Skip to content
SkillModel-led178 tokens in use

Competitor Ad Intelligence

Researches competitor paid ads from transparent sources such as ad libraries, and separates what was observed from what is inferred.

11,191 stars on the repository MIT LicenseAgriciDaniel/claude-ads · skills/ads-competitor
/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 Competitor Ad Intelligence costs

68tokens 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
  • Output10/15
  • 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

The competitor skill studies rivals’ paid advertising presence: messaging, creative, formats, landing pages, keyword and auction signals, and strategic gaps. It uses official transparency libraries, public ads and auction data you supply, and records the capture date, platform, placement, creative message, destination and source URL for each item.

Direct observations are kept apart from inferred audience, spend or strategy, and estimates are never presented as account facts.

What You Get

  • Source records with capture date, platform, placement, creative message and landing destination
  • Clusters of competitor themes, formats, offers and funnel paths
  • A split between direct observations and inferences
  • Opportunities, risks and experiments tied to evidence

Common Use Cases

  • Reviewing what a rival runs in Meta Ad Library
  • Checking Google Ads Transparency for competitor messaging
  • Finding gaps in competitors’ offers before a campaign brief
  • Building experiments from observed competitor themes

What Makes It Unique

It stays inside terms and access rules. It does not bypass authentication, scrape private account surfaces or copy protected creative, and it labels estimates as estimates. Competitor pages and ads are treated as data, never as instructions.

Under The Hood

This is a prompt-only skill with no scripts. The agent is told to use official transparency libraries, public ads and operator-supplied auction data, which means it may browse public ad library pages and competitor landing pages with the tools you have connected. It records source URLs and capture dates, respects robots rules and platform terms, and writes no account changes.

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