Menu
Extract individual PNG frames from any WhatsApp sticker — static .webp, animated .webp, or Lottie .was. Use when the user wants to see, analyze, clone, or recreate a sticker.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | sticker-frames |
| description | Extract individual PNG frames from any WhatsApp sticker — static .webp, animated .webp, or Lottie .was. Use when the user wants to see, analyze, clone, or recreate a sticker. |
| allowed-tools | Bash(extract-frames:*),Bash(ffmpeg:*),Bash(ffprobe:*) |
WhatsApp stickers arrive as files in /workspace/attachments/:
| Extension | Format | What it is |
|---|---|---|
.webp | RIFF/WebP | Static image OR animated WebP |
.was | WhatsApp Animated Sticker | Lottie JSON (usually gzip-wrapped) — vector animation |
You cannot view a .was file directly — it is vector data, not raster. This skill rasterizes both formats into a numbered sequence of PNG frames you can Read with vision.
extract-frames /workspace/attachments/sticker-1777730095530.was
extract-frames /workspace/attachments/sticker-1777730095530.webp /tmp/my-frames
/tmp/sticker-frames-<nanos>/.Cap is 60 frames by default (covers typical sticker length). For longer animations pass --max-frames N after the path.
This skill does not auto-send to the user — frames are an input for your analysis, not output for the chat.
After extraction, the typical flow is:
Read each frame PNG (vision).If the user just sent a sticker without asking anything specific, ask what they want to do with it before extracting — extraction takes a few seconds.
unknown format — magic bytes don't match WebP, gzip, or raw JSON. The file may be corrupt or a format WhatsApp introduced after this skill was written. Report the magic bytes from stderr to the user.render-lottie.mjs doesn't finish in ~30s, the JSON may be invalid or use a Lottie feature lottie-web doesn't support. Read the JSON header (head -c 500 /tmp/.../lottie.json) and report.frame_001.png for what looks animated, that's the source's fault, not the skill's.Add the EasyBits MCP server (@easybits.cloud/mcp) so the container agent can manage cloud files, images, video/voice generation, designs, websites, forms, brand kits, characters, and a built-in DB. 65+ tools (server-side).
Reference & priority guide for the EasyBits MCP server (`mcp__easybits__*`). When to use EasyBits vs native skills, and which EasyBits tools exist.
Semantic search over your workspace text files using local multilingual embeddings (fastembed + e5-small). Free, local.
Extract text from images locally with PaddleOCR weights via onnxruntime. Free, multi-language, batch.
Remove backgrounds and segment images locally with the u2net family (rembg). Free, no API keys, works in batch.
Generate vector logos (SVG) and convert raster images to SVG via Recraft on fal.ai. Use for logo / brand mark / icon requests, or when the user sends a PNG/JPG and wants the editable SVG version.