AI Plugin IndexMedia
There are 2,478 media tools for AI assistants in this directory: 1,052 MCP servers and 1,426 skills. The highest scored are voicemode, FunASR, Remove AI Watermarks.
The best media MCP servers, compared →Top picks
voicemode
mbailey
95Natural voice conversations for AI assistants - STT/TTS via MCP
AAA
FunASRmodelscope
94Transcribe local audio with FunASR and SenseVoice using private, on-device inference.
AAA
Remove AI Watermarkswiltodelta
94Identify and remove AI watermarks and provenance metadata from your own images and video.
AAA
FFmpegpollinations
91Trim, convert, resize, compress, and remix audio and video.
AAB
Ffmpeg Skill
kajisho5
90Agent Skill that gives coding agents (Claude Code, Cursor, Codex) a local video editor: 42 FFmpeg tools with a machine-readable contract, contract-derived MCP server, FFmpeg capability detection, probe-first / verify-last workflow. Cut, join, silence remo
AAA
Meigen
jau123
90Composable image and video generation tools, reusable visual skills, and optional creative workflows for MCP clients
AAA
MCP servers (153)
- 1voicemode mbailey · MediaNatural voice conversations for AI assistants - STT/TTS via MCP95
- 2FunASR modelscope · MediaTranscribe local audio with FunASR and SenseVoice using private, on-device inference.94
- 3Remove AI Watermarks wiltodelta · MediaIdentify and remove AI watermarks and provenance metadata from your own images and video.94
- 4FFmpeg pollinations · MediaTrim, convert, resize, compress, and remix audio and video.91
- 5Ffmpeg Skill kajisho5 · MediaAgent Skill that gives coding agents (Claude Code, Cursor, Codex) a local video editor: 42 FFmpeg tools with a machine-readable contract, contract-derived MCP server, FFmpeg capability detection, probe-first / verify-last workflow. Cut, join, silence remo90
- 6Meigen jau123 · MediaComposable image and video generation tools, reusable visual skills, and optional creative workflows for MCP clients90
- 7Sapiens Sintéticos inhabitants · MediaOperate your Sapiens Sintéticos AI studio: generate image, article, voice, music and video.89
- 8Claude Video Vision jordanrendric · MediaMCP server that gives Claude Code the ability to watch and understand videos — extracts frames via ffmpeg and processes audio via multiple backends89
- 9Glif glifxyz · MediaGenerate images, video, and audio with Glif's media-generation agent87
- 10SyncSo SyncSo-Inc · MediaLive New York events, shows, classes, tours, markets, music, theater, comedy, art and nightlife87
- ADYour product hereThis row is seen by people browsing media tools. Book it from $249 a month.See prices →
- 11CartCut cartesiancs · MediaEdit video in the CartCut desktop editor: cuts from a transcript, captions, motion, effects.87
- 12Kinocut KyaniteLabs · MediaGuardrailed video editing MCP server: 200 FFmpeg tools, Video Receipts, Shorts repurposing.87
- 13Capcut CLI renezander030 · MediaIndependent, unofficial CLI to create and edit CapCut projects — build drafts from scratch, add video/audio/text, subtitles, timing, speed, volume, templates, cut long-form to shorts. No API needed. Not affiliated with ByteDance.87
- 14Ima2 Gen lidge-ai · MediaLocal-first visual generation runtime and studio for people and coding agents, with reproducible image and video workflows across multiple providers.87
- 15mcp Tuteliq · MediaDetect grooming, bullying, fraud, and 16+ online threats across text, voice, image, and video.86
- 16Your Move Exercise Video API ymove-app · Media1,413+ HD exercise videos with muscles and instructions, plus workout and program generation.86
- 17Server Video Resource modelcontextprotocol · MediaMCP App Server demonstrating video resources served as base64 blobs86
- 18Server Sheet Music modelcontextprotocol · MediaMCP App Server for rendering and playing sheet music from ABC notation86
- 19Tanvo tanvoai · MediaAI photo, video and song apps plus image, video and music generation on Tanvo (tanvo.ai).85
- 20ClipmivoAI BarneyD66 · MediaAI video workflows: model discovery, credit quotes, generation, private media and usage.85
- 21watch-skill oxbshw · MediaWatch video and live sessions, keep timestamped evidence, and verify an agent's own work.85
- 22Wisp Agents M0xoo · MediaLaunch coding agents, skip the transcript, read the presentation.85
- 23Rendobar rendobar · MediaTransform video, audio and images, and generate media from prompts. FFmpeg, captions, models.84
- 24VIDIA lead788 · MediaVIDIA AI video production: get quotes, start videos, track progress and download results84
- 25Opentabs Plugin Spotify opentabs-dev · MediaOpenTabs plugin for Spotify84
- 26myspAIce neltomw · MediamyspAIce, give your AI a social life: games, music, friendships. An immersive world. Just walk in.83
- 27image-diff pulsemcp · MediaMCP server for programmatic image comparison and visual diff generation.83
- 28REAPER MCP TwelveTake-Studios · MediaEnables AI assistants to control REAPER for mixing, mastering, MIDI and music production.83
- 29Audio audiojs · MediaEdit, analyze and convert audio: loudness, spec checks, denoise, EQ, cuts, BPM, key. No ffmpeg.83
- 30Vivid MCP loopotv · MediaMCP server for VIVID (vividai.tv): generate images, videos, voice and music, edit timelines, record UI walkthroughs, browse your assets and jobs from Claude, Cursor or any MCP client.83
- 31Server Transcript modelcontextprotocol · MediaMCP App Server for live speech transcription83
- 32showtime FavioVazquez · MediaLocal video studio for your coding agent: scenes, voice, music and captions, on your machine.82
- 33three.ws Solana Memo Media nirholas · MediaExtract validated image data URIs from Solana SPL Memos and return them inline to MCP clients.82
- 34three.ws Vision nirholas · MediaImage understanding for AI agents — analyze and describe any image via the three.ws pipeline.82
- 35Aleph Siliconflow MCP rootazero · MediaAleph's official SiliconFlow media-generation MCP server (image / video / TTS)82
- 36Wezard guxi11 · MediaBridge Claude Code and WeCom: PreToolUse approval cards + bidirectional tmux session mirror with image paste82
- 37Video Extract yanlingLabs · MediaDownload any video from a URL, or get its transcript and key frames. All local, no API keys.81
- 38gemini-mcp chrischall · MediaGenerate and edit images with Google Gemini (Nano Banana / Nano Banana Pro) image models.81
- 39Kinocut KyaniteLabs · MediaGuardrailed video editing for AI agents: FFmpeg, captions, effects, Hyperframes, and receipts.81
- 40mcp-video KyaniteLabs · MediaCompatibility package: mcp-video now installs Kinocut (formerly mcp-video).81
- 41NotebookLM MCP roomi-fields · MediaAutomate Google NotebookLM — Q&A with citations, audio, video, content generation81
- 422dai MCP Server 2DAICommunity · MediaMCP server for 2DAI — let Claude, Cursor, Cline and Windsurf generate images and video, upload references and organise your cloud drive on your own 2DAI account.81
- 43Idiolect MCP Moshpit-Labs · MediaMCP server that gives any MCP-compatible AI (Claude, etc.) your Idiolect AI voice — make AI write as you. https://idiolect.app81
- 44Vibeaudio kiril6 · MediaProcedural focus music while your AI coding tools (Claude Code, Codex, Cursor, Grok, Gemini, Copilot) think — a different arrangement per project.81
- 45Cursorcam Avijit07x · MediaAsk your AI agent for a demo video. CursorCam clicks through your web app and renders a polished MP4 that zooms in on each click, from any MCP agent, Claude Code or the CLI.81
- 46PixelDojo blovett80 · MediaGenerate images, video, audio and short films with 140+ AI models from any MCP client.80
- 47LeClap heristop · MediaCompose and render video from one JSON template. Deterministic, runs locally, no generative model.80
- 48vibo-mcp chrischall · MediaVibo (vibodj.com) MCP — plan & manage event music: timeline, songs, ideas, questions, guests80
- 49voice-mcp forgemeshlabs · MediaGive Your Agent A Voice: x402 pay-per-call speech with 20 voices, 10 personas, 31 languages.80
- 50CraftStory itseez3d · MediaTalking-avatar videos from a photo (CraftStory 2.0) and short clips with sound (MiniMax H3).80
- 51Sonicmatch js713-lab · MediaAnalyze video mood and pace, then recommend license-safe BGM with a mix spec.80
- 52Framejam moritzkremb · MediaReview videos from your coding agent: pick a style, then point at the frame and say what to change. Works with Hyperframes, Remotion and any other video tool, over MCP.80
- 53Contenthero MCP contenthero-ai · MediaOfficial ContentHero MCP server. Generate images, video, and audio from any MCP client (Claude Code, Claude Desktop, etc.) using your ContentHero API key.80
- 54Voicelayer MCP EtanHey · MediaVoice I/O layer for AI coding assistants — local TTS, STT, session booking. MCP server.80
- 55Agentvibes paulpreibisch · MediaNow your AI Agents can finally talk back! Professional TTS voice for Claude Code, Claude Desktop (via MCP), and Clawdbot with multi-provider support.80
- 56Creative MCP postward-cc · MediaLocal-first MCP server for video and image editing — ffmpeg and ImageMagick driven by natural language. 100% offline: no keys, no network calls, no uploads, no account.80
- 57Vibeframe MCP Server vericontext · MediaVibeFrame MCP Server - frontier AI video generation for agents (Seedance, Runway, Kling, Gemini Omni) on your own keys, behind a hard cost cap80
- 58Vibeframe CLI vericontext · MediaFrontier AI video generation for coding agents - Seedance, Runway, Veo, and Kling on your own keys, behind a hard cost cap80
- 59applemusic-mcp epheterson · MediaApple Music MCP server: playlists, library, catalog, playback and Up Next, on Mac/Windows/Linux.79
- 60genrelay-mcp gaoruitech · MediaGenerate video and images (Veo 3.1, Grok Imagine, Nano Banana, GPT Image 2) via the GenRelay API.79
- 61Gizmos Audacity gizmos-quest · MediaSafe local audio editing, analysis and production in Audacity 3.7 through mod-script-pipe.79
- 62longtake svatrous · MediaDrive Longtake Studio from an agent: AI video takes on your own API key, characters, drafts, costs79
- 63Lumenkey CLI uncletyson · MediaUnified CLI & MCP Server for LumenKey Multi-Modal AI (Video, Image & LLMs)79
- 64AI Voice henriquearthur · MediaMCP server that lets AI agents speak through Amazon Echo devices79
- 65Scientific Figure Library xuzhougeng · MediaLocal image-code knowledge library with native macOS and local Web clients, plus MCP and Skill for Pi, DeepSeek Harness (dsh), Claude, Codex, Cursor, and Wisp.79
- 66Music Metadata MCP stevebirring-star · MediaMCP server for the FreqBlog Music API — 23 tools covering audio features, honestly-labelled tags, recommendations (Spotify /recommendations + related-artists replacement), harmonic radio, DJ transition scoring + setlist ordering, DJ-format export (Rekordb79
- 67Tracegist MCP Bridge miaswu · MediaLocal-first MCP bridge for reading and transcribing TraceGist package zips.79
- 68Video Editor MCP GitHub Actions · MediaHiggsfield Video Editor as a local MCP server over stdio: edits TSX video projects on this machine with the higgsedit CLI and serves the editor panel.79
- 69spotifyscraper AliAkhtari78 · MediaPublic Spotify metadata, lyrics and podcasts for LLM agents. No API key, read-only.78
- 70macos-mcp-server cyanheads · MediaControl macOS system settings, apps, windows, audio, displays, screenshots, and Focus mode via MCP.78
- 71Kokon GabrieleLozupone · MediaGenerate and edit images offline with Qwen-Image 2.1 on your GPU. Needs the Kokon desktop app.78
- 72PlaceCall voygr-tech · MediaReal phone calls to US businesses: book, ask, get quotes. Returns outcome and transcript.78
- 73Bilibili MCP Server XZXZZX-Ai · MediaBilibili MCP tool for video metadata, transcripts, subtitles, and comment summarization78
- 74Kie AI MCP Server felores · MediaMCP server for Kie.ai APIs: image, video, music and speech generation across Nano Banana, Veo3, Suno, ElevenLabs, ByteDance, Qwen, Runway, Midjourney, Wan, MiniMax H3, Kling, GPT Image 2, Flux Kontext, Recraft, Ideogram, Topaz, HappyHorse and more.78
- 75Dsh Plugin Continuity linxuhao · MediaLocal image / voice / music / SFX generation for DeepSeek Harness with pinned identity: the same character stays the same character across calls, degenerate output is refused rather than returned, and the GPU is untouched when idle. Hand the image half to78
- 76pagebolt Custodia-Admin · MediaScreenshots, PDFs, OG images, page inspection, and narrated video recording for Claude and Cursor.77
- 77BeatDesign BeatAPI · MediaLocal-first open-source AI media workbench with Canvas, video editor, Assets, and MCP tools.77
- 78MarkuprPlus hashfunction · MediaRecords your screen and voice, returns one annotated screenshot and finding per mark.77
- 79mac-voice-mcp jeet0007 · MediaTalk with your AI assistant out loud on a Mac, with on-device speech recognition (whisper.cpp).77
- 80watch-cli sonpiaz · MediaHand any social video to your AI agent — frames + transcript bundled. MCP server for watch-cli.77
- 81Kolbo MCP Zoharvan12 · MediaKolbo AI MCP Server - Generate images, videos, music, speech, and sound effects from Claude Code77
- 82Talqing MCP hello-talqing · MediaMCP server for building Talqing AI voice, video and text agents from Claude Code, Codex, or any MCP client.77
- 83Friend Assistant masterdeepak15 · MediaA self-hosted personal AI assistant for your own PC: a full-screen stage, voice, tools with your approval, and your Claude subscription or a local model.77
- 84Cleanor cleanor-app · MediaZero-auth MCP: image optimize, cited storage/format data, and dev utilities LLMs get wrong.76
- 85katto-mcp miracleweasel · MediaAI video clipping MCP: long videos and podcasts into scored, captioned 9:16 shorts.76
- 86ideogram-mcp qmediat · MediaIdeogram platform MCP (api v2): 18 image models, price quotes, async generations, raw call76
- 87Podkst MCP Server GitHub Actions · MediaOfficial MCP server for podkst.ai: generate AI podcasts (two-host dialogue, monologue, script-to-audio) from any MCP client over stdio.76
- 88Faceless MCP pushpit07 · MediaMCP server for Faceless.so (alias for `faceless mcp`): drive AI faceless video generation, series and publishing from any MCP client.76
- 89Slng AI MCP GitHub Actions · MediaSLNG MCP server: create SLNG managed voice agents, attach phone numbers and place outbound calls from AI assistants.76
- 90Cueframe cueframe-ai · MediaCueFrame video editing CLI: manage media, edit compositions and render MP4s from terminals and scripts.76
- 91Image Tools MCP Server jon-the-dev · MediaMCP server for image optimization, thumbnail generation, and format conversion using ImageMagick76
- 92Gradus Notation delmas41 · MediaGradus Notation + Harmonic Analyzer + Engraver: music tools for any AI agent. Free, no auth.75
- 93ChatSpatial cafferychen777 · MediaSchema-enforced spatial transcriptomics analysis with 20 tools and 65 methods via MCP75
- 94mediagen Cripacx · MediaGenerate images and video from text prompts across Gemini, OpenAI and Kie AI.75
- 95mcp-listen decibri · MediaGive your AI agents the ability to listen. Microphone capture and speech-to-text.75
- 96atx-mcp gridhra · MediaDeterministic, non-generative image transform MCP server: reproducible recipes, immutable originals.75
- 97Music Studio linxule · MediaABC sheet music + Strudel live coding: songs, videos and live jam sessions in ext-apps widgets.75
- 98Sonilo Music & Sound Effects sonilo-ai · MediaLicensed soundtracks and sound effects matched to your video. Commercial use OK.75
- 99Vibelore fbwndrud · MediaLocal MCP server for writing consistent serial fiction with continuity checks and approval workflows, then adapting chapters into webtoon scenes: one image per scene with dialogue in the work language, pre-generation checks and visual review.75
- 100Familiar Ryanjansen92 · MediaAI co-pilot for Foundry VTT: runs combat, scenes, voices and audio. Requires the Familiar module.74
- 101Image Gen nuver-labs · MediaGenerate and edit images from your coding agent with Gemini and OpenAI, using your own API keys.74
- 102gpt-image-mcp youbotapi · MediaGenerate and edit images with GPT Image 2.5 for $0.029 — free key, 50 credits, no card.74
- 103Video Editor MCP agiflow-ai · MediaMCP server for video editing with Remotion74
- 104Audivo AudivoDotDev · MediaPodcast transcripts: send an episode link and get the transcript back, a page at a time.73
- 105Jovie JovieInc · MediaCreate a music artist's Jovie profile from a Spotify URL and read public artist data.73
- 106Tag-per-Track Lory97 · MediaAudio analysis and A&R scoring for music tracks: tags, lyrics, artist stats, demo triage.73
- 107Pedra pedra-ai · MediaAI real-estate photo editing and 360° virtual tours via the Pedra API: staging, renovation, video.73
- 108Gemini fritzprix · MediaA Gemini MCP server providing multimodal analysis and image/video generation.73
- 109Aurora CLI EricDisero · MediaAurora CLI: drive the Aurora AI audio workbench from your terminal or let Claude Code shell out to it. Music generation, covers, sample manufacturing, 7-stem separation — plus bundled agent skills and an MCP configurator.73
- 110Navidrome MCP Blakeem · MediaMCP server for interacting with Navidrome music server73
- 111AI Video Enhancer Studio contentasoftware · MediaUpscale, stabilize, denoise and raise the frame rate of videos locally on your NVIDIA GPU72
- 112Dropl MCP develanet · MediaCreate client-editable photo and video galleries from Cursor or Claude Code, then embed them.72
- 113runapi-mcp runapi-ai · Media130+ AI models for image, video, music, and audio — 18 model families, one RunAPI account.72
- 114Pindoupic qxshn · Mediapindoupic 拼豆图纸生成器 — 图片转拼豆图纸的 CLI + MCP Server。算法与色板都在包内，断网也能出图，图片不上传 / Image → bead pattern chart, CLI + MCP, works fully offline72
- 115mcp Primate-Intelligence · MediaVideo scene understanding for AI agents via the Primate Vision API.71
- 116Vidofy vidofy · MediaGenerate video, images, audio and speech with Vidofy — Veo 3.1, Kling 3.0, Flux 2 and 570+ models.71
- 117Barevalue barevalue-ai · MediaAI podcast editing. Sign up in one call, send audio by link or from disk, get an edited episode.71
- 118Suno MCP YellowKode-Academy · MediaMCP Server for Suno AI — Generate music directly from Claude, Cursor, and any MCP-compatible client. by YellowKode Academy71
- 119Short Video Agent Kit davidmosiah · MediaProvider-neutral short-form AI video toolkit for agents: Sora, Gemini Veo, xAI/Grok, Seedance.70
- 120gongio-mcp JustinBeckwith · MediaMCP server for Gong.io - access calls, transcripts, and users70
- 121mcp-usage Rixtayz · MediaFind out which MCP servers you actually use: local, read-only audit of Claude Code transcripts.70
- 122mcp sudomock · MediaProduct mockup API. Render PSD and photo mockups, generate videos, manage async jobs and webhooks.70
- 123Chutes Media MCP TheStreamCode · MediaGenerate image, video, music and speech through Chutes and save assets into your project.70
- 124Ableton Live MCP Server wstierhout · MediaControl Ableton Live with 156 typed tools for music production and offline .als analysis.70
