Skip to content
SkillModel-led666 tokens in use

ads-meta

Audit Meta, Facebook and Instagram Ads: Pixel and CAPI, attribution, creative fatigue, structure, audiences and policy, with cold-start accounts handled separately.

11,191 stars on the repository MIT LicenseAgriciDaniel/claude-ads · skills/ads-meta
/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-meta costs

77tokens idle
666tokens 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 →
Good
  • Frontmatter8/15
  • Structure25/25
  • Examples0/15
  • Output10/15
  • Size13/15
  • 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-meta is the Meta worker of the Claude Ads skill set. It audits measurement (Pixel, Events Manager, CAPI), attribution, creative diversity and fatigue, account structure, audiences, placements, automation, budgets and policy from the exports and screenshots you provide.

Its cold-start contract checks the account, the Pixel and the conversion history as three separate questions, so a new Pixel is not mistaken for a new account, and mature-account benchmarks are not applied to missing history.

What You Get

  • Findings on Pixel and CAPI setup, attribution, creative, structure, audiences, placements and policy
  • A cold-start classification for account, Pixel and conversion history, each marked confirmed or unknown
  • Prioritized recommendations, unscored opportunities, contradictions and missing inputs
  • A pointer to ads-server-side-tracking for server-side events and ads-optimize for changes

Common Use Cases

  • Auditing a Facebook or Instagram account before scaling spend
  • Reviewing Advantage+ and automation settings
  • Planning tests for a brand-new Pixel or account
  • Checking creative fatigue and diversity

What Makes It Unique

The cold-start evidence contract is specific to this skill. It says an account is cold only when evidence confirms no prior delivery, a Pixel is cold only when it has no valid event history, and conversions are cold only when a lag-mature window shows none. Missing evidence stays unknown, and creative is never called bad only because the Pixel is new.

Under The Hood

The skill is an instruction file with no scripts of its own. The agent reads reference files from the Claude Ads repository, works from the data you supply, and returns findings through shared JSON contracts to the main ads skill. It does not call the Meta API itself or change the account; changes stay drafts until the main mutation gate passes.

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