Build Stateful Cloudflare Agents
Building durable, real-time agents on Cloudflare Workers requires several coordinated APIs. This skill provides focused patterns for the Agents SDK and related Cloudflare services.
Copia esta solicitud en tu Agente. Incluye la página canónica del Skill y el manifiesto.
Review the Skillstore skill "agents-sdk" from https://skillstore.io/skills/cloudflare-agents-sdk.md and its manifest at https://skillstore.io/api/skills/cloudflare-agents-sdk/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Tu Agente debe seguir mostrando su plan y solicitar cualquier confirmación exigida por la política de seguridad.
Usa estos enlaces cuando un agente de IA, crawler o script necesite contexto limpio en vez de leer la página completa.
Usando "agents-sdk". Create a counter agent with persistent state and a React client.
Resultado esperado:
A project plan covering the Agent class, state updates, route configuration, client hook setup, and reconnection behavior.
Usando "agents-sdk". Design a scheduled report workflow with retries.
Resultado esperado:
Usando "agents-sdk". Review an MCP agent that accesses internal tools.
Resultado esperado:
A focused review of transport choice, authentication, service bindings, tool permissions, error handling, and deployment requirements.
All 163 static findings are false positives caused by Markdown formatting, JavaScript template literals, Cloudflare bindings, explicit request handlers, and documentation URLs. No prompt injection, credential disclosure, shell execution, reconnaissance, or malicious intent was found.
Comparte el informe de evaluación versionado, la insignia neutral, la tarjeta insertable y las citas. Skillstore presenta evidencias sin decidir si este Skill es seguro.
https://skillstore.io/skills/cloudflare-agents-sdk/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report[](https://skillstore.io/skills/cloudflare-agents-sdk?utm_source=security_passport_badge)<a href="https://skillstore.io/skills/cloudflare-agents-sdk?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/cloudflare-agents-sdk/security.svg" alt="Skillstore security assessment" loading="lazy"></a><iframe src="https://skillstore.io/embed/skills/cloudflare-agents-sdk.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>cloudflare. (2026). agents-sdk security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/cloudflare-agents-sdk/audits/1@techreport{cloudflare-cloudflare-agents-sdk-2026,
author = {cloudflare},
title = {agents-sdk security audit report (audit version 1)},
institution = {Skillstore},
year = {2026},
number = {1},
url = {https://skillstore.io/skills/cloudflare-agents-sdk/audits/1},
note = {Author version unspecified}
}cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "agents-sdk security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
- name: "cloudflare"
date-released: "2026-08-09"
url: "https://skillstore.io/skills/cloudflare-agents-sdk/audits/1"
identifiers:
- type: other
value: "skillstore:cloudflare-agents-sdk:audit:1"
description: "Skillstore immutable audit report identifier"
Design a Worker agent that stores conversation state, streams responses, and reconnects clients after interruptions.
Combine schedules, workflows, queues, and retries for long-running tasks that survive Worker restarts.
Build and secure an MCP server that connects agent tools to Cloudflare services and internal bindings.
Create a minimal Cloudflare Agent named [agent name]. Include configuration, routing, persistent state, and one callable method. Explain each required file.
Extend my Cloudflare Agent with streaming chat and a React client. Preserve messages across reconnects and identify the required bindings.
Design a durable process for [task]. Use schedules, workflows, queues, and retries where appropriate. Explain failure recovery and observability.
Review this Agents SDK design for state consistency, authentication, tool approval, secret handling, retries, and deployment configuration. Recommend specific changes.
Autor
cloudflareLicencia
MIT
Revisión de Skillstore
r1
Aviso de versión
El autor no declaró una versión.
Repositorio
https://github.com/cloudflare/skills/tree/f96bff754e428838818017f75817f0f9428acd48/skills/agents-sdkRef.
a919b21bdc3c0214c65d59bf3e5fb10beb5abe62
Actualidad del mantenimiento
10/8/2026
Uso
0 descargas · 0 vistas
Plan Cloudflare One Migrations
Legacy security policies often lack direct Cloudflare One equivalents. This skill builds an accountable migration map, staged rollout, validation plan, and rollback path.
Build Cloudflare K2 Streams With Current Documentation
Cloudflare K2 setup and troubleshooting require current API details, configuration rules, and delivery semantics. This skill directs your assistant to relevant documentation before providing guidance.
Profile Cloudflare Workers CPU and Memory
CPU hotspots and memory allocation pressure can make deployed Workers and Durable Objects difficult to diagnose. This skill guides profiling, evidence analysis, and targeted optimization.
Build Stable Cloudflare Sandbox Apps
Cloudflare Sandbox projects can fail when stable and preview packages, images, or APIs are mixed. This skill keeps implementation aligned with the stable release.
Migrate Cloudflare Sandbox Apps to SDK 1.0
Stable Sandbox applications require coordinated API, image, and deployment changes for SDK 1.0. This skill performs the migration and validates the result.
Manage Cloudflare Resources with the cf CLI
Cloudflare command discovery and mixed Wrangler projects can make terminal workflows difficult to verify. This skill guides command lookup, request previews, authentication, and project-aware execution.
Diseña herramientas de agentes fiables
por Asmayaseen
Los agentes fallan cuando los nombres de las herramientas, las entradas, las salidas o los errores son ambiguos. Esta habilidad ofrece patrones prácticos para descripciones de herramientas, esquemas, formatos de respuesta y pruebas.
Diagnosticar la degradación del contexto en agentes de IA
por ChakshuGautam
Las conversaciones largas y los prompts extensos pueden hacer que los agentes de IA pierdan información importante o sigan contexto conflictivo. Esta skill ayuda a Claude, Codex y Claude Code a identificar patrones de degradación y elegir estrategias de mitigación.
Revisar pull requests con agentes de IA
por Bind
La revisión manual de pull requests puede pasar por alto bugs, errores de lógica e infracciones de las reglas del repositorio. Esta skill coordina varios revisores de IA y valida los hallazgos antes de informar resultados concisos.
Crear la estructura de un plugin de Claude Code
por anthropics
Los autores de plugins necesitan una forma fiable de organizar manifiestos, comandos, agentes, skills, hooks y archivos MCP. Esta skill explica el diseño estándar de Claude Code y muestra patrones prácticos para plugins.
Plan McDonald's Meals by Nutrition and Budget
por hessianz
Choosing meals within nutrition and budget limits requires checking menus, serving sizes, and discounts. Chilemai combines current MCP data with local meal planning and confirmed ordering.
Draft and Schedule Social Posts with TimeToPost
por melmayssonowen
Managing platform-specific posts requires consistent wording, account selection, and approval. This skill guides TimeToPost MCP drafting, timing recommendations, and scheduling after explicit user approval.