Skills for your AI
Builds production-ready MCP servers in Java using the official SDK, reactive streams, and Spring Boot, covering server setup, tools, resources, prompts, testing, and dependencies. Use when the user asks to design, implement, configure, or test a Java MCP serve
Builds Model Context Protocol servers in Kotlin with the official io.modelcontextprotocol:kotlin-sdk library, covering tools, resources, prompts, transports, testing, project structure, coroutines and multiplatform targets. Use when the user asks to create an
Reads, creates, and updates Linear issues, projects, teams, comments, cycles, and documentation through the Linear MCP server. Use when the user asks to manage Linear tickets, plan sprints or releases, triage bugs, audit docs, or balance team workload.
Designs production LLM architectures covering serving, fine-tuning, RAG, and multi-model orchestration with measurable latency, throughput, and cost targets. Use when the user needs an LLM serving stack, quantization choice, fine-tuning pipeline, RAG retrieval
Use proactively whenever LLM API costs come up -- or should. Triggers include: 'my AI costs are too high', 'optimize token usage', 'which model should I use', 'LLM spend is out of control', 'implement prompt caching', 'we're about to launch an AI feature', 'bu
Designs and runs adversarial evaluations of deployed LLMs — jailbreak probes, prompt-injection harnesses, and output-safety measurement — producing scored results and signed evidence bundles. Use when planning a red-team engagement, building or running a probe
Produces validated LoRA/QLoRA supervised fine-tuning adapter configurations with target modules, rank, alpha, learning rate, batch size, and Unsloth defaults. Use when configuring a LoRA/QLoRA adapter, choosing rank or learning rate, checking effective batch s
Deploys and optimizes ML models for production inference, covering serving infrastructure, quantization, monitoring, edge and batch serving, and auto-scaling. Use when the user needs to deploy a model, cut inference latency or cost, design serving infrastructu
Guides data analysts through machine learning projects from preprocessing and feature engineering to model selection, tuning, evaluation, interpretability, deployment, and applied use cases. Use when the user asks for help cleaning data for ML, choosing or tun
Creates and configures MCP server integrations as JSON files for the cli-tool components system, including authentication, performance tuning, and security review. Use when the user needs a new MCP configuration, wants an existing MCP integration validated or
Access 1200+ AI Agent tools via Model Context Protocol (MCP)
Generates and reviews MCP server configuration for plugins, covering stdio, SSE, HTTP, and WebSocket setups, tool naming, permissions, security, and lifecycle. Use when adding or integrating an MCP server, writing .mcp.json or plugin.json config, or checking a
Guides developers through scaffolding, configuring, authenticating, deploying, and troubleshooting MCP-based declarative agents for Microsoft 365 Copilot. Use when building a new declarative agent, connecting an MCP server, designing Adaptive Cards or response
Discovers, evaluates, configures, and helps publish MCP servers from official and community registries. Use when the user needs to find MCP servers by capability or transport, assess a server's capabilities or trustworthiness, generate a client configuration,
Designs, implements, and hardens MCP servers with JSON-RPC 2.0 transports, JSON Schema tool definitions, completions, batching, session security, and documentation. Use when building or modifying an MCP server, defining its tools/resources/prompts, adding comp
Design and ship production-ready MCP (Model Context Protocol) servers from OpenAPI contracts instead of hand-written tool wrappers. Python and TypeScript support, schema validation, safe evolution. Use when exposing an existing API as an MCP server, building t
Validates MCP servers for protocol and schema compliance, safety annotations, completions, security, performance, and regression suites. Use when testing an MCP server endpoint or repository, checking JSON-RPC and Streamable HTTP behavior, probing session or i
Merge the winning agent's branch into base, archive losers, and clean up worktrees. Use when the user runs /hub:merge or asks to land the winning AgentHub result and tidy the session.
Creates, refactors, explains, and updates .NET code built on Microsoft Agent Framework, including tool and MCP integration. Use when the user asks to build a new agent or workflow, migrate Semantic Kernel or AutoGen code, explain agent code, add tools or MCP s
Migrate from Cypress or Selenium to Playwright. Use when user mentions "cypress", "selenium", "migrate tests", "convert tests", "switch to playwright", "move from cypress", or "replace selenium".
Implements, fine-tunes, pretrains, quantizes, and deploys LLMs with LitGPT's pretrained architectures and LoRA/QLoRA workflows. Use when the user wants to load a LitGPT model for inference, fine-tune on their own dataset, pretrain from scratch, prepare tokeniz
Explains the RWKV architecture and guides installation, inference, Transformer comparisons, and fine-tuning. Use when the user asks how RWKV works, wants to install or set up RWKV, run or stream inference, compare RWKV with Transformers, or fine-tune an RWKV m
Converts molecular SMILES strings into numerical feature vectors using molfeat featurizers (fingerprints, 2D descriptors, pretrained embeddings, or combined). Use when the user provides SMILES and asks for ECFP/MACCS/MAP4/FCFP fingerprints, RDKit or Mordred de
Automate Monday.com workflows, board management, team collaboration, and cross-board integrations
