Skills Explorer Add Skills

attribution

An agent skill by coreyhaines31, from coreyhaines31/marketingskills. Tags: analytics, data, evaluation, marketing, tracking.

What it does

When the user wants to figure out which marketing actually drives conversions and revenue, choose or interpret an attribution model, or reconcile conflicting numbers across tools. Also use when the user mentions "attribution," "attribution model," "first-touch vs last-touch," "multi-touch," "which channel drives revenue," "what's my real CAC," "my dashboards disagree," "Google/Meta says X but GA says Y," "media mix model," "MMM," "incrementality," "geo lift," "holdout test," "how did you hear about us," "self-reported attribution," "dark social," or wants to instrument attribution themselves — "stitch my bookings to their source," "SavvyCal/Calendly attribution," "close the identify gap," "track conversions on a third-party domain," "first-party / self-hosted attribution." For event tracking setup and UTMs, see analytics. For ad-platform pixels/CAPI, see ads. For pipeline and CRM revenue reporting, see revops. For the AI-search attribution blind spot, see ai-seo.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add coreyhaines31/marketingskills --skill attribution

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/coreyhaines31/marketingskills
cp -r marketingskills/skills/attribution ~/.claude/skills/attribution

Safety box score

Grade B, low risk: 25 of 100 risk points, rated 2026-10-18. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This is a documentation-only attribution skill, but it includes first-party tracking patterns that read browser cookies, pass anonymous IDs through third-party booking links, and send events to analytics/CRM systems. The main risks are remote data transfer and handling API keys/webhook secrets; the outward-facing survey and CRM sync are inherent to the skill’s purpose.

Category levels, from 0 (none) to 3 (high)
CategoryLevelWhy
Code & shell execution0 (none)No native scripts, shell commands, or executable installers are shipped; the files are markdown guidance with code snippets only.
Network access2 (moderate)The runbook explicitly posts data to remote services, e.g. `fetch(`${POSTHOG_HOST}/batch/`, ...)`, and relies on webhook and metadata passthrough flows to third-party domains.
Filesystem reach0 (none)The skill does not read, write, or delete local files or system paths; its writes are to external analytics/CRM systems.
Secrets & credentials2 (moderate)The first-party tracking code reads browser cookies (`document.cookie`) and uses credential-like values such as `POSTHOG_API_KEY` and `SAVVYCAL_WEBHOOK_SECRET`.
Privilege & persistence0 (none)No sudo, global installs, services, scheduled tasks, or OS/shell setting changes are required.
Instruction hijack surface0 (none)I did not find prompt-injection text, hidden instructions, or commands to ignore safeguards; the files are straightforward guidance.
Irreversible actions2 (moderate)It is designed to take outward-facing actions like sending a post-conversion survey and syncing source/confidence/basis into the CRM, which are real writes but bounded to attribution work.
Transparency0 (none)All reviewed content is plain, readable markdown; there are no binaries, minified blobs, or runtime-decoded payloads.

Before installing

Rated 2026-10-18 by an automated review of 6 files from the skill's repository.

Source

Repository
coreyhaines31/marketingskills (all skills from this repository)
Path
skills/attribution/SKILL.md
Branch
main
Collection
marketingskills
Updated
2026-09-21