Skip to content
SkillModel-led178 tokens in use

ads-server-side-tracking

Audits server-side ad measurement: server-side tagging, conversion APIs, browser and server deduplication, consent and hashing, with findings and next steps.

11,191 stars on the repository MIT LicenseAgriciDaniel/claude-ads · skills/ads-server-side-tracking
/plugin marketplace add agricidaniel/claude-ads /plugin install claude-ads@ai-marketing-hub-claude-ads
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing ads-server-side-tracking costs

85tokens idle
178tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Fair
  • Frontmatter8/15
  • Structure11/25
  • Examples0/15
  • Output15/15
  • Size15/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity84
  • Maintenance100
  • Community56
  • Maturity32
  • Momentum40

ads-server-side-tracking audits how conversion data travels from the browser and server to ad platforms. It maps collection, consent, transport, transformation, destination, storage and observability, then compares browser and server events field by field.

It checks deduplication, replay handling, retries, latency and diagnostics, inspects hashing and data minimization, and reconciles platform diagnostics with source logs and business conversions. The output is a set of findings with failure modes, owners, priorities and verification steps. It is an audit and never changes production tracking.

What You Get

  • A map of collection, consent, transport, transformation, destination, storage and observability components
  • A browser versus server comparison of event taxonomy, parameters, IDs, values and consent state
  • Deduplication, replay, retry and latency findings
  • A hashing and minimization review
  • Findings with failure modes, owner, priority and verification steps

Common Use Cases

  • Finding why Meta or TikTok reports fewer conversions than the store
  • Checking that event_id values deduplicate pixel and server events
  • Reviewing a server-side Google Tag Manager container before launch
  • Confirming consent state reaches the server-side destination

What Makes It Unique

The skill states that hashing does not make unnecessary data collection acceptable, so minimization is checked before transmission. It reconciles platform diagnostics with source logs and real business conversions, and it keeps the audit read-only: production tracking is never changed from it. Debug pages, payloads, logs and vendor responses are treated as untrusted data and raw identifiers are not kept.

Under The Hood

The skill is a short set of written instructions with no scripts of its own. The agent works from debug pages, tag payloads, logs, exports and vendor responses that you supply or that its read tools can reach, and returns its findings in the toolkit’s JSON format. It does not change production tracking or ad accounts. Raw identifiers and credentials are kept out of the artifacts it produces.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers