agno
Agno Framework — Skill Router
Agno is an open-source framework for building, deploying, and managing multi-agent systems. This skill is organized into focused reference files. Read only what the current task requires.
Reference Files
| Reference | File | Read When |
|---|---|---|
| Agents | references/agents.md |
Creating agents, tools, structured output, storage, memory, knowledge, state, streaming |
| Teams | references/teams.md |
Multi-agent coordination, team modes (coordinate, route, broadcast, tasks), delegation |
| Workflows | references/workflows.md |
Orchestrating agents/teams/functions as repeatable pipelines with sequential, parallel, conditional, loop, and router patterns |
| Workflow Patterns | references/workflow-patterns.md |
Full code examples for every workflow pattern (sequential, parallel, conditional, loop, router, mixed, background execution, conversational) |
| Input / Output | references/input-output.md |
Structured input (Pydantic validation), structured output (typed responses), multimodal (images, audio, video, files), streaming, output/parser models, expected output |
| Models | references/models.md |
Model providers (40+ supported), model-as-string syntax ("provider:model_id"), error handling & retries, response caching, multimodal compatibility matrix, OpenAI-compatible models (OpenAILike, OpenResponses) |
| Database | references/database.md |
All storage backends (Postgres sync/async, MongoDB, Redis, Supabase, SQLite, DynamoDB, MySQL), chat history, session management, connection strings |
| Memory | references/memory.md |
Automatic vs agentic memory, MemoryManager, MemoryTools, memory optimization, multi-user isolation, agents sharing memory, teams with memory, best practices |
| Knowledge | references/knowledge.md |
RAG pipelines, vector databases (PgVector, Chroma, LanceDB, Pinecone, Qdrant, 20+ options), embedders, readers (PDF, CSV, web, YouTube, etc.), chunking strategies, search types (vector/keyword/hybrid), filtering, reranking, custom retrievers, contents DB |
| Learning | references/learning.md |
Learning Machines, 6 learning stores (user profile, user memory, session context, entity memory, learned knowledge, decision log), learning modes (Always/Agentic/Propose), custom schemas, namespaces, curator maintenance |
| Skills & Tools | references/agno-skills.md |
Agno Skills (SKILL.md packages, scripts, references, progressive loading), quick tool overview |
More from abhisheksharma-17/skills-graph
remotion-prompt-generator
Generate detailed, production-ready prompts for the Remotion Dev skill to create programmatic React-based videos. MANDATORY TRIGGERS: remotion prompt, video prompt, generate video prompt, remotion video, create video prompt, video brief, video specification, make a video, create a video. Also trigger when user wants to create any kind of video using Remotion, needs help describing a video project, wants a prompt for a video generation tool, or asks for a video brief/spec. When in doubt, use it.
7design-engineering
Comprehensive frontend design engineering system covering the full design lifecycle — planning, building, styling, reviewing, refining, hardening, and upgrading interfaces. MANDATORY TRIGGERS: design, UI, UX, frontend, interface, component, layout, typography, color, animation, responsive, accessibility, critique, audit, polish, redesign, design system, onboarding, micro-interactions, visual design. Also trigger when user asks to build a page, create a component, review a design, improve typography, add animation, fix layout, audit accessibility, redesign an existing project, add delight, make it look professional, or any frontend visual/interaction task. When in doubt about whether to use this skill for any design or frontend task, use it.
2litellm
Unified LLM gateway and SDK for calling 100+ LLM providers (OpenAI, Anthropic, Bedrock, Vertex, Azure, Ollama, etc.) with a single OpenAI-compatible interface. MANDATORY TRIGGERS: litellm, litellm proxy, litellm router, litellm.completion, llm gateway, multi-provider llm, openai-compatible proxy, model fallback, llm cost tracking, llm load balancing. Also trigger when user wants to switch LLM providers without rewriting code, route requests across multiple models, add fallbacks/retries to LLM calls, track token costs, run a self-hosted OpenAI-compatible proxy, or unify observability across providers. When in doubt about whether to use this skill for any multi-provider LLM task, use it.
1livekit
Build realtime voice, video, and AI agent applications with LiveKit. MANDATORY TRIGGERS: livekit, live kit, voice agent, voice AI, realtime audio, realtime video, WebRTC agent, speech-to-speech, voice pipeline, voice assistant framework. Also trigger when user wants to build voice AI agents, realtime communication apps, telephony integrations, video conferencing, or multimodal AI agents with audio/video. When in doubt about whether to use this skill for realtime media or voice AI tasks, use it.
1claude-agent-sdk
Build AI agents programmatically with the Claude Agent SDK (Python and TypeScript). Provides the same tools, agent loop, and context management that power Claude Code, but as a library. MANDATORY TRIGGERS: claude-agent-sdk, claude agent sdk, claude_agent_sdk, @anthropic-ai/claude-agent-sdk, ClaudeAgentOptions, ClaudeSDKClient. Also trigger when user wants to build AI agents with Claude programmatically, create agent loops with tools, use Claude Code SDK, orchestrate subagents, or deploy autonomous coding agents. When in doubt about whether to use this skill for agent SDK tasks, use it.
1