21,636 mods in this category, of every kind an
agent can take. Each one carries what it costs per session, what the
scan found, and whether it is the original.
Prepare and upload an approved local video to Xiaohongshu, Douyin, and WeChat Channels through the user's logged-in browser. Analyze the actual video or transcript with AI, generate platform-specific titles, descriptions, and hashtags from the content, validate official topic selection, apply scheduling and…
Generate and edit images, create videos, synthesize speech, transcribe and translate audio using multiple AI providers (OpenAI, Google, ElevenLabs, Deepgram, Fal, Luma, Replicate, Stability, Runway, OpenRouter, Edge TTS). Use when the user asks to create media assets, generate pictures, make videos, produce…
Make Gemini your default writer and image generator: the orchestrator plans and reviews while parallel agy (Antigravity CLI / Gemini) sessions do the writing, plus a gemini-imagegen skill that generates real images via Gemini's generateimage tool.
Generate and edit explorable 3D Gaussian-splat worlds from a text prompt, image, 360 panorama, or iterative pano edit using the SpAItial API — via the hosted SpAItial MCP server (bring-your-own-key). Create worlds, edit panoramas, check status, download splats, export meshes, and manage your library, then preview them.
Use this skill when asked to watch, review, summarize, or analyze videos. Popcorn extracts transcripts and key frames so you can understand video content without watching in real-time.
Create AI-powered short-form video clips from YouTube videos. Supports webhook callbacks. Runs locally from the @ssemble/mcp-server npm package. Needs 1 environment variable to run.
★not rated 7 7mo agoA
tokens not measured
originalMIT
AI video dubbing via OrcaRouter (model orca/dub): upload a video or URL, poll, download the MP4. Runs locally from the @orcadub/cli npm package. Needs 1 environment variable to run.
★not rated 7 23d agoA
tokens not measured
originalMIT
A Chinese long-form writing engine for Claude Code: topic to outline to draft to revision to typeset HTML to cover art. Bring your own corpus, it learns your voice.
★not rated 7
changed 12d agoA
tokens not measured
originalMIT
Produces whiteboard-explainer video layers from a voiceover MP3 for Your Channel YouTube channel (and similar faceless curiosity-essay channels). Orchestrates a multi-agent pipeline that transcribes the audio, plans rapid-cut scenes synchronized to narration, writes per-scene image prompts in fixed whiteboard style…
A music-playing skill that searches several online sources and controls playback through the mpv media player. It supports requests such as finding songs, pausing, continuing, skipping, changing volume, and repeating a track.
Work with Master Canvas AI video handoff packages. Use when a user provides a Master Canvas ZIP or projectmanifest.json and wants Hermes to inspect assets, preserve scene and shot order, prepare ComfyUI/LTX 2.3 jobs, or hand off prompts to Kling, Veo, or another video generation operator. Also use when a user wants…
Turn a rough idea, scene, story, creature, building, environment, or visual reference into a professional colossal-scale concept and a production-ready English image-generation prompt, then recommend suitable image models and concrete settings. Use for…
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…
A workflow for turning Korean lecture notes or subtitles into a whiteboard-style teaching video. It can combine scene images, voice narration, subtitles, dynamic timing, and a final 4K MP4.
Scaffolds a new reveal.js talk deck under talks/ from the canonical template at talks/templates/, turning a paper (LaTeX/PDF), figures, or notes into styled slides. Use whenever the user wants to create a talk, presentation, slides, or deck — for a conference, workshop, seminar, job talk, or lecture — even if they…
Compose audio-reactive music videos from existing video clips and an audio track. USE THIS SKILL when the user wants to: build a music video from clips that react to the song's beats / onsets / spectral content, create rapid-cut hard-cut edits synced to a song, build a DMT-flash / Tron-aesthetic video, or compose a…
★not rated 7 1mo agoA131 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: