mcpbeat Sign in

Gif Generation Skill for Claude

Converts webm/mp4 video files to optimized GIFs via ffmpeg with configurable quality settings. Use when post-processing recordings into shareable GIFs.

2k tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
324
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/athola/claude-night-market --skill gif-generation

The instruction itself

21 sections, as written by the author

Table of Contents

  • Overview
  • Required TodoWrite Items
  • Process
  • Step 1: Validate Input File
  • Step 2: Check ffmpeg Installation
  • Step 3: Execute Conversion
  • Basic Conversion (Fast, Larger File))
  • High Quality with Palette Generation (Recommended))
  • Maximum Quality with Dithering
  • Optimization Options
  • Common Presets
  • Step 4: Verify Output
  • Exit Criteria
  • Troubleshooting
  • Large Output File
  • Color Banding
  • Slow Conversion

GIF Generation Skill

Post-process video files (webm/mp4) and generate optimized GIF output with configurable quality settings.

When To Use

  • Converting recordings to animated GIF format
  • Creating lightweight demo animations

When NOT To Use

  • High-quality video output - use full recording tools
  • Static image generation without animation needs

Overview

This skill handles the conversion of video recordings (typically from browser automation) to GIF format. It provides multiple quality presets and optimization options to balance file size with visual quality.

Required TodoWrite Items

- Validate input video file exists
- Check ffmpeg installation
- Execute GIF conversion
- Verify output and report results

Verification: Run the command with --help flag to verify availability.

Process

Step 1: Validate Input File

Confirm the source video file exists and is a supported format:

# Check file exists and get info
if [[ -f "$INPUT_FILE" ]]; then
    file "$INPUT_FILE"
    ffprobe -v quiet -show_format -show_streams "$INPUT_FILE" 2>/dev/null | head -20
else
    echo "Error: Input file not found: $INPUT_FILE"
    exit 1
fi

Verification: Run the command with --help flag to verify availability.

Supported input formats: .webm, .mp4, .mov, .avi

Step 2: Check ffmpeg Installation

Verify ffmpeg is available:

if ! command -v ffmpeg &> /dev/null; then
    echo "Error: ffmpeg is not installed"
    echo "Install with: sudo apt install ffmpeg (Linux) or brew install ffmpeg (macOS)"
    exit 1
fi
ffmpeg -version | head -1

Verification: Run the command with --help flag to verify availability.

Step 3: Execute Conversion

Choose the appropriate conversion command based on quality requirements:

Basic Conversion (Fast, Larger File)
ffmpeg -i input.webm -vf "fps=10,scale=800:-1" output.gif

Verification: Run the command with --help flag to verify availability.

ffmpeg -i input.webm -vf "fps=10,scale=800:-1:flags=lanczos,split[s0][s1];[s0]palettegen[p];[s1][p]paletteuse" output.gif

Verification: Run the command with --help flag to verify availability.

Maximum Quality with Dithering
ffmpeg -i input.webm -vf "fps=15,scale=1024:-1:flags=lanczos,split[s0][s1];[s0]palettegen=max_colors=256:stats_mode=single[p];[s1][p]paletteuse=dither=bayer:bayer_scale=5" output.gif

Verification: Run the command with --help flag to verify availability.

Optimization Options

| Option | Description | Recommended Value |

|--------|-------------|-------------------|

| fps | Frames per second | 10-15 for smooth, 5-8 for smaller files |

| scale | Width in pixels (-1 maintains aspect ratio) | 800 for web, 480 for thumbnails |

| flags=lanczos | High-quality scaling algorithm | Always use for best quality |

| palettegen | Generate optimized color palette | Use for quality-critical output |

| dither | Dithering algorithm | bayer for patterns, floyd_steinberg for smooth |

Common Presets

# Thumbnail (small, fast loading)
ffmpeg -i input.webm -vf "fps=8,scale=480:-1:flags=lanczos,split[s0][s1];[s0]palettegen[p];[s1][p]paletteuse" thumbnail.gif

# Documentation (balanced)
ffmpeg -i input.webm -vf "fps=10,scale=800:-1:flags=lanczos,split[s0][s1];[s0]palettegen[p];[s1][p]paletteuse" docs.gif

# High-fidelity demo
ffmpeg -i input.webm -vf "fps=15,scale=1024:-1:flags=lanczos,split[s0][s1];[s0]palettegen=max_colors=256[p];[s1][p]paletteuse" demo.gif

Verification: Run the command with --help flag to verify availability.

