gifhorse

0
0
Source

Search video dialogue and create reaction GIFs with timed subtitles. Perfect for creating meme-worthy clips from movies and TV shows.

Install

mkdir -p .claude/skills/gifhorse && curl -L -o skill.zip "https://mcp.directory/api/skills/download/5721" && unzip -o skill.zip -d .claude/skills/gifhorse && rm skill.zip

Installs to .claude/skills/gifhorse

About this skill

GifHorse - Dialogue Search & GIF Creator

Create reaction GIFs from your video library by searching dialogue and adding timed subtitles.

What GifHorse Does

  1. Transcribe videos - Extract dialogue with timestamps by downloading subtitles, using local .srt files, or Whisper AI
  2. Search dialogue - Find quotes across your entire video library instantly
  3. Preview clips - See exactly what will be captured before creating the GIF
  4. Create GIFs - Generate GIFs with perfectly timed subtitles and optional watermarks

Setup

First Time Setup

  1. Install gifhorse (via install button above)
  2. Install FFmpeg-full for subtitle rendering (via install button above)
  3. Transcribe your video library (downloads subtitles automatically):
cd ~/gifhorse && source venv/bin/activate
gifhorse transcribe ~/Movies

The gifhorse command must be run from within its virtual environment. You can activate it with:

cd ~/gifhorse && source venv/bin/activate

Or use the activation helper:

source ~/gifhorse/activate.sh

Available Commands

Transcribe Videos

Extract dialogue from your videos (one-time per video):

# Default: downloads subtitles from online providers (fast, recommended)
gifhorse transcribe /path/to/videos

# Use only local .srt files (no downloading, no Whisper)
gifhorse transcribe /path/to/videos --use-subtitles

# Use Whisper AI (slow but works for any video)
gifhorse transcribe /path/to/video.mp4 --use-whisper

# Re-transcribe videos already in database
gifhorse transcribe /path/to/videos --force

Download Subtitles Only

Download .srt files without storing in the database:

gifhorse fetch-subtitles /path/to/videos
gifhorse fetch-subtitles /path/to/videos --skip-existing

Search Dialogue

Find quotes across your entire library:

# Basic search
gifhorse search "memorable quote"

# Search with surrounding context
gifhorse search "memorable quote" --context 2

# Show all results (no limit)
gifhorse search "memorable quote" --all

# Custom result limit (default: 100)
gifhorse search "memorable quote" --limit 50

Preview Before Creating

See exactly what will be captured:

gifhorse preview "memorable quote" 1
gifhorse preview "quote" 1 --include-before 1 --include-after 1

Create GIF

Generate the GIF with subtitles:

# Basic GIF (auto-named from dialogue, saved to exports/)
gifhorse create "memorable quote" 1

# Explicit output path
gifhorse create "memorable quote" 1 -o reaction.gif

# High quality for social media
gifhorse create "quote" 1 --width 720 --fps 24 --quality high

# Include conversation context
gifhorse create "quote" 1 --include-before 2 --include-after 1

# Substitute words in subtitles (repeatable, target segments by number from preview)
gifhorse create "the age of men" 1 --include-after 1 \
  -s 1 "men" "standardized software" \
  -s 2 "orc" "custom applications"

# Clean replace (no strikethrough)
gifhorse create "quote" 1 -r 1 "old word" "new word"

# Create and send via iMessage
gifhorse create "quote" 1 --send
gifhorse create "quote" 1 --send-to "+15551234567"

Manage Database

# Remove videos by path pattern (SQL LIKE wildcards)
gifhorse remove "%Adventure Time%"
gifhorse remove "%S01%" --yes

# Check subtitle status for a directory
gifhorse subtitle-status ~/Videos
gifhorse subtitle-status ~/Videos --missing-only

Check Status

# See transcription stats
gifhorse stats

# List all transcribed videos
gifhorse list

Configuration

# Set phone number for iMessage sending
gifhorse config --set-phone "+15551234567"

# Show current configuration
gifhorse config --show

Timing Options

Control exactly what gets captured:

  • --include-before N - Include N dialogue segments before the match
  • --include-after N - Include N dialogue segments after the match
  • --padding-before SECS - Add buffer seconds before dialogue starts (default: 1.0)
  • --padding-after SECS - Add buffer seconds after dialogue ends (default: 1.0)
  • --start-offset SECS - Manual adjustment to start time (can be negative)
  • --end-offset SECS - Manual adjustment to end time (can be negative)

Important: For reactions after dialogue, use --padding-after instead of --include-after. The include-after option captures ALL time until the next dialogue segment (could be 30+ seconds!).

Quality Options

  • --quality low|medium|high - Color palette quality (affects file size)
  • --fps N - Frames per second (default: 15, use 24 for smooth)
  • --width N - Width in pixels (default: 480, use 720 for HD)

Subtitle Options

  • -s, --sub NUM OLD NEW - Substitute words in a segment (repeatable). Replaced words render struck through in red, replacements in red. Segment numbers shown by preview.
  • -r, --replace NUM OLD NEW - Replace words cleanly (no strikethrough). Repeatable.
  • --no-subtitles - Create GIF without subtitle overlay

Output

  • Default output filename is auto-derived from dialogue text (e.g., i_dont_think_so.gif) and saved to exports/
  • Use -o PATH to override. Collision handling appends _2, _3, etc.

iMessage

  • --send - Send created GIF to configured phone number via iMessage (macOS only)
  • --send-to NUMBER - Send to a specific phone number (overrides config)

Note: All GIFs automatically include a subtle "gifhorse" watermark in the bottom-right corner.

