System-wide now-playing control for macOS — see and control whatever is playing (Spotify, Apple Music, browsers) right from Claude Code. Zero dependencies, no OAuth, no app lock-in.
★not rated 4 3mo agoA
tokens not measured
originalMIT
Gemini 3 Pro Image (Nano Banana Pro) CLI with Application Default Credentials (ADC) support for Vertex AI. Works in enterprise / CI / Cloud Run environments where GEMINIAPIKEY is not available.
★not rated 4
changed 13d agoA
tokens not measured
originalMIT
AI Blew My Mind (AIBMM) Amplifiers toolkit — prompts, tools, and workflows that enhance AI assistant capabilities. Includes image generation, refinement, and reference image uploads.
End-to-end pipeline for downloading Zoom cloud recordings and publishing them to YouTube with auto-generated titles, descriptions, timestamps, playlists, and AI-generated thumbnails via Gemini.
Transcribe and analyze audio content using Google Gemini. Supports local audio files (mp3, wav, m4a, ogg, flac) and YouTube links up to 9.5 hours long.
Transforma gravações longas (podcast, live, aula) em clipes verticais 9:16 com legenda queimada. A escolha dos trechos é feita pelo Claude na sessão, sem API paga. Crop ciente de cena e de quem está falando (solo / empilhado / letterbox).
Spec-driven worldbuilding plugin. Eight commands guide you from emotional seed to stress-tested world bible — interviewing, researching, locking decisions, generating concept art, and writing to your vault.
A plugin that turns plans into an auto-playing presentation narrated by the Japanese voice characters Zundamon and Shikoku Metan. It supports pausing the presentation.
Diagrams that argue, not boxes that label. An opinionated Excalidraw methodology plus themes and a renderer that turn 'draw me a diagram' into figures that teach.
★not rated 4 yesterdayA
tokens not measured
originalMIT
Generate lip sync mouth shape sprites from any face image using AI. Includes a complete pipeline skill for sprite generation, post-processing, and browser-based demo with real-time audio-driven animation.
★not rated 4 6mo agoA
tokens not measured
originalMIT
Give Claude a voice on macOS (say) or Linux (espeak-ng) — on-demand /speak (verbatim or LLM-summarized), an automatic toggle-speak Stop hook, and adjustable rate/voice/truncation.
★not rated 4 2mo agoA
tokens not measured
originalMIT
Fetch relevant, high-quality, free-to-use images from the web for any project context. Scans your directory for context or takes a description, searches Unsplash/Pexels/Pixabay (API or zero-config WebSearch fallback), presents curated picks, and downloads to your project.
★not rated 4▲
+1 7mo agoA
tokens not measured
originalMIT
Search the Metropolitan Museum of Art collection, browse it by department or update date, fetch full artwork records and open-access images via MCP. STDIO or Streamable HTTP.
★not rated 4
changed 3d agoA
tokens not measured
originalApache-2.0
Halftone paper-collage stop-motion ads: decode a reference into an editable spec, generate cut-out elements on the Gemini image API, and assemble build-from-empty motion with a deterministic local compositor, complete with the handmade stop-motion wobble. No paid video model.
★not rated 4▲
+1 3mo agoA
tokens not measured
originalMIT
Multi-shot AI video storyboard planner for clips longer than a single AI generation (>15s). Breaks a TikTok Reel, Instagram ad, YouTube Short, or product explainer into a coordinated shot list with a shared visual-consistency layer and copy-ready per-shot prompts. Vendored from…
★not rated 4 4mo agoA
tokens not measured
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: