ML Ops
Machine learning operations
ML Training Debugger - Diagnose and Fix Training Issues
by DNYoussef
Context Cascade - Nested Plugin Architecture for Claude Code Official Claude Code Plugin Version 3.1.0 Last updated: 2026-01-09 (see docs/COMPONENT-COUNTS.json for source counts) Context-saving nested architecture: Playbooks -> Skills -> Agents -> Commands. Load only what you need, saving 90%+ context space.
ai-engineer
by boisenoise
Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations.
pict-test-designer
by omkamal
Design comprehensive test cases using PICT (Pairwise Independent Combinatorial Testing) for any piece of requirements or code. Analyzes inputs, generates PICT models with parameters, values, and constraints for valid scenarios using pairwise testing. Outputs the PICT model, markdown table of test cases, and expected results.
webgpu
by cazala
WebGPU/WGSL guidance for initialization, render/compute pipelines, shader authoring, debugging, and performance; use when building or troubleshooting WebGPU apps, GPU compute workloads, or WGSL shaders.
business-competitor-analysis
by manojbajaj95
Perform comprehensive competitor analysis for any business. Produces an executive-summary markdown report with target customer profile, market positioning, pricing/business model, product features, funding/company size, SWOT analysis, and competitive matrix. All findings are data-grounded. Use when the user asks to analyze competitors, understand competitive landscape, compare a business to alternatives, or perform market research.
business-competitor-analysis
by kenneth-liao
Perform comprehensive competitor analysis for any business. Produces an executive-summary markdown report with target customer profile, market positioning, pricing/business model, product features, funding/company size, SWOT analysis, and competitive matrix. All findings are data-grounded. Use when the user asks to analyze competitors, understand competitive landscape, compare a business to alternatives, or perform market research.
nanobanana
by kenneth-liao
AI image generation and editing using Google Gemini models (Nano Banana). Use when the user asks to generate an image, create an image, edit an image, or references "nano banana", "nanobanana", or "gemini image". Supports text-to-image, image editing, multi-image references, and 1K/2K/4K resolution.
near-ai-cloud
by near
NEAR AI Cloud private inference and verification. Use when integrating NEAR AI Cloud API for verifiable private AI inference, verifying model or gateway TEE attestation (NVIDIA NRAS, Intel TDX), verifying chat message signatures, implementing end-to-end encrypted chat, or using the OpenAI-compatible API with NEAR AI Cloud.
pinecone-mcp
by pinecone-io
Reference for the Pinecone MCP server tools. Documents all available tools - list-indexes, describe-index, describe-index-stats, create-index-for-model, upsert-records, search-records, cascading-search, and rerank-documents. Use when an agent needs to understand what Pinecone MCP tools are available, how to use them, or what parameters they accept.
ollama-launch
by richfrem
Start and verify the local Ollama LLM server. Use when Ollama is needed for RLM distillation, seal snapshots, embeddings, or any local LLM inference — and it's not already running. Checks if Ollama is running, starts it if not, and verifies the health endpoint.
model-serving
by ancoleman
LLM and ML model deployment for inference. Use when serving models in production, building AI APIs, or optimizing inference. Covers vLLM (LLM serving), TensorRT-LLM (GPU optimization), Ollama (local), BentoML (ML deployment), Triton (multi-model), LangChain (orchestration), LlamaIndex (RAG), and streaming patterns.
voice-ai
by ScientiaCapital
"Production voice AI agents with sub-500ms latency. Groq LLM, Deepgram STT, Cartesia TTS, Twilio integration. No OpenAI. Use when: voice agent, phone bot, STT, TTS, Deepgram, Cartesia, Twilio, voice AI, speech to text, IVR, call center, voice latency."
unsloth-training
by ScientiaCapital
"Fine-tune LLMs with Unsloth using GRPO or SFT. Supports FP8, vision models, mobile deployment, Docker, packing, GGUF export. Use when: train with GRPO, fine-tune, reward functions, SFT training, FP8 training, vision fine-tuning, phone deployment, docker training, packing, export to GGUF."
sales-revenue
by ScientiaCapital
"B2B sales - cold outreach, lead scoring, pipeline metrics, MEDDIC/BANT qualification, discovery calls, and demos. Use when writing cold emails, scoring leads, running pipeline reviews, or preparing for sales calls."
groq-inference
by ScientiaCapital
"Fast LLM inference with Groq API - chat, vision, audio STT/TTS, tool use. Use when: groq, fast inference, low latency, whisper, PlayAI TTS, Llama, vision API, tool calling, voice agents, real-time AI."
cost-metering
by ScientiaCapital
"Track and manage API costs across sessions. Budget alerts, model routing for cost optimization, spend reports. Use when: cost check, budget status, how much spent, optimize costs, cost tracking."
hubspot-revops-skill
by ScientiaCapital
Use when building revenue analytics on HubSpot â SQL warehouse queries,
business-model-canvas
by ScientiaCapital
"Business model design using Alexander Osterwalder's 9 building blocks. Use when: business model, canvas, value proposition, customer segments, revenue streams, startup planning, analyze business, business strategy."
openrouter-skill
by ScientiaCapital
"Orchestrate Chinese LLMs (DeepSeek, Qwen, Yi, Moonshot) through OpenRouter API with LangChain. Use when: openrouter, chinese llm, deepseek, qwen, moonshot, yi model, model routing, auto router, llm orchestration."
trading-signals
by ScientiaCapital
"Technical analysis patterns - Elliott Wave, Wyckoff, Fibonacci, Markov Regime, and Turtle Trading with confluence detection. Use when analyzing charts, identifying trading signals, or calculating technical levels."
runpod-deployment
by ScientiaCapital
"Deploy GPU workloads to RunPod serverless and pods - vLLM endpoints, A100/H100 setup, scale-to-zero, cost optimization. Use when: deploy to RunPod, GPU serverless, vLLM endpoint, scale to zero, A100 deployment, H100 setup, serverless handler, GPU cost optimization."
agent-capability-matrix
by ScientiaCapital
"Map task types to the best agent, skill, model, and fallback. Route any task to the right tool. Use when: which agent, route task, agent for this, best agent, capability matrix."
performance-scaling
by bejranonda
Cross-model performance optimization and scaling configurations for autonomous agents
writing-intelligence
by antonio0720
Sovereign Writing Intelligence Compiler v2.0 — 7-pass pipeline, signature-grade prose, zero AI residue. Fiction intelligence engine: chapter construction, 12 character roles, dialogue warfare (22 techniques, 9 tension elements), power dynamics, 8-phase tension compression, thriller architecture, transmedia deepening. 7 scoring systems. 16 genres. 8 voices. Trigger on: write, rewrite, edit, draft, revise, ghostwrite, prose, essay, chapter, sermon, speech, pitch, memo, narrative, dialogue, scene, thriller, suspense, tension, pacing, character voice, foreshadowing, subtext, score draft, grade writing, audit prose, anti-slop, AI detection, writing quality, improve writing, chapter construction, scene architecture, character roles, power dynamics, confined space, staging, cold open, fatal detail, silence, callback, worldbuilding, transmedia, lore bible, audio drama, scene audit, role audit, power map, plant audit, novel, short story, screenplay, creative writing, thriller writing, mystery, espionage.