Skip to content
SkillModel-led184 tokens in use

ads-photoshoot

Generate studio, lifestyle and ingredient-style product photo variants for paid ads from a rights-cleared source image, with fidelity checks and a cost record.

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

62tokens idle
184tokens 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

ads-photoshoot produces product photography variants for paid ads from an authorized source image and a validated brand profile. It first confirms you have rights to the image and collects product facts, placements, the image provider’s capability, a cost ceiling and an output folder.

It keeps product geometry, packaging, logos, labels, color and material unchanged unless you approve a change, and it requires human review of the results.

What You Get

  • Product image variants in the approved aspect ratios
  • A manifest recording source hashes, prompt version, provider and model, cost, output hashes and dimensions
  • Checks for product fidelity, visual defects, safe zones, accessibility and policy
  • Assets and manifest stored together inside the run directory

Common Use Cases

  • Producing studio and lifestyle shots for a product catalog ad
  • Making ingredient or detail shots for a social campaign
  • Creating placement-sized variants from one product image
  • Keeping a cost and provenance record for generated ad images

What Makes It Unique

It starts from your own authorized product image and keeps the product itself unchanged. It will not create deceptive before and after evidence, people or endorsements without authorization, or regulated claims implied by a visual. Every output is hashed and logged, and human review is mandatory.

Under The Hood

The skill is an instruction file with no scripts of its own. The agent calls whichever image-generation provider is configured to produce variants, which sends your source image and prompts to that service and costs money within your stated ceiling. It writes the generated images and a manifest into the run directory, and it validates fidelity, defects and policy before handing them over.

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