- 125Frameflow MCP msaeedsakib · MediaMCP server for Google image and video models (Nano Banana, Gemini Omni, Veo) on Gemini Enterprise Agent Platform, with a one-command service account setup for Claude Code, Cursor and Codex70
- 126Slatesvideo CLI EricDisero · MediaSlates CLI: drive the Slates AI video studio from your terminal or let Codex (with your ChatGPT account) or Claude Code shell out to it. Includes the bundled agent skills and an MCP client configurator.70
- 127Viber Channel dgx80 · MediaVoice + text MCP channel between a Claude Code session and the Viber UI (https://viber.dgypx.dev). Push transcripts to Claude; send_message tool delivers text back to the UI.70
- 128Framekit morshoto · MediaAgentic video editing runtime and MCP server for Final Cut Pro70
- 129DialMCP SkillfulAgents · MediaLet AI agents place real phone calls from your verified number, with transcripts and recordings.69
- 130Ottoport Jet1217 · MediaClaude Code plugin, CLI and MCP server for OttoPort — one OpenAI-compatible API for every LLM, image, video, and speech model.69
- 131Kimi Read Image MCP hlf01 · MediaMinimal MCP server that exposes a single kimi_read_image tool for Moonshot and Kimi Coding.69
- 132Simpligen MCP RaynoldVanHeyningen · MediaMCP server for SimpliGen -- drive local/cloud AI image & video generation from an agent.69
- 133The Scribble Thing Boring-Stuff-Club · MediaTurn one line-art image into a prompt-directed, hand-drawn scribe animation MP4.68
- 134clipkit clipkit-video · MediaMCP server for Clipkit — gives AI agents a video toolbox via the Clipkit schema.68
- 135ffmpeg-render-pro beeswaxpat · MediaParallel video rendering tools: detect GPU encoders, render, color grade, merge audio, concat.68
- 136editmamei editmamei · MediaPhotoshop MCP server: natural-language AI photo editing in desktop Photoshop. AI orchestration.68
- 137Jw MCP advenimus · MediaMCP server for JW.org content: Bible scripture lookup with study content, workbook materials, Watchtower articles, and video captions68
- 138Image Vision MCP staticdeng · MediaMulti-model vision MCP server (GLM-4.6V, Kimi, Qwen-VL, GPT-4o) that lets text-only coding models in Claude Code see and understand images.68
- 139Fathom MCP Server agencyenterprise · MediaConnect Claude to Fathom meeting recordings, transcripts, and summaries67
- 140DiffSense GoldenSupremeSaltedFish · MediaMR/PR risk audit MCP server: semantic diff + rule engine, strict read-only. Run as image or pip.67
- 141Taoyuan Music JerryYangAI · MediaWrite an original song for one person: lyrics, two full versions and cover art in about a minute.67
- 142Boson Video linboxin · MediaLet your AI read any video: timed transcript, full-resolution frames, screen text, claim checks.67
- 143Vocametrix Voice Analysis pmarmaroli · MediaClinical voice analysis MCP server — AVQI, DSI, jitter/shimmer, pronunciation assessment, and more.67
- 144rootvine-mcp RagingOrangutan · MediaNeutral commerce resolution for AI agents — music live, ranked by trust, never by commission.67
- 145darkroom sathergate · MediaImage processing pipeline for Next.js. Responsive optimization with Sharp.67
- 146MCP Tts Voicevox kajidog · MediaVOICEVOX integration for MCP - Text-to-Speech server using VOICEVOX engine67
- 147Calldesktech MCP tsushanth · MediaMCP server for the CallDeskTech API — build, publish and operate voice agents (flows, subflows, knowledge bases, numbers, calls, batch calls, webhooks) from any MCP client.67
- 148Tautau MCP castlemilk · MediaMCP server for tautau content, transcription, reporting setup, bug reports, and local Studio project editing67
- 149Kimi Read Video MCP hlf01 · MediaMinimal MCP server that exposes a single kimi_read_video tool for Moonshot and Kimi Coding.67
- 150Mimo MCP Server alionsss · MediaMCP Server for MiMo multimodal capabilities (image, audio, video understanding, ASR, TTS)67
Skills (108)
- 1critical-images thedaviddias · MediaUse when reviewing image assets, markup, and CDN or build transforms related to Prioritize loading critical images. Check encoded size, rendered size, loading strategy, and above-the-fold impact together.84
- 2image-cdn thedaviddias · MediaUse when reviewing image assets, markup, and CDN or build transforms related to Serve images from a CDN. Check encoded size, rendered size, loading strategy, and above-the-fold impact together.84
- 3faq nexmoe · MediaBuild a FAQ from the current video transcript without turning it into an essay.82
- 4storyboard openJiuwen-ai · MediaTurn a brief into a one-row-per-shot storyboard table. Use when planning shot size, camera move, action, scene changes, or the prompt for a clip.82
- 5video-frames iflytek · MediaExtract a single frame from a local video at the first frame, a timestamp, or a zero-based frame index using FFmpeg.82
- 6voice-ai-engine-development sickn33 · MediaBuild real-time conversational AI voice engines using async worker pipelines, streaming transcription, LLM agents, and TTS synthesis with interrupt handling and multi-provider support82
- 7inkos-storyboard Narcooo · Media剧本与叙事文本到可拍、可画、可生图分镜的视觉拆解方法。Used for storyboard and image-prompt production.82
- 8Export Mind Map as Image SSShooter · MediaGuide for exporting mind maps as images using the built-in SCST engine from `@mind-elixir/export-mindmap`.81
- 9video-editor-development Lightricks · MediaArchitecture guidance for the LTX video editor — editor store, selectors, actions, undo/redo, persistence, keyboard behavior, timeline semantics, and hot-path performance.79
- 10manim-video affaan-m · Media日本語翻訳：このファイルは manim-video 用の日本語翻訳が必要です79
- 11music-midi ruvnet · MediaExtract MIDI/score from an existing production79
- 12voice-call spinabot · MediaStart voice calls via the Brigade voice-call plugin.79
- 13pirate genkit-ai · MediaRespond in the voice of a swashbuckling pirate.78
- 14video-frames the-open-agent · MediaExtract frames or short clips from videos using ffmpeg.78
- 15nano-banana-pro Bitterbot-AI · MediaGenerate or edit images via Gemini 3 Pro Image (Nano Banana Pro).78
- 16interactive-image alfredxw · MediaGenerate one image for an already established interactive-story turn.78
- 17yao-audio YaoApp · MediaAudio expert. ALWAYS invoke this skill when the user asks to transcribe, recognize, or convert speech/audio to text.77
- 18image-generate huangruiteng · Media使用内置 image_generate.py 脚本生成图片, 准备清晰具体的 `prompt`。76
- 19songsee Bitterbot-AI · MediaGenerate spectrograms and feature-panel visualizations from audio with the songsee CLI.76
- 20learning-from-mistakes oxbshw · MediaThe user corrected an answer about a video — "no, it actually says X", "that's the wrong timestamp", "you misread the error code" — or asks why a video answer was wrong. Use this to record the correction as a lesson so future answers on similar questions improve, and to show what the system has learned and saved.76
- 21no-ai-slop huytieu · MediaEdit drafts into sharper, more human writing while preserving the writer's personal voice, or detect AI-slop patterns without rewriting. Use when the user wants a draft clearer, more direct, more opinionated, or less AI-sounding, or asks whether writing reads as AI.75
- 22generate-video-cover xiaotianfotos · MediaGenerate a video cover through the sandboxed GPU runtime and Manager Artifact Broker.75
- 23remotion-studio remotion-dev · MediaPreview a Remotion video75
- 24meme-gen fuyuxiang · MediaGenerate meme images with text overlays using Pillow. Pick templates or create custom image macros.75
- 25ipollowork-video-soundtrack Devin-AXIS · MediaAdd or revise music, sound effects and their mix in the active iPolloWork video, using authorized sources, real editable tracks and measured event cues.74
- 26cowart-open-canvas openvetta · MediaOpen the Cowart infinite canvas (tldraw) in Vetta Desktop. Use when the user asks to open, launch, view, or work in the Cowart canvas or wants an infinite canvas for visual planning/image work.74
- 27trailsnap-agent LC044 · MediaQuery a user's TrailSnap photo library through scoped MCP tools to find photos, reconstruct memories, build person timelines, create evidence-backed narratives, or propose an album plan for explicit in-app approval. Use for the user's own TrailSnap library; never claim a proposal was executed or changed the library.74
- 28video-common trustfuture · Media各账号视频流水线共用的四道工序（事实核查与来源台账、AI 封面比例验收、平台文案机制、成片机器验收与交付边界、合规自查）。不直接触发；由各账号 skill（如本仓库的 investigation-video-skill）在对应环节引用。音色、字幕样式、品牌、时长、口吻、平台集合都不在这里，留在各账号 skill。74
- 29voice-call Bitterbot-AI · MediaStart voice calls via the Bitterbot voice-call plugin.73
- 30image-compress dongsheng123132 · Media图片压缩/转换 - 批量压缩、改尺寸、转格式（jpg/png/webp），本地处理不失隐私73
- 31web-video-download rsclaw-ai · MediaUniversal video download — capture video URL from any site and download with cookies73
- 32story-review haowjy · MediaReview work after prose exists: editorial review, craft critique, continuity/voice review, copyediting, proofreading, and synthesis of reader-sim signal. Load when diagnosing a draft rather than rewriting it.73
- 33indextts2-audio vb2250158 · Media通过 RabiSpeech 的本地 IndexTTS2 模型生成中文或音色复刻语音。用户指定 IndexTTS2、中文参考音频、情绪/风格指令、人格声线或本地 WAV 验证时使用。不得直接运行技能内 worker、启动 OumuQ 或调用云端 API。72
- 34qwen-tts-audio vb2250158 · Media通过 RabiSpeech 使用本地 Qwen3-TTS 0.6B 或 1.7B 生成人格、多语言或音色复刻语音。用户指定 Qwen3-TTS、日语/多语言、本地参考音频、人格名或模型大小对比时使用。不得启动技能内 worker、OumuQ 或任何 Qwen/DashScope 云端 API。72
- 35setup-boring-video-skills sugarforever · MediaUse when installing, validating, or repairing the Boring Video planning skill set before its first use.72
- 36rephrase iurysza · MediaProofreads and tightens supplied text while preserving meaning and voice. Use only when the user explicitly asks to rephrase, proofread, or tighten text.71
- 37deslopify iurysza · MediaRemoves generic AI mannerisms, inflated phrasing, and repetition from prose while preserving the author's voice. Use when the user asks to deslopify or naturalize a draft.71
- 38tts mikeyobrien · MediaText-to-speech on Linux -- make the device speak text aloud. Use for voice announcements, reading content aloud, or accessibility.71
- 39release-prep rojopolis · MediaPrepare a new release - bump action.yml image version, verify CHANGELOG entry and stage changes70
- 40speech QuixiAI · MediaSpeak a response aloud through the explicitly configured local voice provider70
- 41canvas-expand Xiangyu-CAS · MediaOutpaint a selected Codex-Canvas image beyond its current frame and collect the expanded image back onto the canvas.70
- 42canvas-remove-bg Xiangyu-CAS · MediaRemove the background from a selected Codex-Canvas image and collect a transparent PNG result back onto the canvas.70
- 43xunzhi-media-domain lishuangqiang · MediaAI-Meeting 媒体与实时通信知识 Skill。用于处理实时语音转写、WebSocket 推送、心跳、错误通知、长文本 TTS 和消息协议；当需求命中 `/api/xunzhi/v1/xunfei/**`、`/api/xunzhi/v1/websocket/**` 或 `@ServerEndpoint` 实时链路时使用。70
- 44cancel malob · MediaStop any currently playing text-to-speech audio69
- 45start malob · MediaEnable auto TTS for this session69
- 46say malob · MediaSpeak the last response aloud using text-to-speech69
- 47tts-router-workflow vb2250158 · MediaRabiSpeech 语音路由旧名称。选择模型、人格、语言或播放方式时加载 tts-router 的统一流程。69
- 48stt mikeyobrien · MediaSpeech-to-text — transcribe voice to text using device microphone. Use for voice commands, dictation, or hands-free input.69
- 49tts mikeyobrien · MediaText-to-speech — make the device speak text aloud. Use for voice announcements, reading content aloud, or accessibility.69
- 50tts mikeyobrien · MediaText-to-speech on macOS -- make the device speak text aloud. Use for voice announcements, reading content aloud, or accessibility.69
- 51concise-responder streamcoreai · MediaKeep voice responses short and natural for spoken conversation69
- 52error-recovery streamcoreai · MediaHandle errors, misunderstandings, and edge cases gracefully in voice conversations69
- 53speechbrain mkurman · MediaSpeechBrain — PyTorch speech toolkit. ASR, speaker recognition, speech separation, diarization, enhancement, language identification, and TTS. Recipe-based training with pre-trained model zoo.69
- 54omd-humanize 3x-haust · MediaRepair discourse from verified facts and a stable voice contract without changing meaning or inventing authority.69
- 55humanize 3x-haust · MediaRepair discourse from verified facts and a stable voice contract without changing meaning or inventing authority.69
- 56yuinijika YuiNijika · MediaYuiNijika's persona skill — personality, and coding conventions. Invoke when writing or coding in YuiNijika's voice.69
- 57openai-image-gen CoWork-OS · MediaBatch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.69
- 58agentic-image-loop CoWork-OS · MediaGenerate -> annotate -> refine -> repeat using generate_image + Visual Annotator (Live Canvas).69
- 59sphr-iiif lukehollis · MediaBuild and verify SPHR IIIF image server scenes and inspectable image planes.69
- 60diffusers mkurman · MediaHuggingFace Diffusers library for diffusion models: text-to-image, image-to-image, inpainting, super-resolution. Supports Stable Diffusion, Flux, SDXL, and custom pipelines.69
- 61image-brief-for-gen tabtin-ai · Media生图 Brief——给 Cowart/生图工具写可执行 brief。用户要生成配图、图标、海报前先写 brief 时使用。68
- 62aliyun-qvq cinience · MediaUse when visual reasoning is needed with Alibaba Cloud Model Studio QVQ models, including step-by-step image reasoning, chart analysis, and visually grounded problem solving.68
- 63ossd-add-logo opensource-observer · MediaUse when adding a logo image for an existing project in oss-directory68
- 64txt2mp3 CoderWanFeng · Media将文本内容转换为 MP3 语音文件，可选择直接朗读。当用户提到文字转语音、TTS、文本朗读、AI 配音时使用。68
- 65compress_image CoderWanFeng · Media压缩图片文件大小，通过调整质量参数控制输出体积。当用户提到压缩图片、图片减肥、缩小图片体积、降低图片质量时使用。68
- 66openreelio-video-editing openreelio · MediaUse OpenReelio MCP tools to inspect video-editing projects, validate command payloads, and propose safe edit plans.68
- 67canvas-edit-text Xiangyu-CAS · MediaRecognize visible text in a selected Codex-Canvas image, apply a user-described text edit with imagegen, and collect the result back onto the canvas.68
- 68image-generation HybridAIOne · MediaGenerate or edit raster images with the image_generate tool.68
- 69music-generation google-gemini · MediaGenerate ambient background music using Lyria via the Interactions API.68
- 70hl-camera hailo-ai · MediaCamera setup, USB/RPi configuration, and troubleshooting.67
