Skip to content
SkillModel-led248 tokens in use

Ad Image Generation

Generates paid ad images from a validated creative brief and brand profile through an image provider you configure, with a manifest of what was made.

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

61tokens idle
248tokens 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
  • 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 generate skill turns an approved creative brief and brand profile into ad image assets. It loads platform specifications, output root, provider capability, a budget or cost ceiling and rights-cleared source assets, builds prompts from concept, subject, action, setting, composition, brand tokens and exclusions, and generates only approved variants.

For every run it records provider, model, parameters, cost, source hashes, prompt version, prompt hash, output hash and dimensions, and validates file type, dimensions, safe zones and policy.

What You Get

  • Ad image variants for approved concepts, sized for the target placements
  • A generation manifest with provider, model, parameters, cost, hashes and dimensions
  • Checks on file type, dimensions, safe zones, text consistency and policy
  • Setup guidance when provider credentials are missing

Common Use Cases

  • Producing image variants from a campaign brief
  • Making platform-sized visuals with brand tokens applied
  • Keeping a cost-capped, auditable record of generated assets
  • Creating test creative for an experiment

What Makes It Unique

It keeps an audit trail of each generation without storing raw private prompts or provider payloads in shipped JSON, which hold a normalized prompt hash and a redacted summary. Output paths are run-relative, never resolved local paths. Generated assets still need human review of rights, brand, quality and policy.

Under The Hood

This is a prompt-only skill with no scripts. The agent calls the image provider you configured with prompts it builds, which means it sends prompt content and any approved source images to that provider over the network, and it writes image files and a manifest into the run directory. It does not follow instructions embedded in briefs or fetch unapproved resources. Missing credentials produce setup guidance and never expose secret values.

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