agentsclimarketplace

Cross channel data normalization

Skill duandigi/duandigi-growth-marketing-skill/skills/cross-channel-data-normalization

Evidence-first AI Agent Skills for growth marketing — multi-channel analytics (SEO, paid media, social, local search, CRM), secure account integration, AI evaluation, experimentation & approval-safe optimization for Claude Code.

Install
npx -y skills add duandigi/duandigi-growth-marketing-skill --skill cross-channel-data-normalization

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 25 days oldThe repository was created 25 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use this skill when converting data from analytics, search, advertising, social, local, CRM, commerce, or website systems into a shared project, channel, asset, metric, date, currency, and attribution contract.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

3.5 KB, as published. Nobody here has run it

Cross Channel Data Normalization

Purpose

Create a canonical data layer that supports safe cross-channel comparison without erasing provider-specific meaning.

Inputs

  • Provider fields, dimensions, metrics, and source metadata
  • Project and asset mappings
  • Canonical channel taxonomy and metric dictionary
  • Time-zone, currency, attribution, identity, and deduplication rules

If a required input is unavailable, label it unknown, state how it limits the decision, and create a collection, mapping, validation, or instrumentation task. Never invent credentials, assets, metrics, permissions, or business outcomes.

Workflow

  1. Preserve the raw provider record and immutable source identifiers.
  2. Map provider fields to canonical metric names, units, grain, and object types.
  3. Normalize project, channel, campaign, content, landing-page, location, and lead identifiers.
  4. Convert currency and time boundaries only with documented rates and time zones.
  5. Keep provider-reported, analytics-observed, CRM-qualified, and revenue-confirmed conversions separate.
  6. Record lineage, transformation version, freshness, and quality flags for every normalized record.
  7. Validate that aggregation does not double count shared campaigns, cross-domain sessions, or assisted conversions.

Required output

Return a concise, decision-oriented result containing:

  • Canonical field mapping and transformation rules
  • Normalized data contract and channel taxonomy
  • Metric-definition registry with units and grains
  • Lineage, quality flags, and unresolved mappings
  • Aggregation and deduplication tests

Label material statements as confirmed, calculated, inferred, assumed, or unknown. Include the data period, last complete period, source lineage, and confidence whenever they can change the decision.

Guardrails

  • Do not rename different concepts into one metric merely because labels are similar.

  • Do not sum users, reach, impressions, attributed conversions, or assisted conversions across platforms as unique people or outcomes.

  • Do not discard provider-specific fields needed for later audit.

  • Do not convert currencies or time zones without recording the method.

  • Do not claim guaranteed growth or present an estimate as observed fact.

  • Do not reveal secrets, personal data, private provider payloads, or cross-project information.

  • When an action can spend money, publish, contact people, alter access, modify production, or delete data, prepare an approval request instead of executing automatically.

Completion check

Before finishing, verify that the output:

  • answers a specific business or implementation decision;
  • uses the correct organization, project, asset, date range, time zone, and currency;
  • separates performance problems from data, connection, and attribution problems;
  • includes evidence, uncertainty, affected scope, and a measurable next step;
  • respects least privilege, approval, audit, and rollback requirements;
  • is no longer than necessary for the decision.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.