- 71hl-event-detection hailo-ai · MediaDetect and report events from video streams.67
- 72video_gen QuixiAI · MediaVideo generation via Runway67
- 73voice_selector win4r · MediaProvides the static system voice catalog used by Jarvis. It does not define a user-facing workflow.67
- 74zimeiti-video-workflow Damonhhh · MediaRun CreatorFlow from topic selection through script, material planning, assembly, QA, and publish wrap-up.67
- 75transcribe badlogic · MediaLocal speech-to-text transcription on Apple Silicon macOS. Supports wav directly and other audio formats via ffmpeg.67
- 76pellicule sailscastshq · MediaCreate videos with Vue using Pellicule - a Vue-native video rendering library67
- 77learn-profile vasanthsreeram · MediaInterview the learner and write .alvar/LEARNER.md so one teacher can fit one mind — pace, voice, solid ground, and how they want to struggle. Use when the user runs /learn-profile or /skill:learn-profile, or says how I learn, learning philosophy, teaching style, set up tutoring, or install my learning preferences.67
- 78videogen mimimaster · MediaGenerate short videos from text or an image reference with a configured video model.66
- 79claude-collider jeremyruppel · MediaUse when live coding music with SuperCollider via ClaudeCollider MCP server.66
- 80yamdl Stmol · MediaUse for YAMDL feature work, CLI behavior, TUI behavior, provider payloads, audio artifacts, or project-specific verification.66
- 81podcast-studio OneWave-AI · MediaGenerate podcast scripts from text content. Use Tone.js and Howler.js for audio mixing. Create intro/outro music, transitions, sound effects.66
- 82openai-whisper CoWork-OS · MediaLocal speech-to-text with the Whisper CLI (no API key).66
- 83docs-social-images rhesis-ai · MediaHow the docs site generates per-page og:image cards, and the cache and font traps when changing them. Use when editing the OG card design, og-theme.js, or a page's social preview image.66
- 84get-widget-screenshot anthem-audio · MediaCapture PNG screenshots from a minimal testbed app that has full access to Anthem's Dart source code. Allows validation of UI changes; you optionally modify the testbed code to suit your needs, then you use the provided commands to capture the screenshot, then you look at the screenshot to validate changes.66
- 85effect-camera-08 aqm857886159 · Media用具体的机位与运动描述控制镜头节奏。 用户要求移轴虚化时使用。66
- 86effect-camera-25 aqm857886159 · Media用具体的机位与运动描述控制镜头节奏。 用户要求黑场转场时使用。66
- 87effect-camera-02 aqm857886159 · Media用具体的机位与运动描述控制镜头节奏。 用户要求过肩对话时使用。66
- 88effect-camera-12 aqm857886159 · Media用具体的机位与运动描述控制镜头节奏。 用户要求快动作降格时使用。66
- 89effect-camera-07 aqm857886159 · Media用具体的机位与运动描述控制镜头节奏。 用户要求摇镜扫景时使用。66
- 90effect-camera-04 aqm857886159 · Media用具体的机位与运动描述控制镜头节奏。 用户要求推轨跟拍时使用。66
- 91effect-camera-05 aqm857886159 · Media用具体的机位与运动描述控制镜头节奏。 用户要求仰拍起势时使用。66
- 92effect-camera-23 aqm857886159 · Media用具体的机位与运动描述控制镜头节奏。 用户要求叠化转场时使用。66
- 93effect-camera-06 aqm857886159 · Media用具体的机位与运动描述控制镜头节奏。 用户要求俯拍众生时使用。66
- 94effect-camera-30 aqm857886159 · Media用具体的机位与运动描述控制镜头节奏。 用户要求上帝视角时使用。66
- 95effect-camera-13 aqm857886159 · Media用具体的机位与运动描述控制镜头节奏。 用户要求焦点转换时使用。66
- 96effect-camera-21 aqm857886159 · Media用具体的机位与运动描述控制镜头节奏。 用户要求长镜头一镜到底时使用。66
- 97effect-camera-10 aqm857886159 · Media用具体的机位与运动描述控制镜头节奏。 用户要求手持跟拍时使用。66
- 98tx5dr-radio-change boybook · MediaImplement or review TX-5DR radio backends, capabilities, meters, power, PTT, audio, spectrum, connection lifecycle, and timing-sensitive RF behavior. Use for Hamlib, ICOM WLAN, TCI, and virtual-radio changes; not for UI-only wording or ordinary plugin logic.66
- 99effect-camera-11 aqm857886159 · Media用具体的机位与运动描述控制镜头节奏。 用户要求慢动作升格时使用。66
- 100effect-camera-27 aqm857886159 · Media用具体的机位与运动描述控制镜头节奏。 用户要求声音转场时使用。66
- 101effect-camera-29 aqm857886159 · Media用具体的机位与运动描述控制镜头节奏。 用户要求客观视角时使用。66
- 102effect-camera-26 aqm857886159 · Media用具体的机位与运动描述控制镜头节奏。 用户要求匹配转场时使用。66
- 103effect-camera-09 aqm857886159 · Media用具体的机位与运动描述控制镜头节奏。 用户要求逆光剪影时使用。66
- 104effect-camera-28 aqm857886159 · Media用具体的机位与运动描述控制镜头节奏。 用户要求主观视角时使用。66
- 105effect-camera-03 aqm857886159 · Media用具体的机位与运动描述控制镜头节奏。 用户要求特写情绪时使用。66
- 106effect-camera-01 aqm857886159 · Media用具体的机位与运动描述控制镜头节奏。 用户要求空镜转场时使用。66
- 107nai5-illustration-composition Miint-Sunny · MediaUse when the user already has an idea or subject and wants an illustration composition, a visual moment, staging, camera, spatial relationships, lighting, or a targeted visual design revision.66
- 108nai5-reverse-prompt Miint-Sunny · MediaUse when the user sends an image and wants a ready-to-use NovelAI V5 prompt reverse-engineered from it, or only one part of it (composition, lighting, colors, outfit, appearance, pose, expression, scene, relationships, or on-image text). Not for merely describing what an image shows.66
