Scan to join WeChat groupBrowse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
Transcribes audio to text with timestamps and optional speaker identification. Use when you need to convert speech to text, create subtitles, transcribe meetings, or process voice recordings.
Use when adding multi-format RAG ingest, chunk, embed, and retrieval pipelines; pair with architect-python-uv-batch or architect-python-uv-fastapi-sqlalchemy.
Skill for creating and editing 3D models using software like Blender for AR/VR applications.
Swarm Collaboration enables multiple AI agents with different personas
Edit AI-generated or draft content to match a voice profile. Use when transforming generic AI output into authentic voice-matched content, or when editing drafts to sound more like you.
Generate synthetic training data using Nebius Token Factory batch inference (50% cheaper than real-time, async, no rate-limit impact). Use this skill whenever the user wants to run batch inference on …
OpenInference semantic conventions and instrumentation for Phoenix AI observability. Use when implementing LLM tracing, creating custom spans, or deploying to production.
Comprehensive guide for Deep Learning with Keras 3 (Multi-Backend: JAX, TensorFlow, PyTorch). Use when building neural networks, CNNs for computer vision, RNNs/Transformers for NLP, time series foreca…
Generate QR codes from text, URLs, or data, supporting custom colors, logos, and multiple output formats.
Manages embedding pipelines for AI/ML models, including creation, optimization, and deployment.
Voice calling: outbound/inbound calls via Twilio PSTN, WebRTC, call recording, transcription
Model training is the process of teaching machine learning models to
Create programmatic vector animations with TypeScript using the Motion Canvas library. Use when building animated explainer videos, tutorials, data visualizations, or presentations with synchronized a…
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies. Dispatch subagents to work concurrently.
Apply Anthropic's production multi-agent research patterns for complex research tasks. Use when research involves multiple independent dimensions, requires synthesis across many sources, or needs para…
Smart answering framework that adapts to question types and delivers evidence-based, natural responses.
Delegate tasks to the cost-effective opencode/glm-5 model. Use when you need inexpensive task execution, simple research, or delegating work that doesn't require the most powerful models.
Fine-tuning pre-trained machine learning models for specific tasks using transfer learning techniques.
YouTube: video management, transcript extraction, channel analytics, comments, playlists, upload
AI-powered chatbots use language models to provide conversational interfaces
Fine-tune a model on Nebius Token Factory. Use this skill whenever the user wants to train, fine-tune, or adapt a model on Nebius — including uploading training data, creating a fine-tuning job, monit…
INVOKE THIS SKILL when optimizing, improving, or debugging LLM prompts using production trace data, evaluations, and annotations. Covers extracting prompts from spans, gathering performance signal, an…
When the session ends or the user requests a 'reflection/summary of the session/update profile/session reflect', based on the evidence of user interaction in the current session, extract dual-track ev…
Analyzes 3D mesh files (STL) to calculate geometric properties (volume, components) and extract attribute data. Use this skill to process noisy 3D scan data and filter debris.