Loading...
Loading...
Found 5,658 Skills
Use when a Luma / 拾光 / 拾光智能体 / 拾光工具 agent needs content research, topic discovery, keyword tables, persona-based search, or Excel-friendly research outputs for short-video planning.
End-to-end Swiggy ordering with Prava card-token checkout. Use when the user wants an AI agent to set up Swiggy MCP, browse/search Swiggy Food/Instamart/Dineout, choose a saved delivery address, add or review Swiggy cart items, create a Prava authorization/payment session, and complete Swiggy checkout using Prava-issued tokenized card credentials. Also use when the user asks to install or configure the Swiggy MCP plus Prava payment flow for agentic purchases.
Research Methodology guides the agent through the complete scientific research lifecycle: hypothesis generation from literature gaps, experimental design with proper controls, systematic literature review, data collection protocols, and peer review preparation.
Shared orchestration engine for the orch-* skill family. Defines the gated Research-Plan-TDD-Review-Commit pipeline, the size classifier, the agent map, and the two human gates that the orch-* operation skills delegate to. Not usually invoked directly.
Run a spec-driven agent loop where coding tasks live as markdown specs that move through inbox → active → archive, get implemented by Claude Code or Codex, and pass a review gate before they count as done. Use when the user mentions "loop factory", a "spec-driven loop", an "agent factory", wants repeatable/reviewable agent work, or when a repo has a factory/specs/inbox or factory/specs/active directory. Also covers installing and scaffolding the loop-factory CLI into a project.
This skill should be used when the user asks to "optimize prompts", "design prompt templates", "evaluate LLM outputs", "build agentic systems", "implement RAG", "create few-shot examples", "analyze token usage", or "design AI workflows". Use for prompt engineering patterns, LLM evaluation frameworks, agent architectures, and structured output design.
Prepare for meetings by gathering context and creating comprehensive agendas
Guides the agent through building LLM-powered applications with LangChain and stateful agent workflows with LangGraph. Triggered when the user asks to "create an AI agent", "build a LangChain chain", "create a LangGraph workflow", "implement tool calling", "build RAG pipeline", "create a multi-agent system", "define agent state", "add human-in-the-loop", "implement streaming", or mentions LangChain, LangGraph, chains, agents, tools, retrieval augmented generation, state graphs, or LLM orchestration.
Task management for session continuity. Use when coordinating multi-step work, managing subagent assignments, or preserving intent across compaction. Triggers on "track tasks", "manage work", "coordinate agents", or when complex work requires sequencing.
Auto-review skill for expert agents. After coding, expert applies elicitation techniques to self-correct before sniper validation. Inspired by BMAD-METHOD.
Inter-agent communication patterns including message passing, shared memory, blackboard systems, and event-driven architectures for LLM agentsUse when "agent communication, message passing, inter-agent, blackboard, agent events, multi-agent, communication, message-passing, events, coordination" mentioned.
Xiaohongshu Copy Optimization Agent System. Specialized in optimizing copy for eyewear products on Xiaohongshu, it supports reading content to be optimized and reference materials, and outputs high-conversion notes that comply with platform specifications. Usage scenarios: When users request to optimize Xiaohongshu eyewear copy, generate Xiaohongshu eyewear notes, or need to refer to platform hot words and writing specifications.