3,611 tools and skills for media tasks
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user
"Extract YouTube video transcripts with metadata and save as Markdown to Obsidian vault. Use this skill when the us
A ClaudeCode skill example with OpenCode
Claude Code / Cursor skill to recommend from 7000+ Nano Banana Pro image prompts.
A Claude skill that automates NotebookLM notebook creation from YouTube videos — research featured people, add sources,
A Clawdbot skill that generates a podcast-style MP3 from one or more URLs using the open-source Podcastfy project.
配图助手 - Claude Code Skill，帮助把文章转换成统一风格的信息图提示词。来自 yunshu0909/yunshu_skillshub 项目。
官方md_exporter调整适配dify的导出pdf样式
Postiz Agents CLI - connect it to Claude / OpenClaw / etc, to schedule social media posts 🤖
Working on motion video
Uses Whisper Transcribe plus grounding to accurately transcribe audio files into text
Manus AI autonomous agent skill for OpenClaw - Research, development, automation, and media generation
A fast CLI tool for Agents to convert their text output to speech using Chatterbox TTS on Apple Silicon. Agent SKILL fil
Fix LED flicker in video footage. Streaming temporal-median for any-length 4K video in ~400MB RAM.
OpenClaw skill for Vapi (vapi.ai) voice agents
Upload images and files to Tencent Cloud Object Storage (COS) and get public URLs. Use this skill when:
Identify large disk usage on macOS, propose a cleanup plan, and perform safe disk cleanup using Trash (not rm) for commo
Claude Code skill for image generation using Gemini 3 Pro Image API
Fast speech-to-text via Groq Whisper API for OpenClaw agents
'Generate audio replies using TTS. Trigger with "read it to me [public URL]" to fetch and read content aloud,
📸 AI agent skill for creating terminal screenshots and recordings with VHS
Clawdbot skill for Pollinations.ai API - AI generation for text, images, videos, and audio with 25+ models
Create professional demo videos with browser automation (GIF recording), ElevenLabs voiceover generation, and Remotion v
OpenClaw skill: Capture screenshots and screen recordings on macOS using built-in tools
Fireflies.ai meeting transcript skill for Claude Code — search, summarize, and ask questions across meetings via GraphQL
An openclaw skill that renders LaTeX math to PNG, JPEG, WebP, or AVIF (and SVG). Use when one need a viewable image from
OpenClaw skill for WhisperX — speech-to-text with word-level timestamps, speaker diarization, and forced alignment
OpenClaw 技能：支持通过 URL 或 video_id 下载抖音视频，支持批量与 JSON 输出。OpenClaw skill for downloading Douyin videos by URL/video_id with b
"Generate text-to-speech audio using Qwen3-TTS. Supports preset speakers, voice design from descriptions, voice clo
Youtube Transcriptor
Motion graphic director skill for AI coding assistants — creative direction and design intelligence for Remotion videos
Claude Code skill for AI video & image generation via agent-media CLI
OpenClaw skill: Capture screenshots and screen recordings on macOS using built-in tools
Short-form video network for AI agents. Generate videos using the latest models, pay with USDC via x402. Mint an onchain
Claude Code skill for AI image generation via Gemini CLI + nanobanana extension
Generate images from text prompts using GLM-Image API (BigModel / Zhipu AI)
Analyze videos to extract structured knowledge including mind maps, key highlights, and timestamps. Use when users want
DIN 5008 German business letter skill for Claude Code. PDF generation with optional LetterXpress postal delivery.
xAI Grok API. Search the web, search X, generate images, generate video.
xAI Grok API. Search the web, search X, generate images, generate video.
SAAS to build and generate professional PDF resumes with drag-and-drop sections, powered by FastAPI and LaTeX
Write PlantUML sequence-diagram blocks in architecture markdown, save .puml files, render local SVG assets, and inject m
CLI audio mastering without a reference track using ffmpeg; accepts audio or video inputs and outputs mastered WAV/MP3 o
Convert PDFs to editable Word documents. Preserves layout, images, text. Handles CMYK/ICCBased colorspaces. CLI tool + C
Claude Code skill for downloading SharePoint, OneDrive, and Teams meeting recordings via Chrome DevTools MCP + ffmpeg
Control the openclaw-voice service via HTTP endpoints. Use when a user asks to start/stop voice capture, put the voice a
Revid API V2 skill for Claude Code — automate video creation, publishing, and media workflows from your terminal
Summarize YouTube videos and answer questions about them. Use when user sends a YouTube link, asks to summarize a video,
OpenClaw skill to control Apple Music via AppleScript
I'm using Abacus AI to listen during Zoom sessions, then I'm using a Claude Code tool to transfer transcrips