Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add PicsArt/gen-ai-skills --skill marketer-ad-variant-factorygit clone --depth 1 https://github.com/PicsArt/gen-ai-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/picsart/gen-ai-skills/marketer-ad-variant-factory)<a href="https://agentmods.dev/skills/picsart/gen-ai-skills/marketer-ad-variant-factory"><img src="https://agentmods.dev/badge/skills/picsart/gen-ai-skills/marketer-ad-variant-factory/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/picsart/gen-ai-skills/marketer-ad-variant-factory"><img src="https://agentmods.dev/badge/skills/picsart/gen-ai-skills/marketer-ad-variant-factory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00020 | $0.02376 |
| Opus 5 | $0.00010 | $0.01188 |
| Sonnet 5 | $0.00004 | $0.00475 |
| Haiku 4.5 | $0.00002 | $0.00238 |
Grade A, and why
marketer-ad-variant-factory scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ad variant factory
Take one approved concept and explode it into 10-30 shippable ad variants for A/B testing on Meta, Google, TikTok, and Pinterest. Built for speed (parallel batch) and for direct upload to ad accounts (deterministic naming).
When to Use
- User has a hero / concept and needs many variants across headline × visual × CTA × background for A/B tests.
- "Fan out 30 variants of this ad for Meta" / "generate a test matrix" / "multiply this creative".
- Prepping a new ad-set launch — needs 9:16, 1:1, 16:9 with 3-5 visual variants each.
- Do NOT use for a single hero (use
gen-ai generate) or for cross-channel creative (usemarketer-campaign-kit). This skill is for depth on one concept, not breadth across channels.
Prerequisites
Ask up front if the brief doesn't cover it (combine into one message):
- Hero asset — path or URL to the approved concept image.
- Axes to vary — visual direction (1-5), background/scene (1-5), focal composition (close-up vs wide), optional: color treatment.
- Platforms / aspect ratios — Meta needs 9:16 + 1:1, TikTok is 9:16, Display wants 16:9. Confirm which.
- Variant count — how many total? 10-15 is typical for a first test, 30+ for broad exploration.
- Naming convention — what does the ad platform require (e.g.
{campaign}_{axis}_{variant}_{size}.webp)? - Brand guardrails — colors (hex), forbidden elements, existing brand.md?
If the user just says "a lot", default to 5 visuals × 3 ratios = 15 variants.
How to Run
- Anchor on the hero. The hero is the reference image — every variant should feel like a sibling, not a cousin. Upload to Drive first if it's local so downstream jobs can reference a URL.
- Define the variant matrix. Keep axes explicit. 5 visual directions × 3 aspect ratios = 15 jobs. Don't mix 8 axes — the test becomes unreadable.
- Write the manifest. One job per variant, unique
idthat maps to your ad-platform naming convention. Theimagefield references the hero. - Estimate + dry-run.
gen-ai batch run variants.json --dry-run - Run at concurrency 6-8. Image variants are fast and independent — push concurrency higher than the default 3. Watch for 429s; back off to 4 if you see them.
gen-ai batch run variants.json -c 8 -o ./ad-variants - Audit and resume. Filter
results.jsonfor non-completed jobs, retry.gen-ai batch resume ./ad-variants - Hand off. Ads platform uploaders expect a flat folder with standard naming —
results.jsonhas every path + URL for direct CSV import to Meta Ads Manager / TikTok Ads / Google Ads.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 140 lines · 20 tokens per session scan A 685a263fcb0f
marketer-ad-variant-factory is a skill published in the GitHub repository PicsArt/gen-ai-skills (4 stars, last pushed 15d ago), licensed MIT. It adds 20 tokens to every session and 2,376 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
compact-manual
Claude Code skill for deterministic context compaction. Compresses the current Claude Code session to the clipboard for a manual rewind+paste workflow. A deterministic alternative to /compact that extracts literal dialog and truncates only tool outputs — no LLM summarization. Use when the user says 'compact the…
musicbrainz
Interroge l'API publique MusicBrainz pour récupérer des métadonnées musicales fiables : recherche d'artistes, discographies complètes (release-groups : albums, EPs, singles, lives, compilations), détails de releases (labels, formats, dates, pays), recordings, œuvres, relations entre entités (membres de groupe…
lastfm
Access Last.fm listening history, music stats, and discovery. Query recent tracks, top artists/albums/tracks, loved tracks, similar artists, and global charts.
tidal-playlist
Manage Tidal playlists — list, create, rename, delete, set public/private visibility, add or remove albums and tracks, and list tracks in a playlist. Use when the user wants to work with playlists or share one.
metalorgie-weekly-releases
Récupère et filtre les sorties d'albums de la semaine publiées sur metalorgie.com ("Les sorties de la semaine"). Affiche les albums correspondant aux genres favoris de l'utilisateur (Metalcore, Post Hardcore, Hardcore, Neo metal) ainsi que les albums de groupes reconnus/notables, même hors genres favoris. Utilise ce…
tidal-library
Add or remove artists, albums, or tracks from your Tidal favorites library. Use when the user wants to save music, like a song, follow an artist, or remove items from their library.