Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/PicsArt/gen-ai-skillsnpx agentmods add skills/picsart/gen-ai-skills/dev-screenshot-beautifierWrote 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-screenshot-beautifier)<a href="https://agentmods.dev/skills/picsart/gen-ai-skills/dev-screenshot-beautifier"><img src="https://agentmods.dev/badge/skills/picsart/gen-ai-skills/dev-screenshot-beautifier/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-screenshot-beautifier"><img src="https://agentmods.dev/badge/skills/picsart/gen-ai-skills/dev-screenshot-beautifier.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 | $0.00016 | $0.02190 |
| Opus 5 | $0.00008 | $0.01095 |
| Sonnet 5 | $0.00003 | $0.00438 |
| Haiku 4.5 | $0.00002 | $0.00219 |
Grade A, and why
dev-screenshot-beautifier 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Screenshot beautifier
A polish pipeline that takes a raw UI screenshot (localhost capture, production screen grab, mobile viewport) and turns it into a blog-ready, changelog-ready, doc-ready hero: device-framed, drop-shadowed, on a gradient backdrop, dark-mode matched.
When to Use
- Release notes / changelog entries that need a hero image per ship.
- Blog posts and docs that reference a product screen.
- PR descriptions where a raw screenshot looks amateurish.
- Twitter/LinkedIn launch posts where the screenshot is the creative.
- Dark-mode and light-mode site variants that each need their own polished hero.
- PM/eng team members who don't have a designer on call.
Not for: generating UI that doesn't exist (use Figma or a mockup tool), or replacing real content with fake text (prefer annotation/blurring).
Prerequisites
Before processing, ask (one message, 5 questions):
- Raw screenshot path — PNG preferred over JPEG for clean edges.
- Device frame: browser chrome (Chrome/Safari/Arc), iPhone bezel, Android, MacBook, iPad, or none (just soft shadow)?
- Background vibe: soft studio gradient, brand palette, dark rim-lit surface, glassmorphic, matte neutral?
- Output target + aspect: blog hero (16:9), Twitter card (1200×675), LinkedIn (1200×627), mobile story (9:16), doc inline (3:2)?
- Dark mode variant needed? If yes, generate a paired dark version.
Skip if the user hands over a detailed brief.
How to Run
-
Estimate the background swap cost.
gen-ai models info recraftv3-replace-bg gen-ai pricing recraftv3-replace-bg -
Option A — Background swap only (UI stays pixel-exact, just drop on a new surface). Use this when the screenshot itself is final.
gen-ai change-bg \ -i ./raw.png \ -p "soft studio gradient, magenta #FF006E to deep purple #0D0A1F, subtle rim light from top-left, very slight film grain" \ --download ./out -
Option B — Full edit (add device frame + shadow + reflection in one pass). Use when you want the model to re-composite.
gen-ai generate -m flux-kontext-pro \ -i ./raw.png \ -p "product screenshot of the provided UI, placed inside a MacBook Pro 14 bezel, floating slightly tilted at 4° right, soft drop shadow below, glassy reflection underneath, matte charcoal background, centered composition, 16:9" \ --aspect-ratio 16:9 \ --download ./out
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 · 166 lines · 16 tokens per session scan A 3d0608aab6f0
dev-screenshot-beautifier is a skill published in the GitHub repository PicsArt/gen-ai-skills (4 stars, last pushed 14d ago), licensed MIT. It adds 16 tokens to every session and 2,190 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
infographic-creator
Create beautiful infographics based on given text content. Use when users request to create infographics.
ppt-orchestrator
A dispatcher for creating presentations, slide decks, long images, and weekly reports. It chooses a visual style and output format, then sends the work to a more specialised add-on.
zhongguose-html-skill
An HTML-only presentation system using traditional Chinese colours and Chinese-style visual design. It helps organise source material into a report structure and produces a self-contained HTML file with its assets.
svg-art
Generates artistic SVGs directly as code — minimal line icons, geometric marks, generative patterns, or hand-drawn compositions — and assembles a modern 2026 HTML gallery preview. Saves each session to its own semantically named folder on the Desktop. Learns from feedback: which styles you loved, which compositions…
deck-guizang-editorial
Editorial magazine meets e-ink: 10 layouts and 5 palettes (Ink, Indigo Porcelain, Forest Ink, Kraft Paper, Dune).
deck-swiss-international
16-column grid, one saturated accent, and 22 locked layouts (Klein Blue, Lemon, Mint, Safety Orange).