AI & ML

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.

Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.

Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.

Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as prompts, or automatically generate all object masks in an image.

Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.

Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.

Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.

Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).

Authors and updates customization overrides for installed BMad skills. Use when the user says 'customize bmad', 'override a skill', 'change agent behavior', or 'customize a workflow'.

Integrate services or agent harnesses with the 33GOD Bloodbank event bus. Covers schemas in Bloodbank schemas/ and docs/event-naming.md, producing events (NATS preferred; Dapr, HTTP /publish, hookd_bridge alternatives), consuming events (NATS, Dapr, FastStream, event-toaster), and agent hook wiring through the canonical services/agent-hooks publisher. Use for event publish/consume, authoring schemas, integrating harnesses (Claude Code, Copilot CLI, OpenCode, Cursor, Aider, Codex CLI, Hermes), or debugging missing envelopes. Triggers: bloodbank, event bus, publish, subscribe, NATS subject, holyfields legacy, CloudEvents, event-toaster, ntfy.delo.sh/bloodbank, bloodbank.v1.agent.session.started, bloodbank.v1.agent.tool.completed, bloodbank.cmd.v1.agent.invocation.start. Skip for generic brokers, n8n, hindsight memory, or non-event-bus 33GOD.

Technical documentation specialist and knowledge curator. Use when the user asks to talk to Paige or requests the tech writer.

Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics

Laravel testing strategies with PHPUnit, Pest, model factories, HTTP tests, Sanctum authentication testing, mocking, and coverage.

Unified media generation via fal.ai MCP — image, video, and audio. Covers text-to-image (Nano Banana), text/image-to-video (Seedance, Kling, Veo 3), text-to-speech (CSM-1B), and video-to-audio (ThinkSound). Use when the user wants to generate images, videos, or audio with AI.

Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.

Interactive agent picker for composing and dispatching parallel teams

Independent model QA expert who audits ML and statistical models end-to-end - from documentation review and data reconstruction to replication, calibration testing, interpretability analysis, performance monitoring, and audit-grade reporting.

Autonomous payment processing specialist that executes vendor payments, contractor invoices, and recurring bills across any payment rail — crypto, fiat, stablecoins. Integrates with AI agent workflows via tool calls.

Comprehensive real estate agent assistant for buyer representation, seller representation, listing management, offer negotiation, transaction coordination, and closing support — delivering a world-class client experience from first showing to final closing across residential and investment real estate

Create and maintain Actor entities — humans and AI agents that participate in the project. Use when adding a new collaborator (human or agent) to the project, updating their preferences/expertise, or querying who does what.

Inspect, plan, and invoke safe cleanup for runtime-manager-owned state without binding the workflow to a specific host orchestrator or agent provider.

Orchestrate multi-agent workflows with task decomposition, role assignment, handoff protocols, and per-session context budgeting.

Discover supply-chain manifests, run structured supply-chain audits, and export SBOMs through a dedicated MCP surface.

AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.

LLM Operations -- RAG, embeddings, vector databases, fine-tuning, prompt engineering avancado, custos de LLM, evals de qualidade e arquiteturas de IA para producao.

This skill should be used when the user asks to "create AGENTS.md", "update AGENTS.md", "maintain agent docs", "set up CLAUDE.md", or needs to keep agent instructions concise. Enforces research-backed best practices for minimal, high-signal agent documentation.

AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.

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

Ingest, index, search, and edit video and audio content from files, URLs, live streams, or desktop sessions. Build visual and spoken indexes with timestamps, generate clips, subtitles, and overlays, and set up real-time monitoring alerts.

AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.

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

Financial analyst agent skill and plugin for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw. Ratio analysis, DCF valuation, budget variance, rolling forecasts. 4 Python tools (stdlib-only).

Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics

Neural search via Exa MCP for web, code, and company research. Use when the user needs web search, code examples, company intel, people lookup, or AI-powered deep research with Exa's neural search engine.

Interactive agent picker for composing and dispatching parallel teams