@calesthio
Building open source AI Assisted and Agentic Tools. Creator of OpenMontage and Crucix — https://www.openmontage.video/
244 skills2 repositories 70.8K
Turn text into standalone speech audio with HeyGen's Starfish model for narration, voiceovers, or podcasts. Choose voices by language or gender, adjust speed and pitch, and add pauses when the selected voice supports them.
Turn a written brief into an explainer video by generating narration, images, music, and optional talking presenters. Assemble scenes with Remotion, adjust their timing to the generated audio, review still frames, and render an MP4.
Add mouse, touch, and keyboard interaction to Three.js scenes. Implement object picking, camera navigation, dragging, and transform handles, with examples for selection feedback, coordinate conversion, and limiting the cost of interaction checks.
Create mathematical and geometric animations in Python with Manim Community Edition. Use guidance, examples, and scene templates to structure animations, display equations, plot graphs, control cameras, and render two-dimensional or three-dimensional scenes.
Integrate FLUX image generation and editing into applications through the BFL API. The guide covers authentication, checking asynchronous results, completion notifications through webhooks, request limits, error handling, regional endpoints, and downloading generated images before their URLs expire.
Build reusable interface components with Tailwind CSS v4, using shared design values for colors, corners, and themes. Covers buttons, forms, responsive layouts, accessibility, and dark mode to help standardize interfaces across a project.
Build Remotion videos using the toolkit’s shared backgrounds, comparison layouts, presenter overlays, and custom scene transitions. Apply its 30fps timing conventions and rendering practices to assemble scenes and coordinate them with voiceover.
Style Three.js objects with realistic, cartoon, or custom materials. Choose material types, adjust textures and reflections, create glass or metal effects, and use shader code for custom appearance while considering rendering performance.
Refactor React components with too many true-or-false options into reusable parts. Provides guidance on component composition, shared state, and flexible interfaces, with examples of good and problematic implementations and specific guidance for React 19.
Create short video clips from text or still images with LTX-2.3 22B. Generate supporting footage, animated backgrounds, or moving portraits while specifying camera motion, lighting, dimensions, and duration, with clips around five seconds by default.
Generate HeyGen videos from text prompts or specify avatars, voices, scripts, and scenes for controlled production. This deprecated skill covers explainers and presentations; its replacement skills separate prompt-based generation from detailed avatar video creation.
Process video and audio with FFmpeg for editing and publishing. Convert formats, resize and compress files, extract audio, trim clips, and change playback speed. Includes recipes for preparing Remotion assets and exporting videos for social platforms and websites.
Create HeyGen avatar videos with a chosen presenter, voice, exact script, and backgrounds for each scene. Use photos as presenters, generate transparent WebM files for compositing, or produce batches of videos with consistent specifications.
Create instrumental tracks, songs with lyrics, background music, and jingles using the ElevenLabs Music API. Describe the sound and duration, or edit a structured composition plan to control musical styles and sections.
Turn a math or science video idea into a detailed scene plan. Research the topic, clarify the audience, and outline visuals, narration, transitions, and implementation notes for Manim, an animation tool.
Generate background music and songs with lyrics using ACE-Step 1.5, with controls for duration, tempo, and musical key. You can also restyle reference audio and separate vocals or individual instruments from mixed tracks.
Generate multilingual narration from scripts in OpenMontage using Azure AI Speech. Choose a voice, adjust speaking rate, pitch, and supported delivery styles, then save individual narration segments as MP3 or WAV files.
Translate and dub existing videos with HeyGen to create versions in multiple languages. Preserve the speaker’s voice characteristics, match lip movements to translated speech, or choose audio-only translation without adjusting the video’s lip movements.
Write, review, and refactor React and Next.js code using performance guidelines from Vercel. Prioritized rules help identify sequential data requests, oversized JavaScript bundles, unnecessary re-renders, and other opportunities to improve loading and responsiveness.
Plan and scope production work with Odyssey's real-time interactive video world models (odyssey.ml — Odyssey-1/Odyssey-2/Starchild-1/Agora-1). Use when a request involves generating video that a user steers live with keyboard, text, speech, or controller input (streamed frames that respond in the moment), or when someone must decide between Odyssey-style interactive generation and offline clip generators (Sora/Veo/Kling) or downloadable 3D / game engines. Covers what is verified versus announced, current access routes, latency and coherence limits, feasible-now versus speculative use cases, pricing/access terms, and content/rights considerations. This is a fast-moving research-stage product; the skill teaches honest scoping, not a promise of production reliability.
The English summary is being prepared. Showing the original description.
Build production OpenAI Realtime voice agents and low-latency spoken interactions with live audio sessions, WebRTC or WebSocket transport, voice activity detection, tool/function calling, prompt design, logging, consent, privacy, safety, latency, and cost controls. Use for speech-to-speech agents and live voice UX; do not use for separate request-based transcription, text-to-speech, or offline audio generation work.
The English summary is being prepared. Showing the original description.
Generate persistent, explorable 3D worlds/environments with Marble by World Labs — from text, a single image, multiple images, video, or a 360 panorama, plus coarse-structure blocking with Chisel. Use this skill when a task needs a navigable 3D scene, VR/immersive backdrop, virtual-production environment, previz set, game-blockout, or web/engine-ready Gaussian splat or mesh, and you must choose an input mode, a Marble model, an export format, and a plan/API route, then review world quality. Covers the Marble web app and the World API, editing/expansion, output formats and what each supports downstream, import into Unity/Unreal/Blender/Houdini/web, pricing/credits, capability limits, and rights/licensing. Not for flat text-to-image, text-to-video clips, or real-time on-the-fly world models (Marble outputs are downloadable, static 3D environments).
The English summary is being prepared. Showing the original description.
Select, run, and govern NVIDIA Cosmos world-video generation across Cosmos 3 Generator, Predict2.5, Transfer2.5, downloadable checkpoints, self-hosted NIMs, and hosted preview surfaces. Use for text/image/video-to-world, controlled world transfer, multiview or action-conditioned physical-AI video, local checkpoint pinning, hardware planning, inference approval, and output validation; do not use for Cosmos Reason/Embed-only tasks.
The English summary is being prepared. Showing the original description.
Use MiniMax's first-party Hailuo video API safely and reproducibly across global and mainland-China platforms. Covers current text-to-video, image-to-video, first/last-frame, and subject-reference models; prompt and camera craft; region/account routing; exact cost approval; asynchronous jobs and callbacks; artifact provenance; and rights, likeness, disclosure, and data-governance review. Use when designing, implementing, debugging, or evaluating direct MiniMax/Hailuo video-generation API workflows. Do not use for the consumer Hailuo site, Video Agent templates, gateways, or unrelated MiniMax modalities.
The English summary is being prepared. Showing the original description.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)