Builds AI agents on Cloudflare using the Agents SDK with state management, real-time WebSockets, scheduled tasks, tool integration, and chat capabilities. Generates production-ready agent code deployed to Workers. Use when: user wants to "build an agent", "AI agent", "chat agent", "stateful agent", mentions "Agents SDK", needs "real-time AI", "WebSocket AI", or asks about agent "state management", "scheduled tasks", or "tool calling". Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
90
86%
Does it follow best practices?
Impact
100%
1.00xAverage score across 3 eval scenarios
Low
Low-risk findings worth noting
State management: setState, SQL storage, and lean state
setState for state updates
100%
100%
SQL table creation in onStart
100%
100%
Parameterized SQL queries
100%
100%
SQL for ticket records
100%
100%
Lean state (no full ticket list in state)
100%
100%
Real-time state sync
100%
100%
onConnect sends queue summary
100%
100%
Correct import source
100%
100%
initialState defined
100%
100%
get_open_tickets uses SQL
100%
100%
Agent project wiring and platform configuration
routeAgentRequest import
100%
100%
routeAgentRequest usage
100%
100%
Agent class exported from index
100%
100%
wrangler.toml durable_objects binding
100%
100%
wrangler.toml migrations entry
100%
100%
wrangler.toml AI binding
100%
100%
wrangler.toml compatibility_date
100%
100%
wrangler.toml main entry
100%
100%
Correct agent import in index
100%
100%
404 fallback response
100%
100%
Scheduled task deduplication and cron syntax
Existing schedule check before daily
100%
100%
Existing schedule check before weekly
100%
100%
Valid daily cron expression
100%
100%
Valid weekly cron expression
100%
100%
One-off reminder uses seconds delay
100%
100%
Callback method names match class methods
100%
100%
Schedule registration in onStart
100%
100%
getSchedules used for listing
100%
100%
Broadcast on digest fire
100%
100%
11c74d6
Table of Contents
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.