O que convex-agents faz?
Construindo agentes de IA com o componente Convex Agent, incluindo gerenciamento de threads, integração de ferramentas, respostas em streaming, padrões RAG e orquestração de fluxos de trabalho.
Construindo agentes de IA com o componente Convex Agent, incluindo gerenciamento de threads, integração de ferramentas, respostas em streaming, padrões RAG e orquestração de fluxos de trabalho
O skill waynesutton/convex-agents capacita desenvolvedores a construir agentes de IA robustos utilizando o componente Convex Agent. Ele oferece suporte completo para gerenciamento de threads, permitindo manter o contexto de conversas de forma eficiente, além de integração com ferramentas externas para expandir as capacidades dos agentes. O skill também implementa respostas em streaming para melhorar a experiência do usuário, padrões RAG (Retrieval-Augmented Generation) para consultar bases de conhecimento, e orquestração de fluxos de trabalho para coordenar múltiplas tarefas. Suportado por plataformas como Convex e frameworks de agentes, ele é ideal para aplicações que exigem interações complexas e dinâmicas com IA, combinando flexibilidade e escalabilidade.
npx skills add https://github.com/waynesutton/convexskills/tree/main/skills/convex-agentsInstalled? Explore more Produtividade e Colaboração skills: steipete/gemini, steipete/gh-issues, steipete/skill-creator · View all 6 →
Construindo agentes de IA com o componente Convex Agent, incluindo gerenciamento de threads, integração de ferramentas, respostas em streaming, padrões RAG e orquestração de fluxos de trabalho.
This repo contains 13 individual skills — each has its own dedicated page.
Prevent feature creep when building software, apps, and AI-powered products. Use this skill when planning features, reviewing scope, building MVPs, managing backlogs, or when a user says "just one more feature." Helps developers and AI agents stay focused, ship faster, and avoid bloated products.
Umbrella skill for all Convex development patterns. Routes to specific skills like convex-functions, convex-realtime, convex-agents, etc.
Guidelines for building production-ready Convex apps covering function organization, query patterns, validation, TypeScript usage, error handling, and the Zen of Convex design philosophy
How to create, structure, and publish self-contained Convex components with proper isolation, exports, and dependency management
Scheduled function patterns for background tasks including interval scheduling, cron expressions, job monitoring, retry strategies, and best practices for long-running tasks
Complete file handling including upload flows, serving files via URL, storing generated files from actions, deletion, and accessing file metadata from system tables
Writing queries, mutations, actions, and HTTP actions with proper argument validation, error handling, internal functions, and runtime considerations
External API integration and webhook handling including HTTP endpoint routing, request/response handling, authentication, CORS configuration, and webhook signature validation
Schema migration strategies for evolving applications including adding new fields, backfilling data, removing deprecated fields, index migrations, and zero-downtime migration patterns
Patterns for building reactive apps including subscription management, optimistic updates, cache behavior, and paginated queries with cursor-based loading
Defining and validating database schemas with proper typing, index configuration, optional fields, unions, and migration strategies for schema changes
Deep security review patterns for authorization logic, data access boundaries, action isolation, rate limiting, and protecting sensitive operations
Quick security audit checklist covering authentication, function exposure, argument validation, row-level access control, and environment variable handling
Gemini CLI one-shot prompts, summaries, generation, skills, hooks, MCP, or Gemma routing.
Fetch GitHub issues, select candidates, spawn background fix agents, open PRs, and optionally process PR review comments.
Create, edit, audit, tidy, validate, or restructure AgentSkills and SKILL.md files.
Search, install, update, sync, or publish agent skills with the ClawHub CLI and registry.
Delegate coding work to Codex, Claude Code, or OpenCode as background workers; not simple edits or read-only code lookup.
List, configure, authenticate, call, and inspect MCP servers/tools with mcporter over HTTP or stdio.