Loading...
Loading...
Found 1,564 Skills
Expert in designing effective prompts for LLM-powered applications. Masters prompt structure, context management, output formatting, and prompt evaluation. Use when "prompt engineering, system prompt, few-shot, chain of thought, prompt design, LLM prompt, instruction tuning, prompt template, output format, prompts, llm, gpt, claude, system-prompt, few-shot, chain-of-thought, evaluation" mentioned.
Build voice agents with the Cartesia Line SDK. Supports 100+ LLM providers via LiteLLM with tool calling, multi-agent handoffs, and real-time interruption handling.
Complete knowledge domain for Firecrawl v2 API - web scraping and crawling that converts websites into LLM-ready markdown or structured data. Use when: scraping websites, crawling entire sites, extracting web content, converting HTML to markdown, building web scrapers, handling dynamic JavaScript content, bypassing anti-bot protection, extracting structured data from web pages, or when encountering "content not loading", "JavaScript rendering issues", or "blocked by bot detection". Keywords: firecrawl, firecrawl api, web scraping, web crawler, scrape website, crawl website, extract content, html to markdown, site crawler, content extraction, web automation, firecrawl-py, firecrawl-js, llm ready data, structured data extraction, bot bypass, javascript rendering, scraping api, crawling api, map urls, batch scraping
AI-powered design review for Figma components with weighted dual-scoring system. Evaluates Style Guide Implementation (70%) and LLM Metadata Accessibility (30%). For export, hands off to atomic-design skill.
Optimizes text, prompts, and documentation for LLM token efficiency. Applies 41 research-backed rules across 6 categories: Claude behavior, token efficiency, structure, reference integrity, perception, and LLM comprehension. Use when optimizing prompts, reducing tokens, compressing verbose docs, or improving LLM instruction quality.
Audit an LLM eval pipeline and surface problems: missing error analysis, unvalidated judges, vanity metrics, etc. Use when inheriting an eval system, when unsure whether evals are trustworthy, or as a starting point when no eval infrastructure exists. Do NOT use when the goal is to build a new evaluator from scratch (use error-analysis, write-judge-prompt, or validate-evaluator instead).
Arquitecto de soluciones digitales basadas en IA. Dos modos: (1) ANALIZAR repositorios o código existente y explicar su arquitectura para cualquier audiencia, incluyendo personas sin conocimiento técnico. (2) DISEÑAR la arquitectura completa de sistemas nuevos que usan LLMs, RAG, agentes o fine-tuning. Usa este skill cuando el usuario mencione: arquitectura de IA, diseño de sistema con LLM, capas arquitectónicas, RAG architecture, tech stack para IA, vector database, diagrama de arquitectura, componentes del sistema, embedding, retrieval, pipeline de datos, MLOps, LLMOps, evaluar enfoques, RAG vs fine-tuning, diseñar solución de inteligencia artificial, explicar repositorio, explicar código, analizar proyecto, qué hace este repo, cómo funciona este sistema, explícame este proyecto, o cualquier variación de "qué componentes necesito" o "explícame cómo funciona esto". Actívalo cuando el usuario pegue código, README, estructura de archivos, o mencione un repositorio de GitHub para analizar. También cuando quiera diseñar arquitectura nueva.
Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browser_use, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle hooks, MCP server setup, or monitoring/observability with Laminar or OpenLIT. Also trigger for questions about browser-use installation, prompting strategies, or sensitive data handling. Do NOT use this for Cloud API/SDK usage or pricing — use the cloud skill instead. Do NOT use this for directly automating a browser via CLI commands — use the browser-use skill instead.
Instrument, trace, evaluate, and monitor LLM applications and AI agents with LangSmith. Use when setting up observability for LLM pipelines, running offline or online evaluations, managing prompts in the Prompt Hub, creating datasets for regression testing, or deploying agent servers. Triggers on: langsmith, langchain tracing, llm tracing, llm observability, llm evaluation, trace llm calls, @traceable, wrap_openai, langsmith evaluate, langsmith dataset, langsmith feedback, langsmith prompt hub, langsmith project, llm monitoring, llm debugging, llm quality, openevals, langsmith cli, langsmith experiment, annotate llm, llm judge.
Use when implementing speech-to-text, audio transcription, real-time streaming STT, audio intelligence features, or voice AI using AssemblyAI APIs or SDKs. Use when user mentions AssemblyAI, voice agents, transcription, speaker diarization, PII redaction of audio, LLM Gateway for audio understanding, or applying LLMs to transcripts. Also use when building voice agents with LiveKit or Pipecat that need speech-to-text, or when the user is working with any audio/video processing pipeline that could benefit from transcription, even if they don't mention AssemblyAI by name.
Set up a new Obsidian knowledge base with the LLM Wiki pattern. Use when the user wants to create a second brain, initialize a vault, set up a personal knowledge base, or says "onboard". Guides through an interactive wizard to configure vault name, location, domain, agent support, and tooling.
This skill should be used when the user asks to "evaluate agent performance", "build test framework", "measure agent quality", "create evaluation rubrics", or mentions LLM-as-judge, multi-dimensional evaluation, agent testing, or quality gates for agent pipelines. Part of the context engineering skill suite — also activates when the user mentions "context engineering" or "context-engineering" in the context of measuring agent effectiveness.