mordor-forge

Interactive AI image generation, editing, and composition using the gemini-media MCP (Google Gemini image models). Use this skill whenever the user asks to generate, create, draw, design, or make an image, illustration, photo, artwork, mockup, logo, icon, sticker, or any visual content. Also use when the user provides a description and wants it turned into a picture, asks to edit or modify an existing image, wants to compose multiple reference images, or mentions "gemini image", "image generation", "generate an image", or similar. This skill handles the full workflow from understanding intent through prompt engineering to model selection and iterative refinement.

Interactive AI music generation using the gemini-media MCP (Google Lyria 3 models). Use this skill whenever the user asks to generate, create, compose, or make music, a song, a beat, a soundtrack, a jingle, background music, or any audio music content. Also use when the user wants to create a melody, instrumental track, song with vocals, podcast intro music, or describes music they want to hear. Triggers on "make me a song", "generate music", "create a beat", "compose a soundtrack", "I need background music for...", "make a jingle", or any music creation request. This skill handles the full workflow from understanding musical intent through prompt construction with structure tags and lyrics to model selection and iterative refinement.

Interactive text-to-speech audio generation using the gemini-media MCP (Google Gemini TTS). Use this skill whenever the user asks to convert text to speech, generate spoken audio, create a voiceover, narrate text, read something aloud, or produce audio from written content. Also use when the user wants a specific voice or language for audio output, mentions "text to speech", "TTS", "voiceover", "narration", "read this aloud", "speak this", or wants audio versions of text content. This skill handles voice selection, language configuration, and the generation workflow.

Interactive AI video generation using the gemini-media MCP (Google Veo 3.1 models). Use this skill whenever the user asks to generate, create, or make a video, clip, animation, or motion content. Also use when the user wants to animate an existing image into video, extend a video clip, create a short film, promotional video, or any moving visual content. Triggers on "generate a video", "make a clip", "animate this image", "create a video of...", "video generation", or similar requests. This skill handles the full workflow from understanding intent through prompt engineering to async generation management and iterative refinement.

Use when the user asks to generate, create, import, refine, texture, rig, animate, convert, stylize, segment, or inspect a 3D model, mesh, asset, Gaussian splat, or game-ready object with trident-mcp.

Use when the user wants to import a generated, converted, rigged, animated, or local 3D model into Blender; set up a scene; inspect materials; adjust lighting; or render a trident-mcp output.

Use when the user wants a high-quality 3D model from multiple views, a reference photo expanded into front/side/back views, Tripo multiview reconstruction, or a multi-angle image-to-3D pipeline.

Interactive learning tutor with spaced repetition, research helpers, and restart-safe study workspaces. Use when the user wants to learn something new: teach me, I want to study, help me learn, study X, create a course on, tutorial for, walk me through learning. Also use for commands like study init, study start, study status, study review, study break, and book catalog setup/search. Works across Claude Code, Codex, Hermes, Cline, OpenCode, and other Agent Skills-compatible clients for programming, math, physics, science, engineering, and other structured learning.

Update DaVinci Resolve compatibility probes, rules, and tests safely. Use when changing GPU detection, OpenCL parsing, vendor-specific checks, CLI diagnostics, or test fixtures in this repository.