Skip to content
SkillModel-led355 tokens in use

Ad Campaign Concepts and Copy

Turns a brand profile and campaign objective into distinct ad concepts, copy decks and creative briefs, checked against current platform specs.

11,191 stars on the repository MIT LicenseAgriciDaniel/claude-ads · skills/ads-create
/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 Ad Campaign Concepts and Copy costs

70tokens idle
355tokens 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
  • Frontmatter12/15
  • Structure11/25
  • Examples0/15
  • Output15/15
  • 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

The create skill produces source-grounded paid ad concepts, messaging, copy and creative briefs. It loads the validated brand profile, objective, audience, offer, proof and platform requirements, separates factual claims from operator-approved claims and creative hypotheses, and writes materially distinct strategic concepts.

Each concept defines insight, promise, proof, hook, narrative, CTA, objections, platform adaptations, destination and an experiment hypothesis. Output is a versioned creative brief and copy deck in the run directory.

What You Get

  • Materially distinct campaign concepts, with each element defined from insight to experiment hypothesis
  • A versioned creative brief and copy deck in the run directory
  • Copy checked against platform limits and policy references
  • A split between factual claims, approved claims and creative hypotheses

Common Use Cases

  • Drafting headlines and descriptions for a Google or Meta campaign
  • Writing a creative brief for a video or image shoot
  • Adapting one concept across several platforms
  • Turning audit findings into new creative directions

What Makes It Unique

It generates strategic concepts, with cosmetic rewrites ruled out, and it refuses to invent testimonials, certifications, scarcity, prices, outcomes or regulated claims. A Meta cold-start rule stops it from calling creative bad only because the Pixel is new. Human review stays required before production or launch.

Under The Hood

This is a prompt-only skill with no scripts. The agent loads the brand profile and the creative spec reference files for active platforms, treats external account and web content as data, and writes the brief and copy deck as files in the run directory. It validates them against the installed contract and checks current specifications against the dated source ledger.

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