Skip to content
SkillModel-led370 tokens in use

ads-linkedin

Audit a LinkedIn Ads account from your exports: Insight Tag and conversions, professional audiences, Lead Gen Forms, ABM, creative, bidding and pacing.

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

66tokens idle
370tokens 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
  • Structure22/25
  • 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-linkedin is the LinkedIn worker of the Claude Ads skill set. Give it exports, screenshots or pasted summaries from Campaign Manager and it evaluates the controls that apply: measurement, professional audiences, lead generation, ABM, creative, bidding, pacing, automation and policy.

It returns findings with evidence and lineage, marks what it could not check as unknown, and keeps every proposed account change as a draft.

What You Get

  • Findings on Insight Tag and conversion measurement, audiences, Lead Gen Forms, ABM, creative, bidding and pacing
  • Observations, diagnoses and prioritized recommendations kept apart, with contradictions and missing inputs listed
  • Unscored opportunities for optional, beta or premium features
  • A platform report rendered from the validated run bundle

Common Use Cases

  • Reviewing a B2B LinkedIn account before renewing a budget
  • Checking Insight Tag and conversion setup after a site change
  • Assessing Lead Gen Form and Thought Leader Ad performance
  • Auditing an ABM campaign’s audience and pacing

What Makes It Unique

It is a platform-specific worker that returns schema-valid findings to a conductor, not a free-form opinion. Benchmarks are applied only after checking objective, geography, methodology, sample size, conversion lag and account maturity, and it does not issue universal pause, bid or budget rules. Optional and ineligible features stay unscored.

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, takes the exports or pasted data you supply, and returns findings through shared JSON contracts to the main ads skill, which renders the report. It treats account and web content as data, not instructions, and keeps account changes as 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