ML Ops
Machine learning operations
async-io-model
by tursodatabase
Explanations of common asynchronous patterns used in tursodb. Involves IOResult, state machines, re-entrancy pitfalls, CompletionGroup. Always use these patterns in core when doing anything IO
dialogue-audio
by inference-sh
"Multi-speaker dialogue audio creation with Dia TTS. Covers speaker tags, emotion control, pacing, conversation flow, and post-production. Use for: podcasts, audiobooks, explainers, character dialogue, conversational content. Triggers: dialogue audio, multi speaker, conversation audio, dia tts, two speakers, podcast audio, character voices, voice acting, dialogue generation, conversation tts, multi voice, speaker tags, dialogue recording"
cellpose-cell-segmentation
by jaechang-hits
"Deep learning cell and nucleus segmentation from fluorescence and brightfield microscopy images. Uses pre-trained models (cyto3, nuclei, tissuenet) and a generalist flow-based algorithm that segments cells without requiring retraining on new image types. Outputs label masks for downstream morphology measurement and tracking. Use scikit-image watershed for rule-based segmentation; use Cellpose when deep learning generalization across staining conditions is needed."
ai-music-generation
by inference-sh
"Generate AI music and songs with ElevenLabs, Diffrythm, Tencent Song Generation via inference.sh CLI. Models: ElevenLabs Music (up to 10 min, commercial license), Diffrythm (fast song generation), Tencent Song Generation (full songs with vocals). Capabilities: text-to-music, song generation, instrumental, lyrics to song, soundtrack creation. Use for: background music, social media content, game soundtracks, podcasts, royalty-free music. Triggers: music generation, ai music, generate song, ai composer, text to music, song generator, create music with ai, suno alternative, udio alternative, ai song, ai soundtrack, generate soundtrack, ai jingle, music ai, beat generator, elevenlabs music, eleven labs music"
Build Your Pipecat Skill
by majiayu000
"Create your Pipecat skill from official documentation, then learn to improve it throughout the chapter"
model-selection
by majiayu000
Automatically applies when choosing LLM models and providers. Ensures proper model comparison, provider selection, cost optimization, fallback patterns, and multi-model strategies.
model-management
by pollinations
"Add, update, or remove text/image/video models. Handles any provider."
flow-nexus-neural
by majiayu000
Train and deploy neural networks in distributed E2B sandboxes with Flow Nexus
evaluating-llms-harness
by Orchestra-Research
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.
foundation-models-on-device
by affaan-m
Apple FoundationModels framework for on-device LLM — text generation, guided generation with @Generable, tool calling, and snapshot streaming in iOS 26+.
ultrawork
by Yeachan-Heo
Parallel execution engine for high-throughput task completion
regex-vs-llm-structured-text
by affaan-m
Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.
nanogpt
by Orchestra-Research
Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).
sparse-autoencoder-training
by Orchestra-Research
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.
sentencepiece
by Orchestra-Research
Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need multilingual support, CJK languages, or reproducible tokenization.
hugging-face-trackio
by huggingface
Track and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API) or retrieving/analyzing logged metrics (CLI). Supports real-time dashboard visualization, HF Space syncing, and JSON output for automation.
security-awareness-training
by Ed1s0nZ
安全意识培训的专业技能和方法论
gguf-quantization
by Orchestra-Research
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.
django-patterns
by affaan-m
Django architecture patterns, REST API design with DRF, ORM best practices, caching, signals, middleware, and production-grade Django apps.
ai-engineer
by rmyndharis
Build production-ready LLM applications, advanced RAG systems, and
peft-fine-tuning
by davila7
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.
fluentui-blazor
by github
Guide for using the Microsoft Fluent UI Blazor component library (Microsoft.FluentUI.AspNetCore.Components NuGet package) in Blazor applications. Use this when the user is building a Blazor app with Fluent UI components, setting up the library, using FluentUI components like FluentButton, FluentDataGrid, FluentDialog, FluentToast, FluentNavMenu, FluentTextField, FluentSelect, FluentAutocomplete, FluentDesignTheme, or any component prefixed with "Fluent". Also use when troubleshooting missing providers, JS interop issues, or theming.
context-degradation
by guanyang
This skill should be used when the user asks to "diagnose context problems", "fix lost-in-middle issues", "debug agent failures", "understand context poisoning", or mentions context degradation, attention patterns, context clash, context confusion, or agent performance degradation. Provides patterns for recognizing and mitigating context failures.
agent-builder
by shareAI-lab
Design and build AI agents for any domain. Use when users: (1) ask to "create an agent", "build an assistant", or "design an AI system" (2) want to understand agent architecture, agentic patterns, or autonomous AI (3) need help with capabilities, subagents, planning, or skill mechanisms (4) ask about Claude Code, Cursor, or similar agent internals (5) want to build agents for business, research, creative, or operational tasks Keywords: agent, assistant, autonomous, workflow, tool use, multi-step, orchestration