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 dev-avatar-servicegit 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/dev-avatar-service)<a href="https://agentmods.dev/skills/picsart/gen-ai-skills/dev-avatar-service"><img src="https://agentmods.dev/badge/skills/picsart/gen-ai-skills/dev-avatar-service/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/dev-avatar-service"><img src="https://agentmods.dev/badge/skills/picsart/gen-ai-skills/dev-avatar-service.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 | $0.00013 | $0.02274 |
| Opus 5 | $0.00006 | $0.01137 |
| Sonnet 5 | $0.00003 | $0.00455 |
| Haiku 4.5 | $0.00001 | $0.00227 |
Grade A, and why
dev-avatar-service 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 11d 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Avatar service
A service endpoint that returns a branded avatar for any user: photoreal, illustrated, or pixel, deterministic from a seed (user ID / email hash / initials). Built around a fallback hierarchy — real photo → upload → AI from initials → static default — with caching by seed so you pay once per user.
When to Use
- New user signup where you need an immediate profile image.
- Comment systems or forums that default to gravatars.
- Team pages, directories, leaderboards without uploaded photos.
- Placeholder avatars during onboarding before the user picks one.
- Branded alternative to Gravatar / UI Avatars / DiceBear.
- Mock data for staging/demo environments.
Not for: deepfaking real people from a single photo (wrong tool + wrong ethics), or stylizing an already-great uploaded photo — let users keep their own.
Prerequisites
Before building, ask (one message, 5 questions):
- Seed source: user ID, email hash, username, initials? Is it stable forever?
- Style: photoreal portrait, illustrated (Pixar/Disney-ish), flat vector, pixel art, claymorphic, monogram?
- Brand palette: accent color for backgrounds + monogram fallbacks.
- Storage + cache: S3/CDN + DB column, Picsart Drive URL, or KV key? TTL?
- Fallback chain: photo → AI avatar → initials-on-color → default SVG? Order matters.
Skip if the user hands over a detailed brief.
How to Run
-
Decide the fallback hierarchy first. This is the whole service:
1. user.photo_url → return as-is 2. cache.get(seed) → return stored AI avatar URL 3. gen-ai generate → store URL + return 4. initials on brand color → SVG fallback (no credits) 5. static /default.png → last resort -
Estimate + validate model.
gen-ai models info recraftv4 gen-ai pricing recraftv4 gen-ai generate -m recraftv4 -p "illustrated avatar, seed abc123" \ --aspect-ratio 1:1 --dry-run --debug -
Deterministic seed → prompt. Hash the seed into stable attribute picks. Never inject
Math.random()or timestamps.SEED="u_482c91" # Pick palette + mood from the seed, not from RNG HUE=$(printf "%s" "$SEED" | shasum | cut -c1-2) # 0-255 from hash gen-ai generate -m recraftv4 \ -p "illustrated profile avatar, round frame, abstract humanoid silhouette, HSL hue ${HUE}, friendly neutral expression, flat vector, centered composition, studio background" \ --aspect-ratio 1:1 \ --negative-prompt "text, watermark, letters, realistic face, specific person" \ --save-to-drive --drive-folder avatars \ --json --no-input | jq -r '.url'
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.
- 11d ago First seen · 171 lines · 13 tokens per session scan A c6f182b2bfc8
dev-avatar-service is a skill published in the GitHub repository PicsArt/gen-ai-skills (4 stars, last pushed 13d ago), licensed MIT. It adds 13 tokens to every session and 2,274 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
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.
tidal-search
Search for artists, albums, or tracks on Tidal. Use when the user wants to find music, look up an artist, search for a song or album.
hypr-video-cli
Generates MP4 videos from canvasState JSON via CLI. Builds canvasState JSON with elements, animations, transitions, keyframes, captions, and effects, then renders with npx hypr-video-cli. Activates when creating videos, promos, clips, or animations from descriptions; composing video/image/text/shape/audio elements on…