Common Workflows

Quick Reaction GIF

gifhorse search "perfect"
gifhorse create "perfect" 1 --padding-after 2.0

Full Conversation Exchange

gifhorse search "key phrase"
gifhorse preview "key phrase" 1 --include-before 2 --include-after 1
gifhorse create "key phrase" 1 --include-before 2 --include-after 1

Meme with Word Substitution

gifhorse preview "the age of men" 1 --include-after 1
gifhorse create "the age of men" 1 --include-after 1 \
  -s 1 "men" "standardized software" \
  -s 2 "orc" "custom applications"

High Quality for Twitter/X

gifhorse create "quote" 1 --width 720 --fps 24 --quality high -o tweet.gif

Scene with Reaction After Dialogue

gifhorse create "memorable line" 1 --padding-after 3.0

Create and Send via iMessage

gifhorse config --set-phone "+15551234567"
gifhorse create "quote" 1 --send

Tips & Tricks

  1. Always preview first - Use preview to verify timing before creating
  2. Default downloads subtitles - Just run gifhorse transcribe and subtitles are fetched automatically
  3. Watch file sizes - High quality + long duration = large files (20s can be 20+ MB)
  4. Padding vs Include - For reactions, use --padding-after not --include-after
  5. Search with context - Add --context 2 to see surrounding dialogue
  6. Re-transcribe with --force - Use --force to update transcriptions after getting better subtitles
  7. Check subtitle coverage - Use subtitle-status to see which videos need subtitles

File Size Guide

  • Low quality, 10s, 360p: ~1-2 MB
  • Medium quality, 10s, 480p: ~3-5 MB
  • High quality, 20s, 720p: ~20+ MB

Troubleshooting

"command not found: gifhorse"

Activate the virtual environment:

cd ~/gifhorse && source venv/bin/activate

Subtitle rendering errors

Make sure FFmpeg-full is installed:

brew install ffmpeg-full

Video file not found

The database stores absolute paths. If you moved videos after transcription, re-transcribe in the new location.

Network Share Support

GifHorse works with network-mounted videos:

# Mount network share (macOS)
open "smb://server-ip/share-name"

# Transcribe from network
gifhorse transcribe "/Volumes/server-ip/Movies"

When to Use This Skill

Invoke gifhorse when the user wants to:

  • Search for dialogue or quotes in their video library
  • Create a reaction GIF from a movie or TV show
  • Make a meme GIF with substituted words
  • Add subtitles to a video clip
  • Transcribe videos for searchable dialogue
  • Preview what a GIF will look like before creating it
  • Send a GIF via iMessage
  • Remove videos from the database
  • Check subtitle status for their video collection

Learn More

License

MIT

seedream-image-gen

openclaw

Generate images via Seedream API (doubao-seedream models). Synchronous generation.

2359

ffmpeg-cli

openclaw

Comprehensive video/audio processing with FFmpeg. Use for: (1) Video transcoding and format conversion, (2) Cutting and merging clips, (3) Audio extraction and manipulation, (4) Thumbnail and GIF generation, (5) Resolution scaling and quality adjustment, (6) Adding subtitles or watermarks, (7) Speed adjustment (slow/fast motion), (8) Color correction and filters.

6723

context-optimizer

openclaw

Advanced context management with auto-compaction and dynamic context optimization for DeepSeek's 64k context window. Features intelligent compaction (merging, summarizing, extracting), query-aware relevance scoring, and hierarchical memory system with context archive. Logs optimization events to chat.

3722

a-stock-analysis

openclaw

A股实时行情与分时量能分析。获取沪深股票实时价格、涨跌、成交量,分析分时量能分布(早盘/尾盘放量)、主力动向(抢筹/出货信号)、涨停封单。支持持仓管理和盈亏分析。Use when: (1) 查询A股实时行情, (2) 分析主力资金动向, (3) 查看分时成交量分布, (4) 管理股票持仓, (5) 分析持仓盈亏。

9121

himalaya

openclaw

CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).

7921

garmin-connect

openclaw

Syncs daily health and fitness data from Garmin Connect into markdown files. Provides sleep, activity, heart rate, stress, body battery, HRV, SpO2, and weight data.

7321

You might also like

flutter-development

aj-geddes

Build beautiful cross-platform mobile apps with Flutter and Dart. Covers widgets, state management with Provider/BLoC, navigation, API integration, and material design.

643969

drawio-diagrams-enhanced

jgtolentino

Create professional draw.io (diagrams.net) diagrams in XML format (.drawio files) with integrated PMP/PMBOK methodologies, extensive visual asset libraries, and industry-standard professional templates. Use this skill when users ask to create flowcharts, swimlane diagrams, cross-functional flowcharts, org charts, network diagrams, UML diagrams, BPMN, project management diagrams (WBS, Gantt, PERT, RACI), risk matrices, stakeholder maps, or any other visual diagram in draw.io format. This skill includes access to custom shape libraries for icons, clipart, and professional symbols.

591705

ui-ux-pro-max

nextlevelbuilder

"UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient."

318399

godot

bfollington

This skill should be used when working on Godot Engine projects. It provides specialized knowledge of Godot's file formats (.gd, .tscn, .tres), architecture patterns (component-based, signal-driven, resource-based), common pitfalls, validation tools, code templates, and CLI workflows. The `godot` command is available for running the game, validating scripts, importing resources, and exporting builds. Use this skill for tasks involving Godot game development, debugging scene/resource files, implementing game systems, or creating new Godot components.

340397

nano-banana-pro

garg-aayush

Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.

452339

fastapi-templates

wshobson

Create production-ready FastAPI projects with async patterns, dependency injection, and comprehensive error handling. Use when building new FastAPI applications or setting up backend API projects.

304231

Stay ahead of the MCP ecosystem

Get weekly updates on new skills and servers.