file, a quickstart, and installation guidance.
The working materials
Input and output templates, example documents, and a review checklist.
The boundaries
Evaluation cases, version history, license, and data-handling notes.
Before you get started.
Environment & installation
Claude Code is a candidate for the first pilot, not a verified supported host. Host choice, account requirements, and installation must be validated with pilot users. AI tool costs are separate from the proposed product price.
Read the installation previewRelease evidence
Prototype v0.1.0 · Last edited September 5, 2026. Authoring: LibSkills prototype project. Independent industry reviewer: not yet assigned. Host test date and result: none. See the required quality gate.
Limitations & review points
- Proposed paid product; no paid package is available yet.
- No account connections, individual lead deduplication, or automatic attribution resolution.
- Small aggregated tables and Markdown output only; large exports and spreadsheet generation need separate validation.
- Missing denominators and incompatible populations remain unresolved. A reviewer must verify the figures before use.
Proposed paid terms
12 months of updates and 30 days of setup support. Client deliverable use allowed; redistribution of paid source excluded. License proposal · Refund proposal.
THE NEXT PIECE OF YOUR WORKFLOW
Keep the work moving.
Marketing agencies ↗
Client Brief Completeness Check
Find the gaps in a client brief before they become gaps in your scope.
Marketing agencies ↗
Client Proposal Builder
Turn approved discovery notes and your rate card into a proposal draft with clear scope.
Marketing agencies ↗
Campaign Brief Builder
Bring product facts, audience, and objectives into one brief your team can review.