export

export is a skill for Claude Code, Codex from aiatelie/ai-atelie. It costs 43 tokens per session (2,205 once invoked), scanned A, original, MIT.

A canvas export skill for saving selected design elements as PNG, JPEG, OGraf bundles, Lottie files, or video.

In plain words
What is it for?
Use it to export a selected design element into a format suitable for tools such as DaVinci Resolve, Final Cut Pro, Premiere, CapCut, or presentation software.
Why use it?
It removes the need to manually prepare canvas elements for use in video editors or presentation tools.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to export a selected design element into a format suitable for tools such as DaVinci Resolve, Final Cut Pro, Premiere, CapCut, or presentation software.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aiatelie/ai-atelie/export
Install

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.

Any agent
npx skills add aiatelie/ai-atelie --skill export
Clone the repo
git clone --depth 1 https://github.com/aiatelie/ai-atelie

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for export

README.md
[![agentmods](https://agentmods.dev/badge/skills/aiatelie/ai-atelie/export.svg)](https://agentmods.dev/skills/aiatelie/ai-atelie/export)
Your own site
<a href="https://agentmods.dev/skills/aiatelie/ai-atelie/export"><img src="https://agentmods.dev/badge/skills/aiatelie/ai-atelie/export.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,205 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00043 $0.02205
Opus 5 $0.00022 $0.01103
Sonnet 5 $0.00009 $0.00441
Haiku 4.5 $0.00004 $0.00220

Measured 8d ago against content hash f7eb3a4673c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

export 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 8d 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.

skills/export/SKILL.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Export

The user wants to take an element from the active design canvas and save it for use in another tool — usually a video editor (DaVinci Resolve, FCP, Premiere, CapCut), sometimes a presentation tool. Pick the right format, call the matching capability, then write a single short sentence.

Critical: do not narrate file creation

The host renders an ArtifactCard inline in the chat for every successful export — thumbnail + filename + size + Download / Preview / Discuss buttons. You don't need to tell the user what you saved or where it landed; the card already shows that. Your reply is a one-sentence header explaining the choice, not a status report.

Bad — narrates what the user can already see:

I've saved the cat banner as a PNG file at exports/cat-banner.png. The file is 2.3MB and 3840×2160 pixels with a transparent background. You can download it using the link.

Good — confirms intent + invites iteration:

Cat banner as a 2× transparent PNG — should work straight on a Resolve overlay track.

Better — confirms + offers next step via mcp__ask-user__ask_user:

Saved as a 2× transparent PNG. Want me to also drop a 4K version for hero use? (then call ask_user with kind:"enum", options:["Yes, 4K too", "No, this is enough"])

Capabilities

These are the tools the host registry exposes. Whatever runtime you're in (MCP today, OpenAI tools later), the names and arg shapes are identical. They all return an artifact envelope:

{ "ok": true, "kind": "image|video|html-graphics|lottie", "filename": "...", "url": "...", "mime": "...", "bytes": N, "metadata": { ... } }
  • export_element — PNG or JPEG via real headless Chromium. Captures everything the browser actually renders (canvas, video, backdrop-filter, mix-blend-mode all work).
  • export_ograf.ograf.zip bundle for DaVinci Resolve 21+'s native HTML graphics import.

(More may be registered — check the tool list. Video / Lottie may have landed by the time you read this.)

Read the full file on GitHub · 150 lines

Changes

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.

  1. 8d ago First seen · 150 lines · 43 tokens per session scan A f7eb3a4673c6

Subscribe to this mod's changes

export is a skill published in the GitHub repository aiatelie/ai-atelie (8 stars, last pushed 3mo ago), licensed MIT. It adds 43 tokens to every session and 2,205 once invoked, about $0.0002 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.

Related

Other skills, from other repositories