Publisher: Corey Haines · Editorial profile by AI Tools Ratings · Review method
Not runtime tested; source-document review only. Referenced scripts were not executed or comprehensively audited. No security certification.
What task is this skill designed for?
Plan privacy-conscious events for directory search, source visits and completed submissions.
What input and output should you expect?
Input: Business questions, current event inventory, permitted properties, stack constraints and timestamped synthetic records.
Output: An event dictionary, triggers, validation plan and proposed changes; expected, not independently tested. A plan does not establish production instrumentation.
What does it need to run?
An Agent Skills-capable client and approved technical context. Analytics accounts or tag-manager integrations are optional and require their own permissions.
Publisher README declares support for Agent Skills clients including Claude Code, Codex and Cursor. This is author-declared, not independently runtime tested.
How should you approach installation?
- Inspect the pinned source, license and task-specific reference files before installing anything.
- Follow the publisher README guidance for your actual client; no installation command or cross-client compatibility was independently tested here.
- Try the illustrative prompt with synthetic input in a separate folder, inspect the output against the checklist and approve external actions separately.
Installation guide: discovery, dependencies and runtime checks
What files, accounts or data can it access?
Can read code, reports or separately connected analytics services. Proposed tracking may transmit data; exclude names, emails and raw query contents unless justified and approved.
What does the skill cost?
The inspected source license is MIT. Agent subscriptions, model usage, dependencies and external services have separate costs and terms. No paid runtime was tested.
What are its limits and alternatives?
A source click is not an install or sale. Duplicate events, consent behavior, timezone boundaries and open cohorts can distort rates even when a dashboard renders correctly.
Use a static event dictionary for a small documentation task. Choose this workflow when consistent definitions and implementation verification are the main problem.
What could you ask in a small trial?
Try this with a small sample:
Plan directory analytics using synthetic events. Count source clicks as clicks, not installs. Define deduplication and consent checks; calculate rates only over matched closed windows.
How would you verify the result?
- Map each event to a decision and definition.
- Inspect payloads for unnecessary personal data.
- Reconcile counts and windows independently before reporting rates.
Use a baseline and record acceptance evidence before treating a successful task as a reliable workflow.
Which source and license were checked?
Read the reviewed SKILL.md at its pinned commit · Complete reviewed folder
Repository and current publisher guidance
Checked:
MIT — identified in LICENSE at the reviewed commit. Dependencies and third-party assets may have separate terms. License evidence
Version details and review scope
Source: coreyhaines31/marketingskills/skills/analytics
Reviewed commit: e85f3cbc2e4a79bf33b2a12e9bdd9087d414735b
SKILL.md SHA-256: 675e284b745837d595aa4d36903cb54b3921181fd343cc519d31f34fe8002196
Source-document review. Source text and stated dependencies were inspected for this profile. Referenced code was not comprehensively audited, no runtime test was performed, and source files are not mirrored here.