learn-from-session
Analyze Claude Code sessions to learn what went right/wrong and suggest high-confidence improvements to skills. Use when asked to analyze a session, learn from…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,664 results
valinor
Connect to Valinor MAD - meet other AI agents, chat, form friendships, send mail
plan-task
Mandatory unless the user explicitly opts out. Use when non-trivial work on features, bug fixes, refactorings, or changes to code, tests, configuration,…
prepare-task-for-implementation-approval
Mandatory as part of the `plan-task` workflow. Use when an active task already exists and the next agent action would otherwise be to seek implementation…
custom-prompt
[Utilities] Use when the user invokes, lists, saves, updates, or deletes a PROJECT-SPECIFIC saved prompt — a named, reusable procedure stored with the project…
agent-md-refactor
Refactor bloated agent instruction systems — from single files (AGENTS.md, CLAUDE.md) to entire project configurations — into organized, progressive-disclosure…
orchestration
Orchestrate complex work through parallel agent coordination. Decompose requests into task graphs, spawn background workers, and synthesize results elegantly.…
pi-log-analyzer
Pi Agent log analysis tool for analyzing structured JSONL logs in the .log/ directory. Supports multi-dimensional analysis by time/role/module/model, identifies warning patterns, and generates visualization reports. Use this skill when the user mentions "analyze logs", "view logs", "log statistics", "log analysis", "recent activity", "model usage", "session analysis".
role-persona
Role-persona CLI for managing AI agent identity, memory, and knowledge systems. Use this skill when the user wants to: manage roles/identities, view or edit…
handoff
Compact the current conversation into a handoff document for another agent to pick up.
kibana-agent-builder
Create and manage Agent Builder agents and custom tools in Kibana. Use when asked to create, update, delete, test, or inspect agents or tools in Agent Builder.
observability-llm-obs
Monitor LLMs and agentic apps: performance, token/cost, response quality, and workflow orchestration. Use when the user asks about LLM monitoring, GenAI…
evals-create-suite
Scaffold a new LLM evaluation suite package with Playwright config, evaluate fixture, and package files. Use when creating a new eval suite, adding an evals…
build-monetized-app
Use when the task is building a new app on Eliza Cloud that earns money — chat apps, agent apps, MCP-backed tools, anything that calls the cloud's…
astra-efficient-orchestration
Choose a cost-aware Codex agent route for Plus or Pro when the user explicitly asks to optimize multi-agent model usage without sacrificing quality.
langchain-aws
LangChain AWS integration — ChatBedrockConverse (Claude/Nova/Llama/Mistral on Bedrock), BedrockEmbeddings, AmazonKnowledgeBasesRetriever,…
langchain-deepagents
LangChain Deep Agents (Python) — build, deploy, and customize stateful long-running agents with virtual filesystems, subagents, human-in-the-loop, and…
langchain-mcp-adapters
LangChain MCP Adapters — connect LangChain agents to MCP (Model Context Protocol) servers. Load MCP tools, prompts, and resources as LangChain-compatible…
langchain-ollama
LangChain Ollama integration — run local LLMs with ChatOllama (chat completions, tool calling, structured output, reasoning/thinking mode), OllamaLLM (raw text…
langchain-openrouter
LangChain OpenRouter integration — ChatOpenRouter gives access to hundreds of models (Claude, GPT-4o, Gemini, Llama, etc.) through a single API key. Supports…
langchain-perplexity
LangChain Perplexity AI integration — ChatPerplexity (chat model with built-in web search and date/domain filtering), PerplexitySearchRetriever for RAG,…
langchain-postgres
LangChain PostgreSQL integration — PGVectorStore (v2, recommended) and PGVector (v1 legacy) for pgvector RAG, PostgresChatMessageHistory for persistent chat,…
langgraph
LangGraph (Python) — build stateful, controllable agent graphs with checkpointing, streaming, persistence, interrupts, fault tolerance, and durable execution.…
mcp-cloudflare
Manage Workers/KV/R2/D1/Hyperdrive via Cloudflare MCP, perform observability/build troubleshooting/audit/container sandbox operations. Triggers:…