Step 4: Verify Output

Confirm successful conversion and report metrics:

if [[ -f "$OUTPUT_FILE" ]]; then
    echo "GIF generated successfully: $OUTPUT_FILE"

    # Report file size
    SIZE=$(du -h "$OUTPUT_FILE" | cut -f1)
    echo "File size: $SIZE"

    # Get dimensions and frame count
    ffprobe -v quiet -select_streams v:0 -show_entries stream=width,height,nb_frames -of csv=p=0 "$OUTPUT_FILE"
else
    echo "Error: GIF generation failed"
    exit 1
fi

Verification: Run the command with --help flag to verify availability.

Exit Criteria

  • [ ] Input file validated as existing video format
  • [ ] ffmpeg confirmed available
  • [ ] GIF file created at specified output path
  • [ ] Output file size reported to user
  • [ ] No ffmpeg errors during conversion

Troubleshooting

Large Output File

Reduce quality settings:

# Lower fps and resolution
ffmpeg -i input.webm -vf "fps=8,scale=640:-1:flags=lanczos,split[s0][s1];[s0]palettegen[p];[s1][p]paletteuse" smaller.gif

Verification: Run the command with --help flag to verify availability.

Color Banding

Use dithering:

ffmpeg -i input.webm -vf "fps=10,scale=800:-1:flags=lanczos,split[s0][s1];[s0]palettegen[p];[s1][p]paletteuse=dither=floyd_steinberg" smooth.gif

Verification: Run the command with --help flag to verify availability.

Slow Conversion

Use basic conversion without palette generation for speed:

ffmpeg -i input.webm -vf "fps=10,scale=800:-1" quick.gif

Verification: Run the command with --help flag to verify availability.

Other skills for the same job

different authors, same section of the catalogue
Canvas Design
by anthropics
vendor ×13

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

1388k tokens
Algorithmic Art
by anthropics
vendor ×10

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

15k tokens scripts
Image Enhancer
by frostant
×6

Improves the quality of images, especially screenshots, by enhancing resolution, sharpness, and clarity. Perfect for preparing images for presentations, documentation, or social media posts.

635 tokens
Video Downloader
by CommandCodeAI
×4

Downloads videos from YouTube and other platforms for offline viewing, editing, or archival. Handles various formats and quality options.

671 tokens
Histolab
by christophacham
×3

Lightweight WSI tile extraction and preprocessing. Use for basic slide processing tissue detection, tile extraction, stain normalization for H&E images. Best for simple pipelines, dataset preparation, quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml.

18k tokens
Omero Integration
by christophacham
×3

Microscopy data management platform. Access images via Python, retrieve datasets, analyze pixels, manage ROIs/annotations, batch processing, for high-content screening and microscopy workflows.

32k tokens
Pydicom
by christophacham
×3

Python library for working with DICOM (Digital Imaging and Communications in Medicine) files. Use this skill when reading, writing, or modifying medical imaging data in DICOM format, extracting pixel data from medical images (CT, MRI, X-ray, ultrasound), anonymizing DICOM files, working with DICOM metadata and tags, converting DICOM images to other formats, handling compressed DICOM data, or processing medical imaging datasets. Applies to tasks involving medical image analysis, PACS systems, radiology workflows, and healthcare imaging applications.

13k tokens scripts
Transformers
by christophacham
×3

This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets.

13k tokens

How to use it

Copy the folder

Take athola/gif-generation from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.

Install what it needs

The instructions reference brew. Without those the skill loads but fails at the first command.