Skip to content
SkillModel-led6,929 tokens in use

ads

Plans, runs and audits paid ads on Google, Meta and LinkedIn, ending each answer with facts, hypotheses and what data is missing.

61,709 stars on the repository MIT Licensecoreyhaines31/marketingskills · skills/ads
npx skills add coreyhaines31/marketingskills --skill ads
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing ads costs

96tokens idle
6,929tokens in use
38,526tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. 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 →
Excellent
  • Frontmatter12/15
  • Structure19/25
  • Examples15/15
  • Output10/15
  • Size13/15
  • Resources15/15

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 →
Excellent
  • Development activity100
  • Maintenance100
  • Community76
  • Maturity32
  • Momentum40

ads gives an agent a working method for paid acquisition. It covers channel selection, account structure and naming, budget allocation, ad copy frameworks, retargeting, landing page alignment and a weekly operating check.

It answers judgement calls such as whether ads are worth it, how to split budget, why CPA rose and whether to kill or keep a campaign. Inputs it cannot see are labeled MISSING, and the agent leaves out an estimate for them.

What You Get

  • A platform selection guide and campaign structure with naming conventions
  • Budget allocation and bid strategy progression advice
  • A Google RSA output spec and ad copy templates
  • A weekly operating check and an audit with guardrails on recommendations
  • Retargeting plans with windows, exclusions and different offers per stage

Common Use Cases

  • Deciding which channel to fund first and how to split budget
  • Diagnosing why CPA rose on a Google or Meta account
  • Auditing a Google Ads account against a checklist
  • Setting up LinkedIn campaigns for a B2B offer

What Makes It Unique

Every audit ends with facts, hypotheses and missing data, and unavailable inputs are marked MISSING. It includes a Meta playbook for the Andromeda era, a decision system for Meta, and a scaling rule that favors net cash over ROAS percentage, with brand and non-brand measured apart.

Under The Hood

The SKILL.md loads first and routes to reference files by task. It runs no scripts. A tool section lists ad platform CLIs and MCP connectors for Google, Meta, LinkedIn and TikTok; using them needs your own account access, and the skill advises starting read-only.

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