ML Ops
Machine learning operations
formal-logic
by biruk741
Formal logic inference rules for constructing and validating proofs. Use when building deductive arguments or checking proof validity.
azure-functions
by automindtechnologie-jpg
"Expert patterns for Azure Functions development including isolated worker model, Durable Functions orchestration, cold start optimization, and production patterns. Covers .NET, Python, and Node.js programming models. Use when: azure function, azure functions, durable functions, azure serverless, function app."
cohere-python-sdk
by RSHVR
Cohere Python SDK reference for chat, streaming, tool use, structured outputs, and RAG. Use when building Python applications with Cohere's Command models, embeddings, or reranking APIs.
but-why
by h14h
Collaboratively write, update, or consult a project's WHY.md and design/ conceptual models — the documents that capture purpose, values, priorities, target users, and how users think about the product. Use when the user wants to create project documentation about why their project exists, discuss project vision or values, write a WHY.md, update conceptual models, revisit project priorities, or when you need to understand a project's purpose and values before doing work. Triggers include "but why", "write a WHY", "document the purpose", "update the why", "project vision", "collaborate on why", "update the design", "conceptual model", "what are the project values", "what's the priority", or "use but-why".
execute
by biruk741
Execute tasks from a mini-orchestrator by spawning parallel subagents in waves. Reads an orchestrator file, identifies available tasks, routes them to the right model by complexity, enforces exclusive file ownership within waves, and tracks progress in a compaction-resilient way. Pure orchestrator — never edits source files directly. Use when /start-work generates a parallel execution plan, when someone says "execute my tasks", "run the orchestrator", "batch my work", or when a developer has multiple independent tasks to parallelize.
expert-systems
by bmcgauley
Comprehensive guidance for understanding, designing, and implementing expert systems using rule-based inference, knowledge representation, and the complete development lifecycle. Use when users need help with expert system concepts, architecture design, rule-based reasoning (forward/backward chaining), knowledge acquisition, development planning, or implementation strategies.
friday-router
by RuneweaverStudios
Austin's intelligent model router with fixed scoring, his preferred models, and OpenClaw integration
cohere-embeddings
by RSHVR
Cohere embeddings reference for vector search, semantic similarity, and RAG. Covers Embed v4 (multimodal, Matryoshka dimensions), input types (CRITICAL for search quality), batch processing, and LangChain integration.
3d-web-experience
by yunaamelia
"Expert in building 3D experiences for the web - Three.js, React Three Fiber, Spline, WebGL, and interactive 3D scenes. Covers product configurators, 3D portfolios, immersive websites, and bringing ..."
teach
by carsten-j
Learning mode - guides the user to complete tasks themselves through Socratic teaching rather than doing it for them. Use when the user wants to learn how to do something instead of having it done for them.
Distributed Scaling
by sovr610
This skill should be used when the user asks to "scale training to multiple GPUs", "set up distributed training", "configure DDP", "use FSDP", "shard the model", "add gradient accumulation", "run with torchrun", "multi-node training", "rank-aware data loading", "distributed checkpointing", "scale to 7B parameters", "reduce GPU memory usage", "configure mixed precision distributed", or needs guidance on DistributedDataParallel, FullyShardedDataParallel, multi-GPU orchestration, or scaling the brain_ai system beyond single-GPU.
agents
by ChronoAIProject
Meta-skill for AI agents working with Chrono CLI. Provides navigation to available skills and MCP tools. Use when starting work on Chrono-related tasks to understand available capabilities, or when unsure which skill to use for a specific task.
gemini
by junoh-moon
Interact with Google's Gemini model via CLI. Use when needing a second opinion from another LLM, cross-validation, or leveraging Gemini's Google Search grounding. Supports multi-turn conversations with session management.
glb-compressor-cli
by kjanat
Compress GLB/glTF 3D models using the glb-compressor CLI. Use when running compression from the command line, writing shell scripts that compress models, or integrating into CI/CD pipelines.
product-manager
by pierreribeiro
Product Manager persona for business vision and strategy. ACTIVATE when messages contain PRD, roadmap, business impact, ROI, metrics, stakeholder, product vision, business strategy, business case, go-to-market, or product planning discussions.
tech-research-pipeline
by tomwangowa
Orchestrates a full technical research workflow by chaining specialized skills in sequence: brainstorming → tech-feasibility → assumption-extractor → micro-poc-validator → critical-research → narrative-auditor → research-cross-validator → research-synthesis. Use when evaluating a technology choice, planning a migration, or making any significant technical decision that warrants rigorous multi-angle analysis. Triggered by "full research pipeline", "rigorous tech evaluation", "research pipeline", or "evaluate [tech] thoroughly".
ai-vision
by httprunner
Multimodal UI understanding and single-step planning via OpenAI-compatible Responses APIs. Use when you need AIQuery/AIAssert and plan-next to extract UI element coordinates, validate UI assertions, summarize screenshots, or decide the next UI action from an image. External agents handle execution via adb/hdc and multi-step loops. Defaults to Doubao models but can be pointed at other multimodal providers via base URL, API key, and model name.
go-create-gorm-model
by cristiano-pacheco
Generate Go GORM models following Pingo modular architecture conventions. Use when creating or updating persistence models in internal/modules/<module>/model/, including table mapping, nullable SQL types, timestamps, and relation fields for identity and monitor modules.
text-to-voice
by kenneropia
Convert text to speech using Kyutai's Pocket TTS. Use when the user asks to "generate speech", "text to speech", "TTS", "convert text to audio", "voice synthesis", "generate voice", "read aloud", or "create audio from text". Supports voice cloning from audio samples and multiple pre-made voices (alba, marius, javert, jean, fantine, cosette, eponine, azelma).
eve-pipelines-workflows
by Incept5
Define and run Eve pipelines and workflows via manifest and CLI. Use when wiring build, release, deploy flows or invoking workflow jobs.
domain-ml
by lywa1998
"Use when building ML/AI apps in Rust. Keywords: machine learning, ML, AI, tensor, model, inference, neural network, deep learning, training, prediction, ndarray, tch-rs, burn, candle, 机器学习, 人工智能, 模型推理"
web-research
by engsimsoft
Глубокий поиск информации в интернете. Загрузи этот skill для сложного исследования или когда нужно проверить много источников.
pytorch-distributed
by cuba6112
Distributed training strategies including DistributedDataParallel (DDP) and Fully Sharded Data Parallel (FSDP). Covers multi-node setup, checkpointing, and process management using torchrun. (ddp, fsdp, distributeddataparallel, torchrun, nccl, rank, process-group)
qwen-tts
by paki81
Local text-to-speech using Qwen3-TTS-12Hz-1.7B-CustomVoice. Use when generating audio from text, creating voice messages, or when TTS is requested. Supports 10 languages including Italian, 9 premium speaker voices, and instruction-based voice control (emotion, tone, style). Alternative to cloud-based TTS services like ElevenLabs. Runs entirely offline after initial model download.