21,557 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.
Use when the user shares an image that Claude can't natively see, or when the user asks to analyze/describe/understand an image. Route every image through this skill — send the image path to eyes.py, which calls a vision model (default qwen3.7-plus) via 百炼 DashScope and returns a Chinese text description. Then answer…
A guide for designing single-image covers for Xiaohongshu, a Chinese social media platform. It can analyse reference covers and turn content into visual layouts and image-generation prompts.
Local speech-to-text using faster-whisper. 4-6x faster than OpenAI Whisper with identical accuracy; GPU acceleration enables 20x realtime transcription. SRT/VTT/TTML/CSV subtitles, speaker diarization, URL/YouTube input, batch processing with ETA, transcript search, chapter detection, per-file language map.
Create professional AWS-themed PowerPoint presentations with two theme options: dark (reInvent 2023/2025 with gradient backgrounds) and light (L100/field enablement with white backgrounds and soft gradient accents). Uses AWS brand colors, rich visual elements (SVG diagrams, architecture diagrams, icons), and…
Expert operation of the Blender MCP connector (26 tools bridging to a Blender addon on localhost:9876). Use this skill WHENEVER the user mentions Blender, bpy, 3D modeling, meshes, materials, GLB/glTF export, .blend files, rendering, viewport, rigging, physics simulation, game assets, or asks to create/edit/inspect…
Search and download podcast episodes from Apple Podcasts. Use when user wants to find podcasts, download podcast episodes, get podcast information, or mentions Apple Podcasts, iTunes, podcast search, or audio downloads.
Use when the user wants GPT Image 2 / GPT-Image-2.0 prompt design for any image deliverable — drama stills, music-video frames and album art, commercial/product/campaign ads, editorial fashion/beauty shoots, posters, thumbnails, book covers, character sheets and multi-shot storyboards, reference-image or…
Use when creating or auditing 2D runtime art such as sprites, tilesets, backgrounds, animation, VFX, maps, or UI assets for Phaser or Godot. Do not use for UI behavior, audio, build delivery, 3D, or marketing art.
Jianmu Agent Studio PPT production fallback skill. Use when building, repairing, reviewing, or improving PPT/courseware generation inside Jianmu Agent Studio, especially when PPTDraftWorker, pptxgenjs, Marp, PPTAgent, DeepPresenter, templates, slide quality gates, or presentation artifacts are involved. Jianmu…
A guide for using Dreamina, an AI service for generating and transforming images and videos, from the command line. The command-line tool is called dreamina and requires an eligible paid account.
Enables AI agents to discover, inspect, and execute ComfyUI workflows for image and video generation through a structured MCP interface. Supports the full task lifecycle—from context loading and workflow discovery, to parameter mounting and task submission, and finally result retrieval and generated asset management.
A prompt-writing workflow for turning a short spoken idea or abstract concept into an editorial paper-collage B-roll video concept. It produces visual directions, still-image prompts, and video prompts in stages.
Sistema para crear y reutilizar un personaje propio formado por bloques blancos blandos en cómics verticales de dos viñetas. Convierte temas, textos o historias en escenas con un contraste absurdo entre ambas partes.
Fotor AI image generator and AI video generator for photo editing, background remover, background replacement, product photos, ad creatives, social media graphics, poster and banner design, image upscaling, photo restoration, portrait enhancement, text-to-video, and image-to-video. Built for e-commerce, marketing…
Convert any content into stunning Apple Keynote-style HTML presentations. Cinematic animations, glassmorphism, ambient effects, and premium design — all in a single self-contained .html file.
★not rated 10 8mo agoA
tokens not measured
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: