gif-gen

Stars0

Forks0

UpdatedApril 1, 2026 at 03:24

Create animated GIFs — crop regions, convert formats, slideshow, or AI-animate

Installation

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.

Source

blissito

blissito/nanoclaw

View GitHub Repository View Creator Repositories

Download

Related occupationsSOC

Based on SOC occupation classification

Software DevelopersComputer and Mathematical Occupations·SOC 15-1252

File Explorer

2 files

SKILL.md

readonly

name	gif-gen
description	Create animated GIFs — crop regions, convert formats, slideshow, or AI-animate
allowed-tools	Bash(generate-gif:*)

GIF Generation

Mode	Command	Cost
Crop	`generate-gif --crop WxH+X+Y img.png`	Free
Convert	`generate-gif --convert img.avif`	Free
Sprite sheet	`generate-gif --sprite 4x3 [--fps N] [--format gif\|webp\|mp4] sprite.png`	Free
Slideshow	`generate-gif img1.png img2.png img3.png`	Free
AI animate	`generate-gif --animate img.png "motion description"`	~$0.42

When to use each mode

User sends image + "recorta X y hazlo gif" / "solo la parte de..." → Crop
User sends image + "conviértelo a gif" / "hazlo gif" (no animation needed) → Convert
User sends sprite sheet + "anima este sprite" / "hazlo gif/webp/mp4" → Sprite sheet
User sends multiple images + "haz un gif" / "gif con estas" → Slideshow
User sends one image + "anima esto" / "dale vida" / "hazlo gif animado" → AI animate

Crop mode — pixel-perfect cropping

Use vision to look at the image and calculate exact pixel coordinates for the crop region.

Steps:

Read the image dimensions first: ffprobe -v error -select_streams v:0 -show_entries stream=width,height -of csv=p=0 /path/to/img.jpg
Look at the image (you already have it as multimodal input) and estimate where the desired region is as a percentage of the full image
Convert percentages to pixel coordinates: X = pct_x × width, Y = pct_y × height, W = pct_w × width, H = pct_h × height
Round to integers and run: generate-gif --crop WxH+X+Y /path/to/img.jpg

Example: User says "solo la calavera de la izquierda" on a 1920x1080 image. You see the skull occupies roughly the left 40% horizontally and middle 60% vertically:

# W=768 (40% of 1920), H=648 (60% of 1080), X=0, Y=216 (20% offset from top)
generate-gif --crop 768x648+0+216 /workspace/group/attachments/img-1.jpg

Important: Always use ffprobe to get real dimensions — don't guess from the resized vision thumbnail.

Sprite sheet mode

Animate a sprite sheet (grid of frames) into GIF, webp, or mp4.

generate-gif --sprite 4x3 /workspace/group/attachments/spritesheet.png
generate-gif --sprite 8x2 --fps 15 --format webp spritesheet.png
generate-gif --sprite 6x1 --fps 24 --format mp4 spritesheet.png

COLSxROWS: grid layout (e.g. 4x3 = 4 columns, 3 rows = 12 frames, read left-to-right, top-to-bottom)
--fps N: frames per second (default: 10)
--format gif|webp|mp4: output format (default: gif)

How to determine the grid:

Use ffprobe to get image dimensions
Look at the image with vision — count columns and rows of frames
Verify: image_width / cols and image_height / rows should give clean frame sizes

Iterate with the user: If the animation speed feels off, adjust --fps. If they want a different format, re-run with --format. Quick iterations since it's all local ffmpeg.

Slideshow mode

generate-gif /workspace/group/attachments/img-1.jpg /workspace/group/attachments/img-2.jpg /workspace/group/attachments/img-3.jpg

Needs at least 2 images
1 frame per second, loops forever
Find attachment paths from [Image: attachments/img-xxx.jpg] in the conversation

AI animate mode

generate-gif --animate /workspace/group/attachments/img-1.jpg "the person smiles and waves"

Takes ~1-3 minutes (AI video generation + conversion)
The prompt describes the motion, not the scene
Good motion prompts: "gentle breeze blows hair", "camera slowly zooms in", "the person turns and smiles"

Output & delivery

Saves to /workspace/group/gif-*.gif or sprite-*.*. Send as image:

mcp__nanoclaw__send_message({ text: "Here's your GIF!", image_path: "/workspace/group/gif-123.gif" })

More from this repository

same repository

escrito-juridico

blissito/nanoclaw

Redactar escritos jurídicos mexicanos largos (recursos de apelación, demandas, contestaciones, amparos) a partir de varios documentos de un expediente (demanda, contestación, pericial, confesional, sentencia), entregados como .docx editable. Úsalo cuando el usuario pida "recurso de apelación", "redacta el escrito", "haz la demanda/contestación en Word", o cualquier pieza procesal larga que deba correlacionar agravios/hechos con documentos fuente y jurisprudencia verificada.

2026-07-100

sintesis-docs

blissito/nanoclaw

Sintetizar o redactar un entregable a partir de varios documentos fuente (o pocos muy grandes) que juntos NO caben en la ventana de contexto — reportes multi-fuente, due diligence, análisis/comparación de contratos, resúmenes de expediente, investigación. Úsalo cuando debas correlacionar información entre múltiples documentos y producir un documento nuevo, y leerlos todos completos reventaría el contexto ("Prompt is too long"). NO es para leer un solo documento corto.

2026-07-100

iconscout

blissito/nanoclaw

Busca y descarga assets de diseño (iconos, ilustraciones, 3D, animaciones Lottie, imágenes AI) desde IconScout. Dispara cuando el user pida un icono/ilustración/animación para un diseño, mockup, presentación o web, o mencione IconScout. 13.8M+ assets con licencia royalty-free.

2026-07-090

voice

blissito/nanoclaw

Text-to-speech with Spanish voices (Kokoro, local & free) and OpenAI fallback

2026-07-070

audio-largo

blissito/nanoclaw

Transcribe a texto el HABLA de un audio largo o pesado (reuniones, notas de voz reenviadas, grabaciones de 10–60+ min). Trocea con ffmpeg y transcribe cada parte con Whisper, sin toparse con el límite de 25MB de la API. Úsala cuando llegue un [Audio file: ...] y el usuario pida "transcribe", "qué dice", "analiza el audio", o para resumir/analizar una grabación de voz.

2026-07-020

doc-remix

blissito/nanoclaw

Haz una versión nueva/ejecutiva/más limpia de un documento institucional (PDFs tipo "orden del día", agendas, hojas de evento, programas) MINANDO sus assets reales (logos, fotos de ponentes, texto, fuentes) y RECONSTRUYENDO en HTML — nunca re-difundiendo la página como imagen. Úsala ante "haz una nueva versión", "versión ejecutiva", "rehazlo más limpio", "adáptalo" de un PDF.

2026-06-110

name	gif-gen
description	Create animated GIFs — crop regions, convert formats, slideshow, or AI-animate
allowed-tools	Bash(generate-gif:*)

GIF Generation

Mode	Command	Cost
Crop	`generate-gif --crop WxH+X+Y img.png`	Free
Convert	`generate-gif --convert img.avif`	Free
Sprite sheet	`generate-gif --sprite 4x3 [--fps N] [--format gif\|webp\|mp4] sprite.png`	Free
Slideshow	`generate-gif img1.png img2.png img3.png`	Free
AI animate	`generate-gif --animate img.png "motion description"`	~$0.42

When to use each mode

User sends image + "recorta X y hazlo gif" / "solo la parte de..." → Crop
User sends image + "conviértelo a gif" / "hazlo gif" (no animation needed) → Convert
User sends sprite sheet + "anima este sprite" / "hazlo gif/webp/mp4" → Sprite sheet
User sends multiple images + "haz un gif" / "gif con estas" → Slideshow
User sends one image + "anima esto" / "dale vida" / "hazlo gif animado" → AI animate

Crop mode — pixel-perfect cropping

Use vision to look at the image and calculate exact pixel coordinates for the crop region.

Steps:

Read the image dimensions first: ffprobe -v error -select_streams v:0 -show_entries stream=width,height -of csv=p=0 /path/to/img.jpg
Look at the image (you already have it as multimodal input) and estimate where the desired region is as a percentage of the full image
Convert percentages to pixel coordinates: X = pct_x × width, Y = pct_y × height, W = pct_w × width, H = pct_h × height
Round to integers and run: generate-gif --crop WxH+X+Y /path/to/img.jpg

Example: User says "solo la calavera de la izquierda" on a 1920x1080 image. You see the skull occupies roughly the left 40% horizontally and middle 60% vertically:

# W=768 (40% of 1920), H=648 (60% of 1080), X=0, Y=216 (20% offset from top)
generate-gif --crop 768x648+0+216 /workspace/group/attachments/img-1.jpg

Important: Always use ffprobe to get real dimensions — don't guess from the resized vision thumbnail.

Sprite sheet mode

Animate a sprite sheet (grid of frames) into GIF, webp, or mp4.

generate-gif --sprite 4x3 /workspace/group/attachments/spritesheet.png
generate-gif --sprite 8x2 --fps 15 --format webp spritesheet.png
generate-gif --sprite 6x1 --fps 24 --format mp4 spritesheet.png

COLSxROWS: grid layout (e.g. 4x3 = 4 columns, 3 rows = 12 frames, read left-to-right, top-to-bottom)
--fps N: frames per second (default: 10)
--format gif|webp|mp4: output format (default: gif)

How to determine the grid:

Use ffprobe to get image dimensions
Look at the image with vision — count columns and rows of frames
Verify: image_width / cols and image_height / rows should give clean frame sizes

Iterate with the user: If the animation speed feels off, adjust --fps. If they want a different format, re-run with --format. Quick iterations since it's all local ffmpeg.

Slideshow mode

generate-gif /workspace/group/attachments/img-1.jpg /workspace/group/attachments/img-2.jpg /workspace/group/attachments/img-3.jpg

Needs at least 2 images
1 frame per second, loops forever
Find attachment paths from [Image: attachments/img-xxx.jpg] in the conversation

AI animate mode

generate-gif --animate /workspace/group/attachments/img-1.jpg "the person smiles and waves"

Takes ~1-3 minutes (AI video generation + conversion)
The prompt describes the motion, not the scene
Good motion prompts: "gentle breeze blows hair", "camera slowly zooms in", "the person turns and smiles"

Output & delivery

Saves to /workspace/group/gif-*.gif or sprite-*.*. Send as image:

mcp__nanoclaw__send_message({ text: "Here's your GIF!", image_path: "/workspace/group/gif-123.gif" })