Catalog
ai-ml skills
129 skills. Every one is readable here; downloads and live use need a subscription.
m365-agents-py
Microsoft 365 Agents SDK for Python. Build multichannel agents for Teams/M365/Copilot Studio with aiohttp hosting, AgentApplication routing, streaming responses, and MSAL-based auth.
manage-skills
Discover, list, create, edit, toggle, copy, move, and delete AI agent skills across 11 tools (Cursor, Claude, Agents, Windsurf, Copilot, Codex, Cline, Aider, Continue, Roo Code, Augment)
mesh-memory
Self-hosted semantic memory for AI agents via MCP. Save worklogs, decisions, and notes, then recall them across sessions by meaning, not keyword. Postgres + pgvector with auto-tagging.
ml-engineer
Build production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks. Implements model serving, feature engineering, A/B testing, and monitoring.
mlops-engineer
Build comprehensive ML pipelines, experiment tracking, and model registries with MLflow, Kubeflow, and modern MLOps tools.
molykit
CRITICAL: Use for MolyKit AI chat toolkit. Triggers on: BotClient, OpenAI, SSE streaming, AI chat, molykit, PlatformSend, spawn(), ThreadToken, cross-platform async, Chat widget, Messages, PromptInput, Avatar, LLM
monte-carlo-monitoring-advisor
Analyze data coverage, create monitors for warehouse tables and AI agents. Covers coverage gaps, use-case analysis, data monitor creation, and agent observability.
moyu
Anti-over-engineering guardrail that activates when an AI coding agent expands scope, adds abstractions, or changes files the user did not request.
multi-agent-architect
Design and optimize production-grade multi-agent systems with LangGraph, LangChain, and DeepAgents for complex AI workflows.
multi-agent-brainstorming
Simulate a structured peer-review process using multiple specialized agents to validate designs, surface hidden assumptions, and identify failure modes before implementation.
odw
Dynamic multi-agent workflows — plan first, then orchestrate parallel agents with adversarial verification via the local odw daemon. Use when the user asks for a "workflow", says "ultracode", or hands you a task spanning many files/items that benefits from parallel agents.
project-development
This skill covers the principles for identifying tasks suited to LLM processing, designing effective project architectures, and iterating rapidly using agent-assisted development.
prompt-caching
Caching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation)
prompt-engineering
Expert guide on prompt engineering patterns, best practices, and optimization techniques. Use when user wants to improve prompts, learn prompting strategies, or debug agent behavior.
prompt-engineering-patterns
Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability.
routerbase-model-gateway
Integrate RouterBase as an OpenAI-compatible model gateway for routing GPT, Claude, Gemini, media, audio, and embedding requests.
runaway-guard
Cost-safety discipline for paid AI / inference APIs: treat $-cost as a third complexity dimension alongside time and space. Forces a written per-run $-cap, per-day $-cap, max-iterations bound, concurrency limit, and a matching provider-dashboard hard cap BEFORE any call site is written.
sam-altman
Agente que simula Sam Altman — CEO da OpenAI, ex-presidente da Y Combinator, arquiteto da era AGI.
sandbase-mcp
Discover, inspect, and invoke 2,000+ AI models and APIs through SandBase's local MCP bridge with explicit schema and cost checks.
scikit-learn
Machine learning in Python with scikit-learn. Use for classification, regression, clustering, model evaluation, and ML pipelines.
tool-design
Build tools that agents can use effectively, including architectural reduction patterns. Use when creating new tools for agent systems, debugging tool-related failures or misuse, or optimizing existing tool sets for better agent performance.
train-sentence-transformers
Train or fine-tune SentenceTransformer, CrossEncoder, and SparseEncoder models for retrieval, similarity, clustering, classification, reranking, and related embedding tasks.
trl-training
Train and fine-tune transformer language models using TRL (Transformers Reinforcement Learning). Supports SFT, DPO, GRPO, KTO, RLOO and Reward Model training via CLI commands.
ui-skills
Opinionated, evolving constraints to guide agents when building interfaces
unified-ai-gateway
Operate and evaluate Unified AI System through nine governed MCP tools, including provider-free prompt enhancement, while preserving fake-provider, authorization, and evidence boundaries.
unslop-commit
Rewrites commit messages so they sound like a careful human engineer wrote them. Strips AI/marketing slop ("comprehensive solution", "robust implementation", "leverage", "enhance", "seamlessly", "This commit..."). Keeps Conventional Commits format.
unsloth-finetuning
Fine-tune and post-train LLMs with Unsloth Core on a single consumer GPU: VRAM sizing, LoRA/QLoRA, GRPO/DPO, chat-template correctness, and GGUF export.
voice-agents
Voice agents represent the frontier of AI interaction - humans speaking naturally with AI systems.
voice-ai-engine-development
Build real-time conversational AI voice engines using async worker pipelines, streaming transcription, LLM agents, and TTS synthesis with interrupt handling and multi-provider support
yann-lecun
Agente que simula Yann LeCun — inventor das Convolutional Neural Networks, Chief AI Scientist da Meta, Prêmio Turing 2018.
yann-lecun-debate
Sub-skill de debates e posições de Yann LeCun. Cobre críticas técnicas detalhadas aos LLMs, rivalidades intelectuais (LeCun vs Hinton, Sutskever, Russell, Yudkowsky, Bostrom), lista completa de rejeições a afirmações mainstream, posição sobre risco existencial de IA, e técnicas de debate ao vivo.
yann-lecun-tecnico
Sub-skill técnica de Yann LeCun. Cobre CNNs, LeNet, backpropagation, JEPA (I-JEPA, V-JEPA, MC-JEPA), AMI (Advanced Machinery of Intelligence), Self-Supervised Learning (SimCLR, MAE, BYOL), Energy-Based Models (EBMs) e código PyTorch completo.