Loading...
Loading...
Found 7,688 Skills
Rewrites an existing skill's SKILL.md (or any pipeline workflow document) into a high-quality, strict, prompt-enforced FSM (Finite State Machine)-driven specification. Use when user says "refine skill", "rewrite SKILL.md", "规范化 skill", "改写工作流文档", "优化 skill 文档", or mentions "skill-refiner".
QuestDB integration. Manage data, records, and automate workflows. Use when the user wants to interact with QuestDB data.
Zoho Calendar integration. Manage data, records, and automate workflows. Use when the user wants to interact with Zoho Calendar data.
Autodesk Revit integration. Manage data, records, and automate workflows. Use when the user wants to interact with Autodesk Revit data.
Scaffolds a personal LLM Wiki from scratch — the Karpathy pattern of incrementally building a persistent, interlinked markdown knowledge base maintained by LLMs. Generates directory structure, schema file, index, log, and workflow conventions. Use when user says "create wiki", "new wiki", "bootstrap wiki", "llm wiki", "knowledge base", "start a wiki", "build a wiki", or wants to set up a structured markdown knowledge base for any domain.
Design conversational AI chatbots including intent recognition, slot filling, dialogue flow, and response generation. Use this skill when the user needs to build a chatbot, design conversation flows, implement intent classification, or improve chatbot accuracy — even if they say 'build a chatbot', 'our bot doesn't understand users', 'design a FAQ bot', or 'improve our chatbot's responses'.
Create and manage Telnyx Missions — automated workflows, tasks, and sub-resources for AI-driven telecom operations. This skill provides JavaScript SDK examples.
Building AI agents with the Convex Agent component including thread management, tool integration, streaming responses, RAG patterns, and workflow orchestration
Build AI applications with OpenAI Agents SDK - text agents, voice agents, multi-agent handoffs, tools with Zod schemas, guardrails, and streaming. Prevents 11 documented errors. Use when: building agents with tools, voice agents with WebRTC, multi-agent workflows, or troubleshooting MaxTurnsExceededError, tool call failures, reasoning defaults, JSON output leaks.
Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.
Guide for creating checkout sessions and payment flows with Dodo Payments - one-time, subscriptions, and overlay checkout.
Design ETL workflows with data validation using tools like Pandas, Dask, or PySpark. Use when building robust data processing systems in Python.