How this skill is triggered — by the user, by Claude, or both
Slash command
/picsart:agency-multi-brand-packThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Run generations for N retainer clients in one coordinated pass — each client's output strictly namespaced, each job gated by that client's brand rules, every run audit-ready for legal and billing.
Run generations for N retainer clients in one coordinated pass — each client's output strictly namespaced, each job gated by that client's brand rules, every run audit-ready for legal and billing.
N clients × M templates per client → one batch, zero cross-contamination. For agencies running weekly/monthly creative cycles across a client portfolio.
Do not use for single-client deep-production work — drop to agency-pitch-mockups or a client-specific workflow. Multi-brand is for portfolio parallelism.
Ask the user (one message):
acme-fintech, zest-retail, nova-travel). Each must have a locked brand-system.json.client:<slug> so per-client spend can be pulled from gen-ai historyIf any client in the list lacks brand-system.json or brand.md, stop and run agency-brand-scoping for that client first — do not batch-generate without locked brand files.
1. VERIFY BRANDS → every client in scope has clients/<slug>/brand.md + brand-system.json
2. SCAFFOLD → build per-client manifest fragments, merge into one master manifest
3. ESTIMATE → gen-ai batch run <manifest.json> --dry-run + estimate; break into smaller batches if > $20
4. RUN → `gen-ai batch run <manifest.json>` with client names in job IDs and a resume-ready output dir
5. VERIFY → per-client output folders populated; cross-check any NULLs in results.json
6. AUDIT → export per-client spend + asset list for billing
7. DELIVER → folder per client, approved files uploaded or linked in the retainer channel
Rules:
out/<slug>/... — never a shared output folder where filenames can collide.brand.md constraints. Batch-level generic prompts are the biggest source of cross-contamination.id so downloaded files and results.json remain easy to group.gen-ai batch resume <output-dir> by default. gen-ai batch resume <output-dir> so mid-run failures don't cost the completed half.{
"batch_kind": "multi-brand-pack",
"week": "2026-04-22",
"defaults": { "model": "recraftv4", "aspectRatio": "1:1" },
"clients": [
{ "slug": "acme-fintech", "templates": ["hero", "social-1", "og"] },
{ "slug": "zest-retail", "templates": ["hero", "social-1", "og"] }
]
}
A scaffolding script expands this into the flat jobs[] manifest the CLI expects. Keep the expanded manifest checked in under out/retainer-<date>/manifest.json for reproducibility.
| Sub-task | Model | Notes |
|---|---|---|
| Per-client hero (default) | recraftv4 | Design-forward, respects brand palette |
| Per-client hero (photo-led brands) | flux-2-pro | Override at the job level for photo-heavy clients |
| Social tiles (1:1, 9:16) | recraftv4 | Same brand rules, cheaper |
| OG / readable-headline slides | ideogram-v3 | Only reliable text rendering |
| Background replacement on product shots | recraftv3-replace-bg | For ecomm retainers |
| Video cuts per brand | kling-v3-standard (draft) / kling-v3-pro (final) | Per-client concurrency 2 |
out/<slug>/, drive:retainer-<date>/<slug>/, results.json job IDs. Redundant is good.clients[] × templates[] beats copy-paste errors.results.json to the repo. Audit trail for legal, billing input, and reproducibility.clients/<slug>/prompts/ — manifest references these, edits propagate.gen-ai-batch.md §CI recipes.rules on a single job, entire batch suspect. Fix: per-job rules, not batch-level.hero.webp overwrites client A's.gen-ai batch resume <output-dir> on a 100-job batch — one provider hiccup costs the whole run.Run gen-ai whoami to confirm authentication, then re-run the failed command with --debug.
CLIENTS=("acme-fintech" "zest-retail" "nova-travel")
WEEK=$(date +%Y-%m-%d)
# Sanity check: every client has a brand file
for c in "${CLIENTS[@]}"; do
test -f "clients/$c/brand.md" || { echo "Missing brand.md for $c"; exit 1; }
done
cat > /tmp/multi-brand-$WEEK.json <<'EOF'
{
"defaults": { "model": "recraftv4", "aspectRatio": "1:1" },
"jobs": [
{ "id": "acme-fintech/hero", "prompt": "acme-fintech Q2 hero — editorial, restrained", "aspectRatio": "16:9" },
{ "id": "acme-fintech/og", "prompt": "acme-fintech OG — headline: Q2 launch", "aspectRatio": "1200x630", "model": "ideogram-v3" },
{ "id": "zest-retail/hero", "prompt": "zest-retail Q2 hero — playful, bold color", "aspectRatio": "16:9" },
{ "id": "nova-travel/hero", "prompt": "nova-travel Q2 hero — cinematic wide", "aspectRatio": "16:9", "model": "flux-2-pro" }
]
}
EOF
gen-ai batch run /tmp/multi-brand-$WEEK.json --dry-run
gen-ai batch run /tmp/multi-brand-$WEEK.json -c 4 -o "out/retainer-$WEEK"
The / in each job id creates the per-client subfolder automatically — outputs land at out/retainer-<date>/<client-slug>/<asset>.webp plus results.json.
# Per-client completion breakdown from results.json
node -e '
const r = require("./out/retainer-2026-04-22/results.json");
const by = {};
for (const j of r.jobs) {
const c = j.id.split("/")[0];
by[c] ||= { completed: 0, failed: 0 };
by[c][j.status] = (by[c][j.status] || 0) + 1;
}
console.table(by);
'
Create an archive sub-folder retainer-$WEEK/<client-slug>/ per client, drop a summary with asset list + estimated spend from gen-ai pricing. Share only the per-client folder link — never the master folder.
| Phase | Typical spend | Typical time |
|---|---|---|
| Scoping (per new client, one-time) | ~$1 | 30 min |
| Production (weekly retainer, 8 clients × 4 assets) | $15-30 | 20-40 min batch + review |
| Flagship-model upgrade pass (2-3 hero upgrades) | $5-10 | 10-15 min |
Per-client weekly spend should be trackable from results.json — if it isn't, the tagging is broken.
workflows/agency-brand-scoping/ — required prerequisite per clientworkflows/agency-pitch-mockups/ — per-client pitch variantworkflows/agency-client-handoff/ — package retainer history at engagement endgen-ai-batch.md — concurrency, gen-ai batch resume <output-dir>, audit recipesGuides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.
npx claudepluginhub picsart/gen-ai-skills --plugin picsart