assets-pipeline
Skill2 starsChanged 6 months agoMITView on GitHub
Génère et intègre des assets multimédia dans un SaaS : images IA (Gemini), SVG (Quiver), vidéo (Remotion), audio (ElevenLabs), scroll 3D. Clés serveur, stockage objet, charte.
- Reads credentials
- Installs packages
- Sends data out
1 other project uses a version of this.
Adopted by
Most recently taken up by
- jame581/GodotPromptertheir own version, first seen Oct 21, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- jame581/GodotPrompter★ 965same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository32 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- apexSkill
- api-genSkill
- brainstormSkill
- debugSkill
- deep-updateSkill
- deploy-checkSkill
- depsSkill
- docs-genSkill
- e2e-testsSkill
- env-setupSkill
- featureSkill
- fixSkill
- forkSkill
- meta-promptSkill
- migrateSkill
- onboardSkill
- oneshotSkill
- perfSkill
- prdSkill
- qualitySkill
- refactorSkill
- reviewSkill
- saas-initSkill
- schema-genSkill
- scope-taskSkill
- session-startSkill
- stripeSkill
- ui-auditSkill
- uiSkill
- variationsSkill
The file
Files
Quand utiliser ce skill
- Ajouter une génération d'image, SVG, vidéo ou audio dans le produit
- Setup scroll 3D / WebGL sur landing ou app
- Aligner landing, marketing et UI sur une même charte visuelle
- Avant d'ajouter des variables d'environnement liées aux APIs d'assets
Règle absolue (voir rules/media-apis.md)
- Appels API assets = server-side uniquement (route API, worker, cron)
- Jamais
NEXT_PUBLIC_*pourQUIVERAI_*,GOOGLE_API_KEY,ELEVENLABS_* - Sortie → stockage objet (Supabase Storage / S3) + URL signée ou CDN
- Lier chaque asset généré à
organizationId/userIden DB (multi-tenant)
Images IA — Gemini
// app/api/generate-image/route.ts (server-side uniquement)
import { GoogleGenerativeAI } from '@google/generative-ai'
const genAI = new GoogleGenerativeAI(process.env.GOOGLE_API_KEY!)
export async function POST(req: Request) {
const { prompt } = await req.json()
const model = genAI.getGenerativeModel({ model: 'gemini-2.0-flash-exp-image-generation' })
const result = await model.generateContent(prompt)
const imageData = result.response.candidates?.[0]?.content.parts
.find(p => p.inlineData)?.inlineData
// Uploader vers Supabase Storage
const { data } = await supabase.storage
.from('assets')
.upload(`generated/${Date.now()}.png`, Buffer.from(imageData!.data, 'base64'), {
contentType: 'image/png',
})
return NextResponse.json({ url: data?.path })
}Docs : https://ai.google.dev/gemini-api/docs/image-generation
SVG — Quiver AI
// app/api/generate-svg/route.ts
const res = await fetch('https://api.quiver.ai/v1/svg', {
method: 'POST',
headers: { Authorization: `Bearer ${process.env.QUIVERAI_API_KEY}` },
body: JSON.stringify({ prompt, style: 'minimal', format: 'svg' }),
})
const { svg } = await res.json()
// Stocker en DB ou Supabase StorageDocs : https://docs.quiver.ai/api-reference/introduction
Vidéo — Remotion
pnpm create video@latest// remotion/MyVideo.tsx
import { AbsoluteFill, useCurrentFrame, interpolate } from 'remotion'
export const MyVideo = () => {
const frame = useCurrentFrame()
const opacity = interpolate(frame, [0, 30], [0, 1])
return <AbsoluteFill style={{ opacity, background: 'white' }}>...</AbsoluteFill>
}Render via @remotion/lambda (AWS) ou @remotion/cloudrun (GCP) — jamais sur le serveur Next.js.
Docs : https://www.remotion.dev/docs/ai/
Audio — ElevenLabs
// app/api/generate-audio/route.ts
const res = await fetch(`https://api.elevenlabs.io/v1/text-to-speech/${voiceId}`, {
method: 'POST',
headers: {
'xi-api-key': process.env.ELEVENLABS_API_KEY!,
'Content-Type': 'application/json',
},
body: JSON.stringify({ text, model_id: 'eleven_multilingual_v2' }),
})
const audioBuffer = await res.arrayBuffer()
// Upload vers storage + retourner URL signéeScroll 3D / WebGL
Stack recommandée : @react-three/fiber + @react-three/drei + three + gsap (ScrollTrigger) + lenis
pnpm add @react-three/fiber @react-three/drei three gsap lenis
pnpm add -D @types/three// Lazy load obligatoire — ne pas bloquer le LCP
const Scene3D = dynamic(() => import('@/components/scene-3d'), {
ssr: false,
loading: () => <div className="h-[600px] bg-black animate-pulse" />,
})Règle : canvas 3D en <Suspense> + dynamic avec ssr: false. Jamais de clés API dans le front.
Checklist avant merge
- Clés API absentes du frontend (Grep
NEXT_PUBLIC_dans les fichiers API assets) - Assets uploadés en storage objet, pas servis depuis
/public organizationIdlié en DB si multi-tenantdocs/brand-assets.mdcréé ou mis à jour dans le repo application cible- Taille des assets vérifiée (images < 200kb WebP, audio < 5MB)
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

