litellm
Call 100+ LLM APIs with one interface using LiteLLM — unified API proxy for OpenAI, Anthropic, Google, Mistral, Cohere, and self-hosted models. Use when…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,663 results
lm-studio-subagents
Offload tasks to local LLMs via LM Studio. Use when a user asks to run local models with LM Studio, save API costs by using local LLMs, create subagents with…
mcp-server-builder
Build Model Context Protocol (MCP) servers that connect AI agents to external services and data sources. Use when a user asks to create an MCP server, build an…
onnx
Open Neural Network Exchange (ONNX) is a framework-neutral file format for machine-learning models, and ONNX Runtime is the engine that runs them on CPU, GPU…
vllm
You are an expert in vLLM, the high-throughput LLM serving engine. You help developers deploy open-source models (Llama, Mistral, Qwen, Phi, Gemma) with…
disciplined-research
Phase 1 of disciplined development. Deep problem understanding before design. Maps existing systems, identifies constraints, surfaces risks, and produces a…
local-knowledge
Leverage personal notes and documentation through Terraphim's role-based search. AI agents can search developer's local knowledge organized by domain (Rust,…
ask-glm
Consult Zhipu GLM-5.2 (via the `zai` CLI) as a COMPLEMENTARY second opinion or big-context analyst — NOT a replacement for Claude. Use PROACTIVELY to…
sfd-model-provider
Help the user configure AI providers for the video-director pipeline. Covers video generation (KIE, Wavespeed, Fal, Replicate, Higgsfield) and audio…
vercel-agent-deploy-to-vercel
Deploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this…
minions-pattern
Route software work across Claude Code and Codex while balancing subscription quota and keeping the top-level host as a thin accountable orchestrator. Use for…
sitemap-coverage
Use when applies to content sites, e-commerce stores, and any site where timely indexing of new pages matters. Use when investigating why new pages take a long…
github-agents
This skill should be used when delegating work to agents that run inside GitHub — Copilot cloud agent, custom agents, Copilot code review, and GitHub Agentic…
m365-copilot-packaging
This skill should be used when shipping an MCP app into Microsoft 365 Copilot as a declarative agent — prerequisites, the widget host CORS URL, OAuth 2.1 and…
mcp-apps-protocol
This skill should be used when implementing or debugging the MCP Apps extension — ui:// resource URIs, the text/html;profile=mcp-app mimeType, every _meta.ui…
mcp-ui-sdk
This skill should be used when working with mcp-ui — createUIResource and its rawHtml/externalUrl/remoteDom content types, the five UI action types (tool,…
ui-porting-migration
This skill should be used when migrating an agent UI between protocols or SDKs — OpenAI Apps SDK to portable MCP Apps, mcp-ui legacy actions to the ui/*…
raytheon
Expert skill for Raytheon (RTX) Defense & Aerospace Expert
simulation-platform-engineer
Expert-level Simulation Platform Engineer specializing in autonomous driving simulation, scenario generation, sensor model validation, and large-scale…
uav-flight-control-engineer
Expert-level UAV Flight Control Engineer specializing in flight control laws (PID, LQR, MPC, INDI), hardware integration (STM32, Pixhawk, FPGA-based FCS),…
agent-dbg
Debug applications using the agent-dbg CLI debugger. Supports Node.js (V8/CDP), Bun (WebKit/JSC), and native code via LLDB (DAP). Use when: (1) investigating…
mcp-python-conventions-taudelta
Use when writing the Python inside an MCP server and deciding how it should behave — where log output may go when stdout carries JSON-RPC framing and why a…
polite-mcp-conventions-taudelta
Use when working in one of the *-polite-mcp personal automation repos (olx-polite-mcp, emag-polite-mcp, altex-polite-mcp, freshful-polite-mcp, temu-polite-mcp)…
brainstorm-first
Compare practical options and recommend one before implementation. Use when the user asks to brainstorm, wants alternatives or UI concepts to choose from, or…