ads-photoshoot — Claude Code skill: what it does, how to install
Generates rights-cleared paid-ad product photography from an authorized image and brand profile. Keeps packaging and logos intact across studio or lifestyle scenes.
npx skills add AgriciDaniel/claude-ads --skill ads-photoshoot -a claude-codeWhat ads-photoshoot does
The skill organizes a disciplined workflow for paid product photography. It begins by verifying image rights, placement targets, and cost limits. Product fidelity comes first: logos, packaging, and materials remain intact unless you explicitly authorize changes.
It tests distinct production angles. These include studio backdrops, contextual lifestyle shots, ingredient stories, or scale details. The skill writes generated files and a manifest atomically to the run folder. The manifest tracks file hashes, prompt versions, model names, and generation costs.
Human review is strictly mandatory. You cannot run this unattended. The instructions forbid deceptive before-and-after proof, fake endorsements, and unverified visual claims.
What it helps with
- generate studio and lifestyle ad photography variants
- preserve exact packaging, labels, and product geometry
- track prompts, model names, and costs in a run manifest
- check asset compliance against ad policies and safe zones
Example prompts for the agent
- Create a studio shot for this product using our brand profile and the authorized photo.
- Generate a lifestyle product image in contextual use without changing packaging logos.
- Run a photoshoot variant showing an ingredient story within our cost ceiling.
How to install ads-photoshoot
1Skills CLI (Vercel)
npx skills add AgriciDaniel/claude-ads --skill ads-photoshoot -a claude-code2Manually: put the files in place
~/.claude/skills/ads-photoshoot/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/ads-photoshoot/
1Skills CLI (Vercel)
npx skills add AgriciDaniel/claude-ads --skill ads-photoshoot -a codex2Manually: put the files in place
.agents/skills/ads-photoshoot/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add AgriciDaniel/claude-ads --skill ads-photoshoot -a cursor2Manually: put the files in place
.cursor/skills/ads-photoshoot/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install AgriciDaniel/claude-ads ads-photoshoot2Manually: put the files in place
.github/skills/ads-photoshoot/SKILL.md1Skills CLI (Vercel)
npx skills add AgriciDaniel/claude-ads --skill ads-photoshoot -a gemini-cli2Platform CLI
gemini skills install https://github.com/AgriciDaniel/claude-ads --path skills/ads-photoshootManually: put the files in place
.devin/skills/ads-photoshoot/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add AgriciDaniel/claude-ads --skill ads-photoshoot -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
From the same set20
The whole set →Similar
Questions about ads-photoshoot
How do I install ads-photoshoot in Claude Code?
Run npx skills add AgriciDaniel/claude-ads --skill ads-photoshoot -a claude-code in your terminal.
What does ads-photoshoot do?
It runs a structured product photography pipeline that generates ad variants while preserving original packaging, logos, and materials.
Does ads-photoshoot allow unattended automation?
No, human review is mandatory. The skill blocks deceptive before-and-after imagery, unauthorized endorsements, and unverified visual claims.
Source text
SKILL.md · MIT
--- name: ads-photoshoot description: "Generate rights-cleared paid-ad product photography variants from an authorized source image and validated brand profile. Triggers on: product photo, product photography, virtual photoshoot, photoshoot, enhance product image, studio shot, lifestyle shot, lifestyle product image, floating product image, ingredient shot." --- # Product Photography Variants 1. Confirm rights to the product image and collect the validated brand profile, product facts, intended placements, provider capability, cost ceiling, and output root. 2. Preserve product geometry, packaging, logos, labels, color, and material unless the operator explicitly approves a change. 3. Define distinct production hypotheses such as studio, contextual use, ingredient story, scale/detail, or lifestyle; do not imply unsupported product outcomes. 4. Generate approved aspect ratios and record source hashes, prompt version, provider/model, cost, output hashes, and dimensions. 5. Validate product fidelity, visual defects, safe zones, accessibility, and policy. 6. Store assets and manifest atomically inside the run directory. Human review is mandatory. Do not create deceptive before/after evidence, people or endorsements without authorization, or regulated claims from visual implication.
© AgriciDaniel · MIT · AgriciDaniel/claude-ads