Repository instructions for a Chinese image-analysis skill that turns an image into a structured description and a Chinese prompt for generating similar images. They define the source files, output language, evidence standards, and maintenance rules.
Instructions for yuji-hatakeyama/opencode-gpt-imagegen, a project described as: OpenCode plugin: image generation via your ChatGPT subscription or OpenAI API.
Instructions for fal-ai-community/genmedia-cli, a project described as: Agent-first CLI for fal.ai — search, run, and manage 1000+ generative AI models.
Instructions for WeModulate/bitwig-mcp-server, covering bitwig mcp server - claude code guide, project overview, project-specific guidelines, development workflow and mcp implementation guidelines.
Instructions for t0mtaylor/peepshow, covering agents.md — peepshow, what peepshow is, when to invoke it, how to invoke and annotate the report after reading.
Instructions for t0mtaylor/peepshow, a project described as: Turn a video — or an animated GIF, APNG, or WebP — into a timeline of still frames so an LLM can "watch" it as a series of images.
Instructions for yfge/ai-video-studio, covering agents guidance for ai-video-studio, instruction order, repository mission, agent system of record and working rules.
Instructions for yfge/ai-video-studio, a project described as: AI video production workflow platform for professional short drama teams. Timeline-first, harness-tested, agent-assisted.
Instructions for froggeric/gemini-watermark-and-synthid-remover, covering claude.md, build commands, architecture, pipeline: detect → remove → inpaint and ai denoise (optional, off by default).
Copilot instructions for ProfRino/Blender-MCP-Assembly-Skill: When writing Blender Python code that creates geometry via MCP tools (mcpblenderexecuteblendercode), always follow the workflow defined in SKILL.md.
Claude Code instructions for gabuldev/auto-edit-video, covering auto-edit-video, quick reference, editar short (vertical, com legendas), editar long (horizontal, sem legendas, com overlays) and batch (vários vídeos).
Claude Code instructions for appautomaton/presentation, a project described as: A business question goes in. A consulting-grade deck comes out. Four composable skills for Claude Code and Codex: strategy storyboarding, brand identity, pixel-perfect PDF, native editable PPTX.
Instructions for soniqo/speech-studio, a project described as: Open-source desktop voice-cloning studio for creators — clone a voice, script lines with emotion markers, synthesize on-device. Tauri + VoxCPM2, runs on macOS, Windows, and Linux.
Claude Code instructions for SkyeShark/eidoverse-video, a project described as: Video-production toolkit for AI agents: Deno + WebGPU + three.js/TSL render engine with VRM character locomotion, simulations, effects, and a full audio pipeline — real-time GPU rendering with minimal CPU.
Claude Code instructions for nmbrthirteen/podcli, covering podcli + podstack: ai podcast content studio, slash commands (podstack), mcp tools (podcli engine), the full pipeline and knowledge base.
Instructions for jeremyruppel/claude-collider, covering claude collider, skills, prefer mcp tools over raw sc code, quick reference and cc api reference.
Instructions for elliottdehn/wam, covering wam repository guidance, local setup, multi-image and multi-view contract, colour and validation and safety.
Claude Code instructions for jsoncut/jsoncut-skill, a project described as: AI agent skill for seamless integration with JsonCut, enabling automated creation and editing of videos and images using the jsoncut.com API.
Instructions for guimatheus92/mcp-video-analyzer, a project described as: MCP server that turns any video — YouTube, Instagram, TikTok, Loom, X, Vimeo, direct URLs, local files — into transcripts, key frames, OCR text, and metadata for AI agents.